Upload 12 files
Browse files- checkpoint-25000/config.json +61 -0
- checkpoint-25000/generation_config.json +7 -0
- checkpoint-25000/model.safetensors +3 -0
- checkpoint-25000/optimizer.pt +3 -0
- checkpoint-25000/rng_state.pth +3 -0
- checkpoint-25000/scheduler.pt +3 -0
- checkpoint-25000/special_tokens_map.json +125 -0
- checkpoint-25000/spiece.model +3 -0
- checkpoint-25000/tokenizer.json +0 -0
- checkpoint-25000/tokenizer_config.json +940 -0
- checkpoint-25000/trainer_state.json +3582 -0
- checkpoint-25000/training_args.bin +3 -0
checkpoint-25000/config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "GT4SD/multitask-text-and-chemistry-t5-base-standard",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 3072,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "relu",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "relu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": false,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 12,
|
| 22 |
+
"num_heads": 12,
|
| 23 |
+
"num_layers": 12,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"summarization": {
|
| 30 |
+
"early_stopping": true,
|
| 31 |
+
"length_penalty": 2.0,
|
| 32 |
+
"max_length": 200,
|
| 33 |
+
"min_length": 30,
|
| 34 |
+
"no_repeat_ngram_size": 3,
|
| 35 |
+
"num_beams": 4,
|
| 36 |
+
"prefix": "summarize: "
|
| 37 |
+
},
|
| 38 |
+
"translation_en_to_de": {
|
| 39 |
+
"early_stopping": true,
|
| 40 |
+
"max_length": 300,
|
| 41 |
+
"num_beams": 4,
|
| 42 |
+
"prefix": "translate English to German: "
|
| 43 |
+
},
|
| 44 |
+
"translation_en_to_fr": {
|
| 45 |
+
"early_stopping": true,
|
| 46 |
+
"max_length": 300,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"prefix": "translate English to French: "
|
| 49 |
+
},
|
| 50 |
+
"translation_en_to_ro": {
|
| 51 |
+
"early_stopping": true,
|
| 52 |
+
"max_length": 300,
|
| 53 |
+
"num_beams": 4,
|
| 54 |
+
"prefix": "translate English to Romanian: "
|
| 55 |
+
}
|
| 56 |
+
},
|
| 57 |
+
"torch_dtype": "float32",
|
| 58 |
+
"transformers_version": "4.45.2",
|
| 59 |
+
"use_cache": true,
|
| 60 |
+
"vocab_size": 32100
|
| 61 |
+
}
|
checkpoint-25000/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.45.2"
|
| 7 |
+
}
|
checkpoint-25000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c39100af0bc6adf0c405601c49b91c497c5f481b328be26357b9da3ad4bdc5d
|
| 3 |
+
size 891558696
|
checkpoint-25000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f5d032103a0ef7490af078f443b36b1b73f6ae2a79d5a59af3f71ed2f489cb8
|
| 3 |
+
size 495452160
|
checkpoint-25000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c1faa365b2a19109c0f74097224f57f991c418277ffa279c868ec1f20eae322
|
| 3 |
+
size 14244
|
checkpoint-25000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbf3163989c126e14e843fe9fe362827873f7547de16bd53ab3b665abc38493d
|
| 3 |
+
size 1064
|
checkpoint-25000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": {
|
| 105 |
+
"content": "</s>",
|
| 106 |
+
"lstrip": false,
|
| 107 |
+
"normalized": false,
|
| 108 |
+
"rstrip": false,
|
| 109 |
+
"single_word": false
|
| 110 |
+
},
|
| 111 |
+
"pad_token": {
|
| 112 |
+
"content": "<pad>",
|
| 113 |
+
"lstrip": false,
|
| 114 |
+
"normalized": false,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"single_word": false
|
| 117 |
+
},
|
| 118 |
+
"unk_token": {
|
| 119 |
+
"content": "<unk>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false
|
| 124 |
+
}
|
| 125 |
+
}
|
checkpoint-25000/spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
checkpoint-25000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-25000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,940 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<pad>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<unk>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"32000": {
|
| 29 |
+
"content": "<extra_id_99>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"32001": {
|
| 37 |
+
"content": "<extra_id_98>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"32002": {
|
| 45 |
+
"content": "<extra_id_97>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"32003": {
|
| 53 |
+
"content": "<extra_id_96>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"32004": {
|
| 61 |
+
"content": "<extra_id_95>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"32005": {
|
| 69 |
+
"content": "<extra_id_94>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"32006": {
|
| 77 |
+
"content": "<extra_id_93>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"32007": {
|
| 85 |
+
"content": "<extra_id_92>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"32008": {
|
| 93 |
+
"content": "<extra_id_91>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"32009": {
|
| 101 |
+
"content": "<extra_id_90>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"32010": {
|
| 109 |
+
"content": "<extra_id_89>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"32011": {
|
| 117 |
+
"content": "<extra_id_88>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"32012": {
|
| 125 |
+
"content": "<extra_id_87>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"32013": {
|
| 133 |
+
"content": "<extra_id_86>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"32014": {
|
| 141 |
+
"content": "<extra_id_85>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"32015": {
|
| 149 |
+
"content": "<extra_id_84>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"32016": {
|
| 157 |
+
"content": "<extra_id_83>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"32017": {
|
| 165 |
+
"content": "<extra_id_82>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"32018": {
|
| 173 |
+
"content": "<extra_id_81>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"32019": {
|
| 181 |
+
"content": "<extra_id_80>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"32020": {
|
| 189 |
+
"content": "<extra_id_79>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"32021": {
|
| 197 |
+
"content": "<extra_id_78>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"32022": {
|
| 205 |
+
"content": "<extra_id_77>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"32023": {
|
| 213 |
+
"content": "<extra_id_76>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"32024": {
|
| 221 |
+
"content": "<extra_id_75>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"32025": {
|
| 229 |
+
"content": "<extra_id_74>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"32026": {
|
| 237 |
+
"content": "<extra_id_73>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"32027": {
|
| 245 |
+
"content": "<extra_id_72>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"32028": {
|
| 253 |
+
"content": "<extra_id_71>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"32029": {
|
| 261 |
+
"content": "<extra_id_70>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"32030": {
|
| 269 |
+
"content": "<extra_id_69>",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"32031": {
|
| 277 |
+
"content": "<extra_id_68>",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"32032": {
|
| 285 |
+
"content": "<extra_id_67>",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"32033": {
|
| 293 |
+
"content": "<extra_id_66>",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"32034": {
|
| 301 |
+
"content": "<extra_id_65>",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
"32035": {
|
| 309 |
+
"content": "<extra_id_64>",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": false,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": true
|
| 315 |
+
},
|
| 316 |
+
"32036": {
|
| 317 |
+
"content": "<extra_id_63>",
|
| 318 |
+
"lstrip": false,
|
| 319 |
+
"normalized": false,
|
| 320 |
+
"rstrip": false,
|
| 321 |
+
"single_word": false,
|
| 322 |
+
"special": true
|
| 323 |
+
},
|
| 324 |
+
"32037": {
|
| 325 |
+
"content": "<extra_id_62>",
|
| 326 |
+
"lstrip": false,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"rstrip": false,
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"special": true
|
| 331 |
+
},
|
| 332 |
+
"32038": {
|
| 333 |
+
"content": "<extra_id_61>",
|
| 334 |
+
"lstrip": false,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": false,
|
| 337 |
+
"single_word": false,
|
| 338 |
+
"special": true
|
| 339 |
+
},
|
| 340 |
+
"32039": {
|
| 341 |
+
"content": "<extra_id_60>",
|
| 342 |
+
"lstrip": false,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"rstrip": false,
|
| 345 |
+
"single_word": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
"32040": {
|
| 349 |
+
"content": "<extra_id_59>",
|
| 350 |
+
"lstrip": false,
|
| 351 |
+
"normalized": false,
|
| 352 |
+
"rstrip": false,
|
| 353 |
+
"single_word": false,
|
| 354 |
+
"special": true
|
| 355 |
+
},
|
| 356 |
+
"32041": {
|
| 357 |
+
"content": "<extra_id_58>",
|
| 358 |
+
"lstrip": false,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"rstrip": false,
|
| 361 |
+
"single_word": false,
|
| 362 |
+
"special": true
|
| 363 |
+
},
|
| 364 |
+
"32042": {
|
| 365 |
+
"content": "<extra_id_57>",
|
| 366 |
+
"lstrip": false,
|
| 367 |
+
"normalized": false,
|
| 368 |
+
"rstrip": false,
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"special": true
|
| 371 |
+
},
|
| 372 |
+
"32043": {
|
| 373 |
+
"content": "<extra_id_56>",
|
| 374 |
+
"lstrip": false,
|
| 375 |
+
"normalized": false,
|
| 376 |
+
"rstrip": false,
|
| 377 |
+
"single_word": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
"32044": {
|
| 381 |
+
"content": "<extra_id_55>",
|
| 382 |
+
"lstrip": false,
|
| 383 |
+
"normalized": false,
|
| 384 |
+
"rstrip": false,
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"special": true
|
| 387 |
+
},
|
| 388 |
+
"32045": {
|
| 389 |
+
"content": "<extra_id_54>",
|
| 390 |
+
"lstrip": false,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": false,
|
| 393 |
+
"single_word": false,
|
| 394 |
+
"special": true
|
| 395 |
+
},
|
| 396 |
+
"32046": {
|
| 397 |
+
"content": "<extra_id_53>",
|
| 398 |
+
"lstrip": false,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"rstrip": false,
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"special": true
|
| 403 |
+
},
|
| 404 |
+
"32047": {
|
| 405 |
+
"content": "<extra_id_52>",
|
| 406 |
+
"lstrip": false,
|
| 407 |
+
"normalized": false,
|
| 408 |
+
"rstrip": false,
|
| 409 |
+
"single_word": false,
|
| 410 |
+
"special": true
|
| 411 |
+
},
|
| 412 |
+
"32048": {
|
| 413 |
+
"content": "<extra_id_51>",
|
| 414 |
+
"lstrip": false,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"rstrip": false,
|
| 417 |
+
"single_word": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
"32049": {
|
| 421 |
+
"content": "<extra_id_50>",
|
| 422 |
+
"lstrip": false,
|
| 423 |
+
"normalized": false,
|
| 424 |
+
"rstrip": false,
|
| 425 |
+
"single_word": false,
|
| 426 |
+
"special": true
|
| 427 |
+
},
|
| 428 |
+
"32050": {
|
| 429 |
+
"content": "<extra_id_49>",
|
| 430 |
+
"lstrip": false,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"rstrip": false,
|
| 433 |
+
"single_word": false,
|
| 434 |
+
"special": true
|
| 435 |
+
},
|
| 436 |
+
"32051": {
|
| 437 |
+
"content": "<extra_id_48>",
|
| 438 |
+
"lstrip": false,
|
| 439 |
+
"normalized": false,
|
| 440 |
+
"rstrip": false,
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"special": true
|
| 443 |
+
},
|
| 444 |
+
"32052": {
|
| 445 |
+
"content": "<extra_id_47>",
|
| 446 |
+
"lstrip": false,
|
| 447 |
+
"normalized": false,
|
| 448 |
+
"rstrip": false,
|
| 449 |
+
"single_word": false,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
"32053": {
|
| 453 |
+
"content": "<extra_id_46>",
|
| 454 |
+
"lstrip": false,
|
| 455 |
+
"normalized": false,
|
| 456 |
+
"rstrip": false,
|
| 457 |
+
"single_word": false,
|
| 458 |
+
"special": true
|
| 459 |
+
},
|
| 460 |
+
"32054": {
|
| 461 |
+
"content": "<extra_id_45>",
|
| 462 |
+
"lstrip": false,
|
| 463 |
+
"normalized": false,
|
| 464 |
+
"rstrip": false,
|
| 465 |
+
"single_word": false,
|
| 466 |
+
"special": true
|
| 467 |
+
},
|
| 468 |
+
"32055": {
|
| 469 |
+
"content": "<extra_id_44>",
|
| 470 |
+
"lstrip": false,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"rstrip": false,
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"special": true
|
| 475 |
+
},
|
| 476 |
+
"32056": {
|
| 477 |
+
"content": "<extra_id_43>",
|
| 478 |
+
"lstrip": false,
|
| 479 |
+
"normalized": false,
|
| 480 |
+
"rstrip": false,
|
| 481 |
+
"single_word": false,
|
| 482 |
+
"special": true
|
| 483 |
+
},
|
| 484 |
+
"32057": {
|
| 485 |
+
"content": "<extra_id_42>",
|
| 486 |
+
"lstrip": false,
|
| 487 |
+
"normalized": false,
|
| 488 |
+
"rstrip": false,
|
| 489 |
+
"single_word": false,
|
| 490 |
+
"special": true
|
| 491 |
+
},
|
| 492 |
+
"32058": {
|
| 493 |
+
"content": "<extra_id_41>",
|
| 494 |
+
"lstrip": false,
|
| 495 |
+
"normalized": false,
|
| 496 |
+
"rstrip": false,
|
| 497 |
+
"single_word": false,
|
| 498 |
+
"special": true
|
| 499 |
+
},
|
| 500 |
+
"32059": {
|
| 501 |
+
"content": "<extra_id_40>",
|
| 502 |
+
"lstrip": false,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"rstrip": false,
|
| 505 |
+
"single_word": false,
|
| 506 |
+
"special": true
|
| 507 |
+
},
|
| 508 |
+
"32060": {
|
| 509 |
+
"content": "<extra_id_39>",
|
| 510 |
+
"lstrip": false,
|
| 511 |
+
"normalized": false,
|
| 512 |
+
"rstrip": false,
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"special": true
|
| 515 |
+
},
|
| 516 |
+
"32061": {
|
| 517 |
+
"content": "<extra_id_38>",
|
| 518 |
+
"lstrip": false,
|
| 519 |
+
"normalized": false,
|
| 520 |
+
"rstrip": false,
|
| 521 |
+
"single_word": false,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
"32062": {
|
| 525 |
+
"content": "<extra_id_37>",
|
| 526 |
+
"lstrip": false,
|
| 527 |
+
"normalized": false,
|
| 528 |
+
"rstrip": false,
|
| 529 |
+
"single_word": false,
|
| 530 |
+
"special": true
|
| 531 |
+
},
|
| 532 |
+
"32063": {
|
| 533 |
+
"content": "<extra_id_36>",
|
| 534 |
+
"lstrip": false,
|
| 535 |
+
"normalized": false,
|
| 536 |
+
"rstrip": false,
|
| 537 |
+
"single_word": false,
|
| 538 |
+
"special": true
|
| 539 |
+
},
|
| 540 |
+
"32064": {
|
| 541 |
+
"content": "<extra_id_35>",
|
| 542 |
+
"lstrip": false,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"rstrip": false,
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"special": true
|
| 547 |
+
},
|
| 548 |
+
"32065": {
|
| 549 |
+
"content": "<extra_id_34>",
|
| 550 |
+
"lstrip": false,
|
| 551 |
+
"normalized": false,
|
| 552 |
+
"rstrip": false,
|
| 553 |
+
"single_word": false,
|
| 554 |
+
"special": true
|
| 555 |
+
},
|
| 556 |
+
"32066": {
|
| 557 |
+
"content": "<extra_id_33>",
|
| 558 |
+
"lstrip": false,
|
| 559 |
+
"normalized": false,
|
| 560 |
+
"rstrip": false,
|
| 561 |
+
"single_word": false,
|
| 562 |
+
"special": true
|
| 563 |
+
},
|
| 564 |
+
"32067": {
|
| 565 |
+
"content": "<extra_id_32>",
|
| 566 |
+
"lstrip": false,
|
| 567 |
+
"normalized": false,
|
| 568 |
+
"rstrip": false,
|
| 569 |
+
"single_word": false,
|
| 570 |
+
"special": true
|
| 571 |
+
},
|
| 572 |
+
"32068": {
|
| 573 |
+
"content": "<extra_id_31>",
|
| 574 |
+
"lstrip": false,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"rstrip": false,
|
| 577 |
+
"single_word": false,
|
| 578 |
+
"special": true
|
| 579 |
+
},
|
| 580 |
+
"32069": {
|
| 581 |
+
"content": "<extra_id_30>",
|
| 582 |
+
"lstrip": false,
|
| 583 |
+
"normalized": false,
|
| 584 |
+
"rstrip": false,
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"special": true
|
| 587 |
+
},
|
| 588 |
+
"32070": {
|
| 589 |
+
"content": "<extra_id_29>",
|
| 590 |
+
"lstrip": false,
|
| 591 |
+
"normalized": false,
|
| 592 |
+
"rstrip": false,
|
| 593 |
+
"single_word": false,
|
| 594 |
+
"special": true
|
| 595 |
+
},
|
| 596 |
+
"32071": {
|
| 597 |
+
"content": "<extra_id_28>",
|
| 598 |
+
"lstrip": false,
|
| 599 |
+
"normalized": false,
|
| 600 |
+
"rstrip": false,
|
| 601 |
+
"single_word": false,
|
| 602 |
+
"special": true
|
| 603 |
+
},
|
| 604 |
+
"32072": {
|
| 605 |
+
"content": "<extra_id_27>",
|
| 606 |
+
"lstrip": false,
|
| 607 |
+
"normalized": false,
|
| 608 |
+
"rstrip": false,
|
| 609 |
+
"single_word": false,
|
| 610 |
+
"special": true
|
| 611 |
+
},
|
| 612 |
+
"32073": {
|
| 613 |
+
"content": "<extra_id_26>",
|
| 614 |
+
"lstrip": false,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"rstrip": false,
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"special": true
|
| 619 |
+
},
|
| 620 |
+
"32074": {
|
| 621 |
+
"content": "<extra_id_25>",
|
| 622 |
+
"lstrip": false,
|
| 623 |
+
"normalized": false,
|
| 624 |
+
"rstrip": false,
|
| 625 |
+
"single_word": false,
|
| 626 |
+
"special": true
|
| 627 |
+
},
|
| 628 |
+
"32075": {
|
| 629 |
+
"content": "<extra_id_24>",
|
| 630 |
+
"lstrip": false,
|
| 631 |
+
"normalized": false,
|
| 632 |
+
"rstrip": false,
|
| 633 |
+
"single_word": false,
|
| 634 |
+
"special": true
|
| 635 |
+
},
|
| 636 |
+
"32076": {
|
| 637 |
+
"content": "<extra_id_23>",
|
| 638 |
+
"lstrip": false,
|
| 639 |
+
"normalized": false,
|
| 640 |
+
"rstrip": false,
|
| 641 |
+
"single_word": false,
|
| 642 |
+
"special": true
|
| 643 |
+
},
|
| 644 |
+
"32077": {
|
| 645 |
+
"content": "<extra_id_22>",
|
| 646 |
+
"lstrip": false,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"rstrip": false,
|
| 649 |
+
"single_word": false,
|
| 650 |
+
"special": true
|
| 651 |
+
},
|
| 652 |
+
"32078": {
|
| 653 |
+
"content": "<extra_id_21>",
|
| 654 |
+
"lstrip": false,
|
| 655 |
+
"normalized": false,
|
| 656 |
+
"rstrip": false,
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"special": true
|
| 659 |
+
},
|
| 660 |
+
"32079": {
|
| 661 |
+
"content": "<extra_id_20>",
|
| 662 |
+
"lstrip": false,
|
| 663 |
+
"normalized": false,
|
| 664 |
+
"rstrip": false,
|
| 665 |
+
"single_word": false,
|
| 666 |
+
"special": true
|
| 667 |
+
},
|
| 668 |
+
"32080": {
|
| 669 |
+
"content": "<extra_id_19>",
|
| 670 |
+
"lstrip": false,
|
| 671 |
+
"normalized": false,
|
| 672 |
+
"rstrip": false,
|
| 673 |
+
"single_word": false,
|
| 674 |
+
"special": true
|
| 675 |
+
},
|
| 676 |
+
"32081": {
|
| 677 |
+
"content": "<extra_id_18>",
|
| 678 |
+
"lstrip": false,
|
| 679 |
+
"normalized": false,
|
| 680 |
+
"rstrip": false,
|
| 681 |
+
"single_word": false,
|
| 682 |
+
"special": true
|
| 683 |
+
},
|
| 684 |
+
"32082": {
|
| 685 |
+
"content": "<extra_id_17>",
|
| 686 |
+
"lstrip": false,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"rstrip": false,
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"special": true
|
| 691 |
+
},
|
| 692 |
+
"32083": {
|
| 693 |
+
"content": "<extra_id_16>",
|
| 694 |
+
"lstrip": false,
|
| 695 |
+
"normalized": false,
|
| 696 |
+
"rstrip": false,
|
| 697 |
+
"single_word": false,
|
| 698 |
+
"special": true
|
| 699 |
+
},
|
| 700 |
+
"32084": {
|
| 701 |
+
"content": "<extra_id_15>",
|
| 702 |
+
"lstrip": false,
|
| 703 |
+
"normalized": false,
|
| 704 |
+
"rstrip": false,
|
| 705 |
+
"single_word": false,
|
| 706 |
+
"special": true
|
| 707 |
+
},
|
| 708 |
+
"32085": {
|
| 709 |
+
"content": "<extra_id_14>",
|
| 710 |
+
"lstrip": false,
|
| 711 |
+
"normalized": false,
|
| 712 |
+
"rstrip": false,
|
| 713 |
+
"single_word": false,
|
| 714 |
+
"special": true
|
| 715 |
+
},
|
| 716 |
+
"32086": {
|
| 717 |
+
"content": "<extra_id_13>",
|
| 718 |
+
"lstrip": false,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"rstrip": false,
|
| 721 |
+
"single_word": false,
|
| 722 |
+
"special": true
|
| 723 |
+
},
|
| 724 |
+
"32087": {
|
| 725 |
+
"content": "<extra_id_12>",
|
| 726 |
+
"lstrip": false,
|
| 727 |
+
"normalized": false,
|
| 728 |
+
"rstrip": false,
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"special": true
|
| 731 |
+
},
|
| 732 |
+
"32088": {
|
| 733 |
+
"content": "<extra_id_11>",
|
| 734 |
+
"lstrip": false,
|
| 735 |
+
"normalized": false,
|
| 736 |
+
"rstrip": false,
|
| 737 |
+
"single_word": false,
|
| 738 |
+
"special": true
|
| 739 |
+
},
|
| 740 |
+
"32089": {
|
| 741 |
+
"content": "<extra_id_10>",
|
| 742 |
+
"lstrip": false,
|
| 743 |
+
"normalized": false,
|
| 744 |
+
"rstrip": false,
|
| 745 |
+
"single_word": false,
|
| 746 |
+
"special": true
|
| 747 |
+
},
|
| 748 |
+
"32090": {
|
| 749 |
+
"content": "<extra_id_9>",
|
| 750 |
+
"lstrip": false,
|
| 751 |
+
"normalized": false,
|
| 752 |
+
"rstrip": false,
|
| 753 |
+
"single_word": false,
|
| 754 |
+
"special": true
|
| 755 |
+
},
|
| 756 |
+
"32091": {
|
| 757 |
+
"content": "<extra_id_8>",
|
| 758 |
+
"lstrip": false,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"rstrip": false,
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"special": true
|
| 763 |
+
},
|
| 764 |
+
"32092": {
|
| 765 |
+
"content": "<extra_id_7>",
|
| 766 |
+
"lstrip": false,
|
| 767 |
+
"normalized": false,
|
| 768 |
+
"rstrip": false,
|
| 769 |
+
"single_word": false,
|
| 770 |
+
"special": true
|
| 771 |
+
},
|
| 772 |
+
"32093": {
|
| 773 |
+
"content": "<extra_id_6>",
|
| 774 |
+
"lstrip": false,
|
| 775 |
+
"normalized": false,
|
| 776 |
+
"rstrip": false,
|
| 777 |
+
"single_word": false,
|
| 778 |
+
"special": true
|
| 779 |
+
},
|
| 780 |
+
"32094": {
|
| 781 |
+
"content": "<extra_id_5>",
|
| 782 |
+
"lstrip": false,
|
| 783 |
+
"normalized": false,
|
| 784 |
+
"rstrip": false,
|
| 785 |
+
"single_word": false,
|
| 786 |
+
"special": true
|
| 787 |
+
},
|
| 788 |
+
"32095": {
|
| 789 |
+
"content": "<extra_id_4>",
|
| 790 |
+
"lstrip": false,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"rstrip": false,
|
| 793 |
+
"single_word": false,
|
| 794 |
+
"special": true
|
| 795 |
+
},
|
| 796 |
+
"32096": {
|
| 797 |
+
"content": "<extra_id_3>",
|
| 798 |
+
"lstrip": false,
|
| 799 |
+
"normalized": false,
|
| 800 |
+
"rstrip": false,
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"special": true
|
| 803 |
+
},
|
| 804 |
+
"32097": {
|
| 805 |
+
"content": "<extra_id_2>",
|
| 806 |
+
"lstrip": false,
|
| 807 |
+
"normalized": false,
|
| 808 |
+
"rstrip": false,
|
| 809 |
+
"single_word": false,
|
| 810 |
+
"special": true
|
| 811 |
+
},
|
| 812 |
+
"32098": {
|
| 813 |
+
"content": "<extra_id_1>",
|
| 814 |
+
"lstrip": false,
|
| 815 |
+
"normalized": false,
|
| 816 |
+
"rstrip": false,
|
| 817 |
+
"single_word": false,
|
| 818 |
+
"special": true
|
| 819 |
+
},
|
| 820 |
+
"32099": {
|
| 821 |
+
"content": "<extra_id_0>",
|
| 822 |
+
"lstrip": false,
|
| 823 |
+
"normalized": false,
|
| 824 |
+
"rstrip": false,
|
| 825 |
+
"single_word": false,
|
| 826 |
+
"special": true
|
| 827 |
+
}
|
| 828 |
+
},
|
| 829 |
+
"additional_special_tokens": [
|
| 830 |
+
"<extra_id_0>",
|
| 831 |
+
"<extra_id_1>",
|
| 832 |
+
"<extra_id_2>",
|
| 833 |
+
"<extra_id_3>",
|
| 834 |
+
"<extra_id_4>",
|
| 835 |
+
"<extra_id_5>",
|
| 836 |
+
"<extra_id_6>",
|
| 837 |
+
"<extra_id_7>",
|
| 838 |
+
"<extra_id_8>",
|
| 839 |
+
"<extra_id_9>",
|
| 840 |
+
"<extra_id_10>",
|
| 841 |
+
"<extra_id_11>",
|
| 842 |
+
"<extra_id_12>",
|
| 843 |
+
"<extra_id_13>",
|
| 844 |
+
"<extra_id_14>",
|
| 845 |
+
"<extra_id_15>",
|
| 846 |
+
"<extra_id_16>",
|
| 847 |
+
"<extra_id_17>",
|
| 848 |
+
"<extra_id_18>",
|
| 849 |
+
"<extra_id_19>",
|
| 850 |
+
"<extra_id_20>",
|
| 851 |
+
"<extra_id_21>",
|
| 852 |
+
"<extra_id_22>",
|
| 853 |
+
"<extra_id_23>",
|
| 854 |
+
"<extra_id_24>",
|
| 855 |
+
"<extra_id_25>",
|
| 856 |
+
"<extra_id_26>",
|
| 857 |
+
"<extra_id_27>",
|
| 858 |
+
"<extra_id_28>",
|
| 859 |
+
"<extra_id_29>",
|
| 860 |
+
"<extra_id_30>",
|
| 861 |
+
"<extra_id_31>",
|
| 862 |
+
"<extra_id_32>",
|
| 863 |
+
"<extra_id_33>",
|
| 864 |
+
"<extra_id_34>",
|
| 865 |
+
"<extra_id_35>",
|
| 866 |
+
"<extra_id_36>",
|
| 867 |
+
"<extra_id_37>",
|
| 868 |
+
"<extra_id_38>",
|
| 869 |
+
"<extra_id_39>",
|
| 870 |
+
"<extra_id_40>",
|
| 871 |
+
"<extra_id_41>",
|
| 872 |
+
"<extra_id_42>",
|
| 873 |
+
"<extra_id_43>",
|
| 874 |
+
"<extra_id_44>",
|
| 875 |
+
"<extra_id_45>",
|
| 876 |
+
"<extra_id_46>",
|
| 877 |
+
"<extra_id_47>",
|
| 878 |
+
"<extra_id_48>",
|
| 879 |
+
"<extra_id_49>",
|
| 880 |
+
"<extra_id_50>",
|
| 881 |
+
"<extra_id_51>",
|
| 882 |
+
"<extra_id_52>",
|
| 883 |
+
"<extra_id_53>",
|
| 884 |
+
"<extra_id_54>",
|
| 885 |
+
"<extra_id_55>",
|
| 886 |
+
"<extra_id_56>",
|
| 887 |
+
"<extra_id_57>",
|
| 888 |
+
"<extra_id_58>",
|
| 889 |
+
"<extra_id_59>",
|
| 890 |
+
"<extra_id_60>",
|
| 891 |
+
"<extra_id_61>",
|
| 892 |
+
"<extra_id_62>",
|
| 893 |
+
"<extra_id_63>",
|
| 894 |
+
"<extra_id_64>",
|
| 895 |
+
"<extra_id_65>",
|
| 896 |
+
"<extra_id_66>",
|
| 897 |
+
"<extra_id_67>",
|
| 898 |
+
"<extra_id_68>",
|
| 899 |
+
"<extra_id_69>",
|
| 900 |
+
"<extra_id_70>",
|
| 901 |
+
"<extra_id_71>",
|
| 902 |
+
"<extra_id_72>",
|
| 903 |
+
"<extra_id_73>",
|
| 904 |
+
"<extra_id_74>",
|
| 905 |
+
"<extra_id_75>",
|
| 906 |
+
"<extra_id_76>",
|
| 907 |
+
"<extra_id_77>",
|
| 908 |
+
"<extra_id_78>",
|
| 909 |
+
"<extra_id_79>",
|
| 910 |
+
"<extra_id_80>",
|
| 911 |
+
"<extra_id_81>",
|
| 912 |
+
"<extra_id_82>",
|
| 913 |
+
"<extra_id_83>",
|
| 914 |
+
"<extra_id_84>",
|
| 915 |
+
"<extra_id_85>",
|
| 916 |
+
"<extra_id_86>",
|
| 917 |
+
"<extra_id_87>",
|
| 918 |
+
"<extra_id_88>",
|
| 919 |
+
"<extra_id_89>",
|
| 920 |
+
"<extra_id_90>",
|
| 921 |
+
"<extra_id_91>",
|
| 922 |
+
"<extra_id_92>",
|
| 923 |
+
"<extra_id_93>",
|
| 924 |
+
"<extra_id_94>",
|
| 925 |
+
"<extra_id_95>",
|
| 926 |
+
"<extra_id_96>",
|
| 927 |
+
"<extra_id_97>",
|
| 928 |
+
"<extra_id_98>",
|
| 929 |
+
"<extra_id_99>"
|
| 930 |
+
],
|
| 931 |
+
"clean_up_tokenization_spaces": false,
|
| 932 |
+
"eos_token": "</s>",
|
| 933 |
+
"extra_ids": 100,
|
| 934 |
+
"legacy": true,
|
| 935 |
+
"model_max_length": 512,
|
| 936 |
+
"pad_token": "<pad>",
|
| 937 |
+
"sp_model_kwargs": {},
|
| 938 |
+
"tokenizer_class": "T5Tokenizer",
|
| 939 |
+
"unk_token": "<unk>"
|
| 940 |
+
}
|
checkpoint-25000/trainer_state.json
ADDED
|
@@ -0,0 +1,3582 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.3424564003944397,
|
| 3 |
+
"best_model_checkpoint": "./results/chembl.trans_only_T5Chem_dmodel512_layers12_batch120_lr0.0005_train0.80/checkpoint-25000",
|
| 4 |
+
"epoch": 1.4214236979758925,
|
| 5 |
+
"eval_steps": 5000,
|
| 6 |
+
"global_step": 25000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.002842847395951785,
|
| 13 |
+
"grad_norm": 0.4646081328392029,
|
| 14 |
+
"learning_rate": 0.0004999955580509438,
|
| 15 |
+
"loss": 0.6585,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.00568569479190357,
|
| 20 |
+
"grad_norm": 0.19792014360427856,
|
| 21 |
+
"learning_rate": 0.0004999911161018877,
|
| 22 |
+
"loss": 0.53,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.008528542187855356,
|
| 27 |
+
"grad_norm": 0.16343972086906433,
|
| 28 |
+
"learning_rate": 0.0004999866741528315,
|
| 29 |
+
"loss": 0.5034,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.01137138958380714,
|
| 34 |
+
"grad_norm": 0.20607765018939972,
|
| 35 |
+
"learning_rate": 0.0004999822322037754,
|
| 36 |
+
"loss": 0.496,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.014214236979758927,
|
| 41 |
+
"grad_norm": 0.14076846837997437,
|
| 42 |
+
"learning_rate": 0.0004999777902547192,
|
| 43 |
+
"loss": 0.4841,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.017057084375710713,
|
| 48 |
+
"grad_norm": 0.12710894644260406,
|
| 49 |
+
"learning_rate": 0.000499973348305663,
|
| 50 |
+
"loss": 0.4816,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.019899931771662497,
|
| 55 |
+
"grad_norm": 0.1586833894252777,
|
| 56 |
+
"learning_rate": 0.0004999689063566068,
|
| 57 |
+
"loss": 0.477,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.02274277916761428,
|
| 62 |
+
"grad_norm": 0.18906599283218384,
|
| 63 |
+
"learning_rate": 0.0004999644644075506,
|
| 64 |
+
"loss": 0.4743,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.02558562656356607,
|
| 69 |
+
"grad_norm": 0.14747406542301178,
|
| 70 |
+
"learning_rate": 0.0004999600224584944,
|
| 71 |
+
"loss": 0.465,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.028428473959517853,
|
| 76 |
+
"grad_norm": 0.15983326733112335,
|
| 77 |
+
"learning_rate": 0.0004999555805094383,
|
| 78 |
+
"loss": 0.4647,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.03127132135546964,
|
| 83 |
+
"grad_norm": 0.14171165227890015,
|
| 84 |
+
"learning_rate": 0.0004999511385603821,
|
| 85 |
+
"loss": 0.4603,
|
| 86 |
+
"step": 550
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.034114168751421425,
|
| 90 |
+
"grad_norm": 0.13967591524124146,
|
| 91 |
+
"learning_rate": 0.0004999466966113259,
|
| 92 |
+
"loss": 0.4574,
|
| 93 |
+
"step": 600
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.036957016147373206,
|
| 97 |
+
"grad_norm": 0.2039215862751007,
|
| 98 |
+
"learning_rate": 0.0004999422546622698,
|
| 99 |
+
"loss": 0.4536,
|
| 100 |
+
"step": 650
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.039799863543324994,
|
| 104 |
+
"grad_norm": 0.15800215303897858,
|
| 105 |
+
"learning_rate": 0.0004999378127132136,
|
| 106 |
+
"loss": 0.4544,
|
| 107 |
+
"step": 700
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.04264271093927678,
|
| 111 |
+
"grad_norm": 0.16743983328342438,
|
| 112 |
+
"learning_rate": 0.0004999333707641574,
|
| 113 |
+
"loss": 0.4528,
|
| 114 |
+
"step": 750
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.04548555833522856,
|
| 118 |
+
"grad_norm": 0.16410502791404724,
|
| 119 |
+
"learning_rate": 0.0004999289288151012,
|
| 120 |
+
"loss": 0.4498,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.04832840573118035,
|
| 125 |
+
"grad_norm": 0.17722439765930176,
|
| 126 |
+
"learning_rate": 0.000499924486866045,
|
| 127 |
+
"loss": 0.4461,
|
| 128 |
+
"step": 850
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.05117125312713214,
|
| 132 |
+
"grad_norm": 0.13122214376926422,
|
| 133 |
+
"learning_rate": 0.0004999200449169889,
|
| 134 |
+
"loss": 0.4422,
|
| 135 |
+
"step": 900
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.05401410052308392,
|
| 139 |
+
"grad_norm": 0.1328468769788742,
|
| 140 |
+
"learning_rate": 0.0004999156029679327,
|
| 141 |
+
"loss": 0.4438,
|
| 142 |
+
"step": 950
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.05685694791903571,
|
| 146 |
+
"grad_norm": 0.1839675009250641,
|
| 147 |
+
"learning_rate": 0.0004999111610188765,
|
| 148 |
+
"loss": 0.4429,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.059699795314987494,
|
| 153 |
+
"grad_norm": 0.14567476511001587,
|
| 154 |
+
"learning_rate": 0.0004999067190698203,
|
| 155 |
+
"loss": 0.4356,
|
| 156 |
+
"step": 1050
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.06254264271093928,
|
| 160 |
+
"grad_norm": 0.1527237445116043,
|
| 161 |
+
"learning_rate": 0.0004999022771207641,
|
| 162 |
+
"loss": 0.438,
|
| 163 |
+
"step": 1100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.06538549010689106,
|
| 167 |
+
"grad_norm": 0.1287076622247696,
|
| 168 |
+
"learning_rate": 0.000499897835171708,
|
| 169 |
+
"loss": 0.4343,
|
| 170 |
+
"step": 1150
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.06822833750284285,
|
| 174 |
+
"grad_norm": 0.11131107807159424,
|
| 175 |
+
"learning_rate": 0.0004998933932226518,
|
| 176 |
+
"loss": 0.4367,
|
| 177 |
+
"step": 1200
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.07107118489879463,
|
| 181 |
+
"grad_norm": 0.13373662531375885,
|
| 182 |
+
"learning_rate": 0.0004998889512735956,
|
| 183 |
+
"loss": 0.4316,
|
| 184 |
+
"step": 1250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.07391403229474641,
|
| 188 |
+
"grad_norm": 0.13251946866512299,
|
| 189 |
+
"learning_rate": 0.0004998845093245395,
|
| 190 |
+
"loss": 0.4347,
|
| 191 |
+
"step": 1300
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.07675687969069821,
|
| 195 |
+
"grad_norm": 0.14924846589565277,
|
| 196 |
+
"learning_rate": 0.0004998800673754833,
|
| 197 |
+
"loss": 0.4315,
|
| 198 |
+
"step": 1350
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.07959972708664999,
|
| 202 |
+
"grad_norm": 0.12222905457019806,
|
| 203 |
+
"learning_rate": 0.0004998756254264271,
|
| 204 |
+
"loss": 0.4311,
|
| 205 |
+
"step": 1400
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.08244257448260177,
|
| 209 |
+
"grad_norm": 0.10474367439746857,
|
| 210 |
+
"learning_rate": 0.0004998711834773709,
|
| 211 |
+
"loss": 0.4289,
|
| 212 |
+
"step": 1450
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.08528542187855356,
|
| 216 |
+
"grad_norm": 0.11413396149873734,
|
| 217 |
+
"learning_rate": 0.0004998667415283148,
|
| 218 |
+
"loss": 0.4287,
|
| 219 |
+
"step": 1500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.08812826927450534,
|
| 223 |
+
"grad_norm": 0.1532815843820572,
|
| 224 |
+
"learning_rate": 0.0004998622995792587,
|
| 225 |
+
"loss": 0.4266,
|
| 226 |
+
"step": 1550
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.09097111667045713,
|
| 230 |
+
"grad_norm": 0.16395249962806702,
|
| 231 |
+
"learning_rate": 0.0004998578576302025,
|
| 232 |
+
"loss": 0.4254,
|
| 233 |
+
"step": 1600
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.09381396406640892,
|
| 237 |
+
"grad_norm": 0.13058966398239136,
|
| 238 |
+
"learning_rate": 0.0004998534156811463,
|
| 239 |
+
"loss": 0.4236,
|
| 240 |
+
"step": 1650
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.0966568114623607,
|
| 244 |
+
"grad_norm": 0.15570798516273499,
|
| 245 |
+
"learning_rate": 0.0004998489737320901,
|
| 246 |
+
"loss": 0.4267,
|
| 247 |
+
"step": 1700
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.09949965885831248,
|
| 251 |
+
"grad_norm": 0.1350376456975937,
|
| 252 |
+
"learning_rate": 0.0004998445317830339,
|
| 253 |
+
"loss": 0.421,
|
| 254 |
+
"step": 1750
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.10234250625426428,
|
| 258 |
+
"grad_norm": 0.13523083925247192,
|
| 259 |
+
"learning_rate": 0.0004998400898339777,
|
| 260 |
+
"loss": 0.4212,
|
| 261 |
+
"step": 1800
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.10518535365021606,
|
| 265 |
+
"grad_norm": 0.12544061243534088,
|
| 266 |
+
"learning_rate": 0.0004998356478849215,
|
| 267 |
+
"loss": 0.424,
|
| 268 |
+
"step": 1850
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.10802820104616784,
|
| 272 |
+
"grad_norm": 0.12443090230226517,
|
| 273 |
+
"learning_rate": 0.0004998312059358654,
|
| 274 |
+
"loss": 0.4217,
|
| 275 |
+
"step": 1900
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.11087104844211963,
|
| 279 |
+
"grad_norm": 0.11098171025514603,
|
| 280 |
+
"learning_rate": 0.0004998267639868092,
|
| 281 |
+
"loss": 0.4226,
|
| 282 |
+
"step": 1950
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.11371389583807141,
|
| 286 |
+
"grad_norm": 0.129473477602005,
|
| 287 |
+
"learning_rate": 0.000499822322037753,
|
| 288 |
+
"loss": 0.4237,
|
| 289 |
+
"step": 2000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.1165567432340232,
|
| 293 |
+
"grad_norm": 0.1107649877667427,
|
| 294 |
+
"learning_rate": 0.0004998178800886969,
|
| 295 |
+
"loss": 0.4241,
|
| 296 |
+
"step": 2050
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.11939959062997499,
|
| 300 |
+
"grad_norm": 0.12195456773042679,
|
| 301 |
+
"learning_rate": 0.0004998134381396407,
|
| 302 |
+
"loss": 0.4176,
|
| 303 |
+
"step": 2100
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.12224243802592677,
|
| 307 |
+
"grad_norm": 0.12097357213497162,
|
| 308 |
+
"learning_rate": 0.0004998089961905845,
|
| 309 |
+
"loss": 0.4156,
|
| 310 |
+
"step": 2150
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.12508528542187855,
|
| 314 |
+
"grad_norm": 0.11261444538831711,
|
| 315 |
+
"learning_rate": 0.0004998045542415283,
|
| 316 |
+
"loss": 0.4179,
|
| 317 |
+
"step": 2200
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.12792813281783033,
|
| 321 |
+
"grad_norm": 0.13488833606243134,
|
| 322 |
+
"learning_rate": 0.0004998001122924721,
|
| 323 |
+
"loss": 0.4175,
|
| 324 |
+
"step": 2250
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.1307709802137821,
|
| 328 |
+
"grad_norm": 0.11204372346401215,
|
| 329 |
+
"learning_rate": 0.000499795670343416,
|
| 330 |
+
"loss": 0.4169,
|
| 331 |
+
"step": 2300
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.13361382760973392,
|
| 335 |
+
"grad_norm": 0.10848614573478699,
|
| 336 |
+
"learning_rate": 0.0004997912283943598,
|
| 337 |
+
"loss": 0.4156,
|
| 338 |
+
"step": 2350
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.1364566750056857,
|
| 342 |
+
"grad_norm": 0.1451840102672577,
|
| 343 |
+
"learning_rate": 0.0004997867864453036,
|
| 344 |
+
"loss": 0.4154,
|
| 345 |
+
"step": 2400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.13929952240163748,
|
| 349 |
+
"grad_norm": 0.14736251533031464,
|
| 350 |
+
"learning_rate": 0.0004997823444962474,
|
| 351 |
+
"loss": 0.4155,
|
| 352 |
+
"step": 2450
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.14214236979758926,
|
| 356 |
+
"grad_norm": 0.12735013663768768,
|
| 357 |
+
"learning_rate": 0.0004997779025471912,
|
| 358 |
+
"loss": 0.4089,
|
| 359 |
+
"step": 2500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.14498521719354104,
|
| 363 |
+
"grad_norm": 0.212030827999115,
|
| 364 |
+
"learning_rate": 0.0004997734605981351,
|
| 365 |
+
"loss": 0.415,
|
| 366 |
+
"step": 2550
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.14782806458949282,
|
| 370 |
+
"grad_norm": 0.11738018691539764,
|
| 371 |
+
"learning_rate": 0.0004997690186490789,
|
| 372 |
+
"loss": 0.4102,
|
| 373 |
+
"step": 2600
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.15067091198544463,
|
| 377 |
+
"grad_norm": 0.1060812696814537,
|
| 378 |
+
"learning_rate": 0.0004997645767000228,
|
| 379 |
+
"loss": 0.4136,
|
| 380 |
+
"step": 2650
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.15351375938139641,
|
| 384 |
+
"grad_norm": 0.12909935414791107,
|
| 385 |
+
"learning_rate": 0.0004997601347509666,
|
| 386 |
+
"loss": 0.4102,
|
| 387 |
+
"step": 2700
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.1563566067773482,
|
| 391 |
+
"grad_norm": 0.15052352845668793,
|
| 392 |
+
"learning_rate": 0.0004997556928019104,
|
| 393 |
+
"loss": 0.4092,
|
| 394 |
+
"step": 2750
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.15919945417329998,
|
| 398 |
+
"grad_norm": 0.13438868522644043,
|
| 399 |
+
"learning_rate": 0.0004997512508528542,
|
| 400 |
+
"loss": 0.4102,
|
| 401 |
+
"step": 2800
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.16204230156925176,
|
| 405 |
+
"grad_norm": 0.11692175269126892,
|
| 406 |
+
"learning_rate": 0.000499746808903798,
|
| 407 |
+
"loss": 0.4103,
|
| 408 |
+
"step": 2850
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.16488514896520354,
|
| 412 |
+
"grad_norm": 0.11706849187612534,
|
| 413 |
+
"learning_rate": 0.0004997423669547419,
|
| 414 |
+
"loss": 0.4104,
|
| 415 |
+
"step": 2900
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.16772799636115535,
|
| 419 |
+
"grad_norm": 0.14066801965236664,
|
| 420 |
+
"learning_rate": 0.0004997379250056858,
|
| 421 |
+
"loss": 0.4104,
|
| 422 |
+
"step": 2950
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.17057084375710713,
|
| 426 |
+
"grad_norm": 0.14922069013118744,
|
| 427 |
+
"learning_rate": 0.0004997334830566296,
|
| 428 |
+
"loss": 0.4125,
|
| 429 |
+
"step": 3000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.1734136911530589,
|
| 433 |
+
"grad_norm": 0.14433512091636658,
|
| 434 |
+
"learning_rate": 0.0004997290411075734,
|
| 435 |
+
"loss": 0.404,
|
| 436 |
+
"step": 3050
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.1762565385490107,
|
| 440 |
+
"grad_norm": 0.11257103830575943,
|
| 441 |
+
"learning_rate": 0.0004997245991585172,
|
| 442 |
+
"loss": 0.4089,
|
| 443 |
+
"step": 3100
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.17909938594496247,
|
| 447 |
+
"grad_norm": 0.13209494948387146,
|
| 448 |
+
"learning_rate": 0.000499720157209461,
|
| 449 |
+
"loss": 0.4081,
|
| 450 |
+
"step": 3150
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.18194223334091425,
|
| 454 |
+
"grad_norm": 0.13629132509231567,
|
| 455 |
+
"learning_rate": 0.0004997157152604048,
|
| 456 |
+
"loss": 0.4062,
|
| 457 |
+
"step": 3200
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.18478508073686606,
|
| 461 |
+
"grad_norm": 0.11546222865581512,
|
| 462 |
+
"learning_rate": 0.0004997112733113486,
|
| 463 |
+
"loss": 0.4037,
|
| 464 |
+
"step": 3250
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.18762792813281784,
|
| 468 |
+
"grad_norm": 0.12525054812431335,
|
| 469 |
+
"learning_rate": 0.0004997068313622925,
|
| 470 |
+
"loss": 0.4064,
|
| 471 |
+
"step": 3300
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.19047077552876962,
|
| 475 |
+
"grad_norm": 0.14944538474082947,
|
| 476 |
+
"learning_rate": 0.0004997023894132363,
|
| 477 |
+
"loss": 0.4085,
|
| 478 |
+
"step": 3350
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.1933136229247214,
|
| 482 |
+
"grad_norm": 0.15211829543113708,
|
| 483 |
+
"learning_rate": 0.0004996979474641801,
|
| 484 |
+
"loss": 0.4063,
|
| 485 |
+
"step": 3400
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.19615647032067318,
|
| 489 |
+
"grad_norm": 0.12800821661949158,
|
| 490 |
+
"learning_rate": 0.000499693505515124,
|
| 491 |
+
"loss": 0.4033,
|
| 492 |
+
"step": 3450
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.19899931771662496,
|
| 496 |
+
"grad_norm": 0.10901828110218048,
|
| 497 |
+
"learning_rate": 0.0004996890635660678,
|
| 498 |
+
"loss": 0.4041,
|
| 499 |
+
"step": 3500
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.20184216511257674,
|
| 503 |
+
"grad_norm": 0.13710814714431763,
|
| 504 |
+
"learning_rate": 0.0004996846216170116,
|
| 505 |
+
"loss": 0.4059,
|
| 506 |
+
"step": 3550
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.20468501250852855,
|
| 510 |
+
"grad_norm": 0.11688549071550369,
|
| 511 |
+
"learning_rate": 0.0004996801796679554,
|
| 512 |
+
"loss": 0.4019,
|
| 513 |
+
"step": 3600
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.20752785990448033,
|
| 517 |
+
"grad_norm": 0.10226283967494965,
|
| 518 |
+
"learning_rate": 0.0004996757377188992,
|
| 519 |
+
"loss": 0.4023,
|
| 520 |
+
"step": 3650
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.2103707073004321,
|
| 524 |
+
"grad_norm": 0.1010371595621109,
|
| 525 |
+
"learning_rate": 0.0004996712957698431,
|
| 526 |
+
"loss": 0.4031,
|
| 527 |
+
"step": 3700
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.2132135546963839,
|
| 531 |
+
"grad_norm": 0.12441287934780121,
|
| 532 |
+
"learning_rate": 0.0004996668538207869,
|
| 533 |
+
"loss": 0.4031,
|
| 534 |
+
"step": 3750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.21605640209233568,
|
| 538 |
+
"grad_norm": 0.12629808485507965,
|
| 539 |
+
"learning_rate": 0.0004996624118717307,
|
| 540 |
+
"loss": 0.4046,
|
| 541 |
+
"step": 3800
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.21889924948828746,
|
| 545 |
+
"grad_norm": 0.1441943198442459,
|
| 546 |
+
"learning_rate": 0.0004996579699226745,
|
| 547 |
+
"loss": 0.4065,
|
| 548 |
+
"step": 3850
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.22174209688423926,
|
| 552 |
+
"grad_norm": 0.08717290312051773,
|
| 553 |
+
"learning_rate": 0.0004996535279736184,
|
| 554 |
+
"loss": 0.4043,
|
| 555 |
+
"step": 3900
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.22458494428019105,
|
| 559 |
+
"grad_norm": 0.12982551753520966,
|
| 560 |
+
"learning_rate": 0.0004996490860245623,
|
| 561 |
+
"loss": 0.3997,
|
| 562 |
+
"step": 3950
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.22742779167614283,
|
| 566 |
+
"grad_norm": 0.11208934336900711,
|
| 567 |
+
"learning_rate": 0.0004996446440755061,
|
| 568 |
+
"loss": 0.3966,
|
| 569 |
+
"step": 4000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.2302706390720946,
|
| 573 |
+
"grad_norm": 0.13264520466327667,
|
| 574 |
+
"learning_rate": 0.0004996402021264499,
|
| 575 |
+
"loss": 0.401,
|
| 576 |
+
"step": 4050
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.2331134864680464,
|
| 580 |
+
"grad_norm": 0.1360943764448166,
|
| 581 |
+
"learning_rate": 0.0004996357601773937,
|
| 582 |
+
"loss": 0.3999,
|
| 583 |
+
"step": 4100
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.23595633386399817,
|
| 587 |
+
"grad_norm": 0.1145951896905899,
|
| 588 |
+
"learning_rate": 0.0004996313182283375,
|
| 589 |
+
"loss": 0.3995,
|
| 590 |
+
"step": 4150
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.23879918125994998,
|
| 594 |
+
"grad_norm": 0.12475068867206573,
|
| 595 |
+
"learning_rate": 0.0004996268762792813,
|
| 596 |
+
"loss": 0.4017,
|
| 597 |
+
"step": 4200
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.24164202865590176,
|
| 601 |
+
"grad_norm": 0.09585878252983093,
|
| 602 |
+
"learning_rate": 0.0004996224343302251,
|
| 603 |
+
"loss": 0.4007,
|
| 604 |
+
"step": 4250
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.24448487605185354,
|
| 608 |
+
"grad_norm": 0.11792745441198349,
|
| 609 |
+
"learning_rate": 0.000499617992381169,
|
| 610 |
+
"loss": 0.3991,
|
| 611 |
+
"step": 4300
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.24732772344780532,
|
| 615 |
+
"grad_norm": 0.16740038990974426,
|
| 616 |
+
"learning_rate": 0.0004996135504321129,
|
| 617 |
+
"loss": 0.3984,
|
| 618 |
+
"step": 4350
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.2501705708437571,
|
| 622 |
+
"grad_norm": 0.09640038013458252,
|
| 623 |
+
"learning_rate": 0.0004996091084830567,
|
| 624 |
+
"loss": 0.3976,
|
| 625 |
+
"step": 4400
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.2530134182397089,
|
| 629 |
+
"grad_norm": 0.09332569688558578,
|
| 630 |
+
"learning_rate": 0.0004996046665340005,
|
| 631 |
+
"loss": 0.3998,
|
| 632 |
+
"step": 4450
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.25585626563566066,
|
| 636 |
+
"grad_norm": 0.11328030377626419,
|
| 637 |
+
"learning_rate": 0.0004996002245849443,
|
| 638 |
+
"loss": 0.3979,
|
| 639 |
+
"step": 4500
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.25869911303161247,
|
| 643 |
+
"grad_norm": 0.1477869302034378,
|
| 644 |
+
"learning_rate": 0.0004995957826358881,
|
| 645 |
+
"loss": 0.3973,
|
| 646 |
+
"step": 4550
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.2615419604275642,
|
| 650 |
+
"grad_norm": 0.09623896330595016,
|
| 651 |
+
"learning_rate": 0.0004995913406868319,
|
| 652 |
+
"loss": 0.3962,
|
| 653 |
+
"step": 4600
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.26438480782351603,
|
| 657 |
+
"grad_norm": 0.11626730114221573,
|
| 658 |
+
"learning_rate": 0.0004995868987377757,
|
| 659 |
+
"loss": 0.3958,
|
| 660 |
+
"step": 4650
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.26722765521946784,
|
| 664 |
+
"grad_norm": 0.10988286882638931,
|
| 665 |
+
"learning_rate": 0.0004995824567887196,
|
| 666 |
+
"loss": 0.3944,
|
| 667 |
+
"step": 4700
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.2700705026154196,
|
| 671 |
+
"grad_norm": 0.12107770144939423,
|
| 672 |
+
"learning_rate": 0.0004995780148396634,
|
| 673 |
+
"loss": 0.3931,
|
| 674 |
+
"step": 4750
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.2729133500113714,
|
| 678 |
+
"grad_norm": 0.11602004617452621,
|
| 679 |
+
"learning_rate": 0.0004995735728906072,
|
| 680 |
+
"loss": 0.3963,
|
| 681 |
+
"step": 4800
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.27575619740732316,
|
| 685 |
+
"grad_norm": 0.10920259356498718,
|
| 686 |
+
"learning_rate": 0.0004995691309415511,
|
| 687 |
+
"loss": 0.395,
|
| 688 |
+
"step": 4850
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.27859904480327496,
|
| 692 |
+
"grad_norm": 0.1066461130976677,
|
| 693 |
+
"learning_rate": 0.0004995646889924949,
|
| 694 |
+
"loss": 0.3938,
|
| 695 |
+
"step": 4900
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.2814418921992268,
|
| 699 |
+
"grad_norm": 0.1071213036775589,
|
| 700 |
+
"learning_rate": 0.0004995602470434387,
|
| 701 |
+
"loss": 0.3943,
|
| 702 |
+
"step": 4950
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.2842847395951785,
|
| 706 |
+
"grad_norm": 0.08286375552415848,
|
| 707 |
+
"learning_rate": 0.0004995558050943825,
|
| 708 |
+
"loss": 0.3948,
|
| 709 |
+
"step": 5000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.2842847395951785,
|
| 713 |
+
"eval_loss": 0.38135138154029846,
|
| 714 |
+
"eval_runtime": 583.2891,
|
| 715 |
+
"eval_samples_per_second": 226.149,
|
| 716 |
+
"eval_steps_per_second": 28.269,
|
| 717 |
+
"step": 5000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.28712758699113033,
|
| 721 |
+
"grad_norm": 0.11819513142108917,
|
| 722 |
+
"learning_rate": 0.0004995513631453263,
|
| 723 |
+
"loss": 0.3969,
|
| 724 |
+
"step": 5050
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.2899704343870821,
|
| 728 |
+
"grad_norm": 0.10034069418907166,
|
| 729 |
+
"learning_rate": 0.0004995469211962702,
|
| 730 |
+
"loss": 0.3962,
|
| 731 |
+
"step": 5100
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.2928132817830339,
|
| 735 |
+
"grad_norm": 0.09750229120254517,
|
| 736 |
+
"learning_rate": 0.000499542479247214,
|
| 737 |
+
"loss": 0.3938,
|
| 738 |
+
"step": 5150
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.29565612917898565,
|
| 742 |
+
"grad_norm": 0.14667393267154694,
|
| 743 |
+
"learning_rate": 0.0004995380372981578,
|
| 744 |
+
"loss": 0.395,
|
| 745 |
+
"step": 5200
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.29849897657493746,
|
| 749 |
+
"grad_norm": 0.1200270876288414,
|
| 750 |
+
"learning_rate": 0.0004995335953491016,
|
| 751 |
+
"loss": 0.3939,
|
| 752 |
+
"step": 5250
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.30134182397088927,
|
| 756 |
+
"grad_norm": 0.12305665761232376,
|
| 757 |
+
"learning_rate": 0.0004995291534000456,
|
| 758 |
+
"loss": 0.3885,
|
| 759 |
+
"step": 5300
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.304184671366841,
|
| 763 |
+
"grad_norm": 0.09782176464796066,
|
| 764 |
+
"learning_rate": 0.0004995247114509894,
|
| 765 |
+
"loss": 0.3907,
|
| 766 |
+
"step": 5350
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.30702751876279283,
|
| 770 |
+
"grad_norm": 0.10045728832483292,
|
| 771 |
+
"learning_rate": 0.0004995202695019332,
|
| 772 |
+
"loss": 0.3921,
|
| 773 |
+
"step": 5400
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.3098703661587446,
|
| 777 |
+
"grad_norm": 0.15331445634365082,
|
| 778 |
+
"learning_rate": 0.000499515827552877,
|
| 779 |
+
"loss": 0.3953,
|
| 780 |
+
"step": 5450
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.3127132135546964,
|
| 784 |
+
"grad_norm": 0.10946525633335114,
|
| 785 |
+
"learning_rate": 0.0004995113856038208,
|
| 786 |
+
"loss": 0.3917,
|
| 787 |
+
"step": 5500
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.31555606095064814,
|
| 791 |
+
"grad_norm": 0.12001294642686844,
|
| 792 |
+
"learning_rate": 0.0004995069436547646,
|
| 793 |
+
"loss": 0.3915,
|
| 794 |
+
"step": 5550
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.31839890834659995,
|
| 798 |
+
"grad_norm": 0.11100505292415619,
|
| 799 |
+
"learning_rate": 0.0004995025017057084,
|
| 800 |
+
"loss": 0.3916,
|
| 801 |
+
"step": 5600
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.32124175574255176,
|
| 805 |
+
"grad_norm": 0.11148565262556076,
|
| 806 |
+
"learning_rate": 0.0004994980597566523,
|
| 807 |
+
"loss": 0.3947,
|
| 808 |
+
"step": 5650
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.3240846031385035,
|
| 812 |
+
"grad_norm": 0.10728944838047028,
|
| 813 |
+
"learning_rate": 0.0004994936178075961,
|
| 814 |
+
"loss": 0.3898,
|
| 815 |
+
"step": 5700
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.3269274505344553,
|
| 819 |
+
"grad_norm": 0.09397928416728973,
|
| 820 |
+
"learning_rate": 0.00049948917585854,
|
| 821 |
+
"loss": 0.3877,
|
| 822 |
+
"step": 5750
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.3297702979304071,
|
| 826 |
+
"grad_norm": 0.12607477605342865,
|
| 827 |
+
"learning_rate": 0.0004994847339094838,
|
| 828 |
+
"loss": 0.3919,
|
| 829 |
+
"step": 5800
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.3326131453263589,
|
| 833 |
+
"grad_norm": 0.11440327763557434,
|
| 834 |
+
"learning_rate": 0.0004994802919604276,
|
| 835 |
+
"loss": 0.3928,
|
| 836 |
+
"step": 5850
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.3354559927223107,
|
| 840 |
+
"grad_norm": 0.1275177150964737,
|
| 841 |
+
"learning_rate": 0.0004994758500113714,
|
| 842 |
+
"loss": 0.389,
|
| 843 |
+
"step": 5900
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.33829884011826244,
|
| 847 |
+
"grad_norm": 0.11246796697378159,
|
| 848 |
+
"learning_rate": 0.0004994714080623152,
|
| 849 |
+
"loss": 0.3862,
|
| 850 |
+
"step": 5950
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.34114168751421425,
|
| 854 |
+
"grad_norm": 0.11354568600654602,
|
| 855 |
+
"learning_rate": 0.000499466966113259,
|
| 856 |
+
"loss": 0.3908,
|
| 857 |
+
"step": 6000
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.343984534910166,
|
| 861 |
+
"grad_norm": 0.10693259537220001,
|
| 862 |
+
"learning_rate": 0.0004994625241642029,
|
| 863 |
+
"loss": 0.389,
|
| 864 |
+
"step": 6050
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.3468273823061178,
|
| 868 |
+
"grad_norm": 0.12362982332706451,
|
| 869 |
+
"learning_rate": 0.0004994580822151467,
|
| 870 |
+
"loss": 0.39,
|
| 871 |
+
"step": 6100
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.34967022970206957,
|
| 875 |
+
"grad_norm": 0.1343277543783188,
|
| 876 |
+
"learning_rate": 0.0004994536402660905,
|
| 877 |
+
"loss": 0.3934,
|
| 878 |
+
"step": 6150
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.3525130770980214,
|
| 882 |
+
"grad_norm": 0.15133637189865112,
|
| 883 |
+
"learning_rate": 0.0004994491983170344,
|
| 884 |
+
"loss": 0.382,
|
| 885 |
+
"step": 6200
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.3553559244939732,
|
| 889 |
+
"grad_norm": 0.11031973361968994,
|
| 890 |
+
"learning_rate": 0.0004994447563679782,
|
| 891 |
+
"loss": 0.3908,
|
| 892 |
+
"step": 6250
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.35819877188992494,
|
| 896 |
+
"grad_norm": 0.09201149642467499,
|
| 897 |
+
"learning_rate": 0.000499440314418922,
|
| 898 |
+
"loss": 0.3888,
|
| 899 |
+
"step": 6300
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.36104161928587675,
|
| 903 |
+
"grad_norm": 0.10396040976047516,
|
| 904 |
+
"learning_rate": 0.0004994358724698658,
|
| 905 |
+
"loss": 0.3861,
|
| 906 |
+
"step": 6350
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.3638844666818285,
|
| 910 |
+
"grad_norm": 0.11148199439048767,
|
| 911 |
+
"learning_rate": 0.0004994314305208096,
|
| 912 |
+
"loss": 0.3897,
|
| 913 |
+
"step": 6400
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.3667273140777803,
|
| 917 |
+
"grad_norm": 0.11479378491640091,
|
| 918 |
+
"learning_rate": 0.0004994269885717535,
|
| 919 |
+
"loss": 0.3883,
|
| 920 |
+
"step": 6450
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.3695701614737321,
|
| 924 |
+
"grad_norm": 0.09433585405349731,
|
| 925 |
+
"learning_rate": 0.0004994225466226973,
|
| 926 |
+
"loss": 0.3841,
|
| 927 |
+
"step": 6500
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.37241300886968387,
|
| 931 |
+
"grad_norm": 0.1304759830236435,
|
| 932 |
+
"learning_rate": 0.0004994181046736411,
|
| 933 |
+
"loss": 0.3876,
|
| 934 |
+
"step": 6550
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.3752558562656357,
|
| 938 |
+
"grad_norm": 0.11292573064565659,
|
| 939 |
+
"learning_rate": 0.0004994136627245849,
|
| 940 |
+
"loss": 0.3872,
|
| 941 |
+
"step": 6600
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.37809870366158743,
|
| 945 |
+
"grad_norm": 0.0928904116153717,
|
| 946 |
+
"learning_rate": 0.0004994092207755289,
|
| 947 |
+
"loss": 0.3875,
|
| 948 |
+
"step": 6650
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.38094155105753924,
|
| 952 |
+
"grad_norm": 0.10247938334941864,
|
| 953 |
+
"learning_rate": 0.0004994047788264727,
|
| 954 |
+
"loss": 0.3885,
|
| 955 |
+
"step": 6700
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.383784398453491,
|
| 959 |
+
"grad_norm": 0.11605235934257507,
|
| 960 |
+
"learning_rate": 0.0004994003368774165,
|
| 961 |
+
"loss": 0.3847,
|
| 962 |
+
"step": 6750
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.3866272458494428,
|
| 966 |
+
"grad_norm": 0.1496395617723465,
|
| 967 |
+
"learning_rate": 0.0004993958949283603,
|
| 968 |
+
"loss": 0.3861,
|
| 969 |
+
"step": 6800
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.3894700932453946,
|
| 973 |
+
"grad_norm": 0.11461085826158524,
|
| 974 |
+
"learning_rate": 0.0004993914529793041,
|
| 975 |
+
"loss": 0.3862,
|
| 976 |
+
"step": 6850
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.39231294064134636,
|
| 980 |
+
"grad_norm": 0.11239515244960785,
|
| 981 |
+
"learning_rate": 0.0004993870110302479,
|
| 982 |
+
"loss": 0.3865,
|
| 983 |
+
"step": 6900
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.3951557880372982,
|
| 987 |
+
"grad_norm": 0.11601614952087402,
|
| 988 |
+
"learning_rate": 0.0004993825690811917,
|
| 989 |
+
"loss": 0.3837,
|
| 990 |
+
"step": 6950
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.3979986354332499,
|
| 994 |
+
"grad_norm": 0.13389568030834198,
|
| 995 |
+
"learning_rate": 0.0004993781271321355,
|
| 996 |
+
"loss": 0.3866,
|
| 997 |
+
"step": 7000
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.40084148282920173,
|
| 1001 |
+
"grad_norm": 0.12181925028562546,
|
| 1002 |
+
"learning_rate": 0.0004993736851830794,
|
| 1003 |
+
"loss": 0.388,
|
| 1004 |
+
"step": 7050
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.4036843302251535,
|
| 1008 |
+
"grad_norm": 0.10346251726150513,
|
| 1009 |
+
"learning_rate": 0.0004993692432340233,
|
| 1010 |
+
"loss": 0.3879,
|
| 1011 |
+
"step": 7100
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.4065271776211053,
|
| 1015 |
+
"grad_norm": 0.11786284297704697,
|
| 1016 |
+
"learning_rate": 0.0004993648012849671,
|
| 1017 |
+
"loss": 0.3859,
|
| 1018 |
+
"step": 7150
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.4093700250170571,
|
| 1022 |
+
"grad_norm": 0.10377379506826401,
|
| 1023 |
+
"learning_rate": 0.0004993603593359109,
|
| 1024 |
+
"loss": 0.3838,
|
| 1025 |
+
"step": 7200
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.41221287241300886,
|
| 1029 |
+
"grad_norm": 0.12437117844820023,
|
| 1030 |
+
"learning_rate": 0.0004993559173868547,
|
| 1031 |
+
"loss": 0.385,
|
| 1032 |
+
"step": 7250
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.41505571980896067,
|
| 1036 |
+
"grad_norm": 0.09871742129325867,
|
| 1037 |
+
"learning_rate": 0.0004993514754377985,
|
| 1038 |
+
"loss": 0.387,
|
| 1039 |
+
"step": 7300
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.4178985672049124,
|
| 1043 |
+
"grad_norm": 0.09648123383522034,
|
| 1044 |
+
"learning_rate": 0.0004993470334887423,
|
| 1045 |
+
"loss": 0.3843,
|
| 1046 |
+
"step": 7350
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.4207414146008642,
|
| 1050 |
+
"grad_norm": 0.14795717597007751,
|
| 1051 |
+
"learning_rate": 0.0004993425915396861,
|
| 1052 |
+
"loss": 0.3833,
|
| 1053 |
+
"step": 7400
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.42358426199681604,
|
| 1057 |
+
"grad_norm": 0.10902711004018784,
|
| 1058 |
+
"learning_rate": 0.00049933814959063,
|
| 1059 |
+
"loss": 0.3823,
|
| 1060 |
+
"step": 7450
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.4264271093927678,
|
| 1064 |
+
"grad_norm": 0.09183204919099808,
|
| 1065 |
+
"learning_rate": 0.0004993337076415738,
|
| 1066 |
+
"loss": 0.3871,
|
| 1067 |
+
"step": 7500
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.4292699567887196,
|
| 1071 |
+
"grad_norm": 0.11348464339971542,
|
| 1072 |
+
"learning_rate": 0.0004993292656925176,
|
| 1073 |
+
"loss": 0.3828,
|
| 1074 |
+
"step": 7550
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.43211280418467135,
|
| 1078 |
+
"grad_norm": 0.08863567560911179,
|
| 1079 |
+
"learning_rate": 0.0004993248237434615,
|
| 1080 |
+
"loss": 0.3817,
|
| 1081 |
+
"step": 7600
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.43495565158062316,
|
| 1085 |
+
"grad_norm": 0.1327882558107376,
|
| 1086 |
+
"learning_rate": 0.0004993203817944053,
|
| 1087 |
+
"loss": 0.3838,
|
| 1088 |
+
"step": 7650
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.4377984989765749,
|
| 1092 |
+
"grad_norm": 0.11749105900526047,
|
| 1093 |
+
"learning_rate": 0.0004993159398453491,
|
| 1094 |
+
"loss": 0.3865,
|
| 1095 |
+
"step": 7700
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.4406413463725267,
|
| 1099 |
+
"grad_norm": 0.09009282290935516,
|
| 1100 |
+
"learning_rate": 0.0004993114978962929,
|
| 1101 |
+
"loss": 0.3823,
|
| 1102 |
+
"step": 7750
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.44348419376847853,
|
| 1106 |
+
"grad_norm": 0.106484554708004,
|
| 1107 |
+
"learning_rate": 0.0004993070559472367,
|
| 1108 |
+
"loss": 0.3797,
|
| 1109 |
+
"step": 7800
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.4463270411644303,
|
| 1113 |
+
"grad_norm": 0.12862497568130493,
|
| 1114 |
+
"learning_rate": 0.0004993026139981806,
|
| 1115 |
+
"loss": 0.3804,
|
| 1116 |
+
"step": 7850
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.4491698885603821,
|
| 1120 |
+
"grad_norm": 0.1015087440609932,
|
| 1121 |
+
"learning_rate": 0.0004992981720491244,
|
| 1122 |
+
"loss": 0.3806,
|
| 1123 |
+
"step": 7900
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.45201273595633384,
|
| 1127 |
+
"grad_norm": 0.10782980173826218,
|
| 1128 |
+
"learning_rate": 0.0004992937301000682,
|
| 1129 |
+
"loss": 0.3858,
|
| 1130 |
+
"step": 7950
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.45485558335228565,
|
| 1134 |
+
"grad_norm": 0.09852251410484314,
|
| 1135 |
+
"learning_rate": 0.000499289288151012,
|
| 1136 |
+
"loss": 0.3824,
|
| 1137 |
+
"step": 8000
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.45769843074823746,
|
| 1141 |
+
"grad_norm": 0.10274305194616318,
|
| 1142 |
+
"learning_rate": 0.000499284846201956,
|
| 1143 |
+
"loss": 0.381,
|
| 1144 |
+
"step": 8050
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.4605412781441892,
|
| 1148 |
+
"grad_norm": 0.10695527493953705,
|
| 1149 |
+
"learning_rate": 0.0004992804042528998,
|
| 1150 |
+
"loss": 0.3839,
|
| 1151 |
+
"step": 8100
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.463384125540141,
|
| 1155 |
+
"grad_norm": 0.09151016920804977,
|
| 1156 |
+
"learning_rate": 0.0004992759623038436,
|
| 1157 |
+
"loss": 0.3842,
|
| 1158 |
+
"step": 8150
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.4662269729360928,
|
| 1162 |
+
"grad_norm": 0.15730440616607666,
|
| 1163 |
+
"learning_rate": 0.0004992715203547874,
|
| 1164 |
+
"loss": 0.3798,
|
| 1165 |
+
"step": 8200
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.4690698203320446,
|
| 1169 |
+
"grad_norm": 0.10243304073810577,
|
| 1170 |
+
"learning_rate": 0.0004992670784057312,
|
| 1171 |
+
"loss": 0.38,
|
| 1172 |
+
"step": 8250
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.47191266772799634,
|
| 1176 |
+
"grad_norm": 0.1174805536866188,
|
| 1177 |
+
"learning_rate": 0.000499262636456675,
|
| 1178 |
+
"loss": 0.3817,
|
| 1179 |
+
"step": 8300
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.47475551512394815,
|
| 1183 |
+
"grad_norm": 0.10942196846008301,
|
| 1184 |
+
"learning_rate": 0.0004992581945076188,
|
| 1185 |
+
"loss": 0.3829,
|
| 1186 |
+
"step": 8350
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.47759836251989995,
|
| 1190 |
+
"grad_norm": 0.10109516978263855,
|
| 1191 |
+
"learning_rate": 0.0004992537525585626,
|
| 1192 |
+
"loss": 0.3803,
|
| 1193 |
+
"step": 8400
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.4804412099158517,
|
| 1197 |
+
"grad_norm": 0.09248687326908112,
|
| 1198 |
+
"learning_rate": 0.0004992493106095065,
|
| 1199 |
+
"loss": 0.3796,
|
| 1200 |
+
"step": 8450
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.4832840573118035,
|
| 1204 |
+
"grad_norm": 0.11525557935237885,
|
| 1205 |
+
"learning_rate": 0.0004992448686604504,
|
| 1206 |
+
"loss": 0.3823,
|
| 1207 |
+
"step": 8500
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.48612690470775527,
|
| 1211 |
+
"grad_norm": 0.10481023788452148,
|
| 1212 |
+
"learning_rate": 0.0004992404267113942,
|
| 1213 |
+
"loss": 0.3781,
|
| 1214 |
+
"step": 8550
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.4889697521037071,
|
| 1218 |
+
"grad_norm": 0.09493274986743927,
|
| 1219 |
+
"learning_rate": 0.000499235984762338,
|
| 1220 |
+
"loss": 0.38,
|
| 1221 |
+
"step": 8600
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.49181259949965883,
|
| 1225 |
+
"grad_norm": 0.08859369158744812,
|
| 1226 |
+
"learning_rate": 0.0004992315428132818,
|
| 1227 |
+
"loss": 0.3789,
|
| 1228 |
+
"step": 8650
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.49465544689561064,
|
| 1232 |
+
"grad_norm": 0.11814738810062408,
|
| 1233 |
+
"learning_rate": 0.0004992271008642256,
|
| 1234 |
+
"loss": 0.3809,
|
| 1235 |
+
"step": 8700
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.49749829429156245,
|
| 1239 |
+
"grad_norm": 0.1322488635778427,
|
| 1240 |
+
"learning_rate": 0.0004992226589151694,
|
| 1241 |
+
"loss": 0.3795,
|
| 1242 |
+
"step": 8750
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.5003411416875142,
|
| 1246 |
+
"grad_norm": 0.1304454803466797,
|
| 1247 |
+
"learning_rate": 0.0004992182169661132,
|
| 1248 |
+
"loss": 0.3794,
|
| 1249 |
+
"step": 8800
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.503183989083466,
|
| 1253 |
+
"grad_norm": 0.09153052419424057,
|
| 1254 |
+
"learning_rate": 0.0004992137750170571,
|
| 1255 |
+
"loss": 0.3769,
|
| 1256 |
+
"step": 8850
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.5060268364794178,
|
| 1260 |
+
"grad_norm": 0.10608222335577011,
|
| 1261 |
+
"learning_rate": 0.0004992093330680009,
|
| 1262 |
+
"loss": 0.3748,
|
| 1263 |
+
"step": 8900
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.5088696838753696,
|
| 1267 |
+
"grad_norm": 0.1054573506116867,
|
| 1268 |
+
"learning_rate": 0.0004992048911189447,
|
| 1269 |
+
"loss": 0.3817,
|
| 1270 |
+
"step": 8950
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.5117125312713213,
|
| 1274 |
+
"grad_norm": 0.1694241166114807,
|
| 1275 |
+
"learning_rate": 0.0004992004491698886,
|
| 1276 |
+
"loss": 0.3774,
|
| 1277 |
+
"step": 9000
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.5145553786672732,
|
| 1281 |
+
"grad_norm": 0.13877439498901367,
|
| 1282 |
+
"learning_rate": 0.0004991960072208324,
|
| 1283 |
+
"loss": 0.3769,
|
| 1284 |
+
"step": 9050
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.5173982260632249,
|
| 1288 |
+
"grad_norm": 0.10788954794406891,
|
| 1289 |
+
"learning_rate": 0.0004991915652717762,
|
| 1290 |
+
"loss": 0.3819,
|
| 1291 |
+
"step": 9100
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.5202410734591767,
|
| 1295 |
+
"grad_norm": 0.12326483428478241,
|
| 1296 |
+
"learning_rate": 0.00049918712332272,
|
| 1297 |
+
"loss": 0.3812,
|
| 1298 |
+
"step": 9150
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.5230839208551284,
|
| 1302 |
+
"grad_norm": 0.07986534386873245,
|
| 1303 |
+
"learning_rate": 0.0004991826813736638,
|
| 1304 |
+
"loss": 0.3797,
|
| 1305 |
+
"step": 9200
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.5259267682510803,
|
| 1309 |
+
"grad_norm": 0.11102836579084396,
|
| 1310 |
+
"learning_rate": 0.0004991782394246077,
|
| 1311 |
+
"loss": 0.3797,
|
| 1312 |
+
"step": 9250
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.5287696156470321,
|
| 1316 |
+
"grad_norm": 0.10697384923696518,
|
| 1317 |
+
"learning_rate": 0.0004991737974755515,
|
| 1318 |
+
"loss": 0.3767,
|
| 1319 |
+
"step": 9300
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.5316124630429838,
|
| 1323 |
+
"grad_norm": 0.11679094284772873,
|
| 1324 |
+
"learning_rate": 0.0004991693555264953,
|
| 1325 |
+
"loss": 0.3782,
|
| 1326 |
+
"step": 9350
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.5344553104389357,
|
| 1330 |
+
"grad_norm": 0.10827042162418365,
|
| 1331 |
+
"learning_rate": 0.0004991649135774391,
|
| 1332 |
+
"loss": 0.376,
|
| 1333 |
+
"step": 9400
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.5372981578348874,
|
| 1337 |
+
"grad_norm": 0.0934649109840393,
|
| 1338 |
+
"learning_rate": 0.0004991604716283831,
|
| 1339 |
+
"loss": 0.3775,
|
| 1340 |
+
"step": 9450
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.5401410052308392,
|
| 1344 |
+
"grad_norm": 0.08999691903591156,
|
| 1345 |
+
"learning_rate": 0.0004991560296793269,
|
| 1346 |
+
"loss": 0.3783,
|
| 1347 |
+
"step": 9500
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.5429838526267909,
|
| 1351 |
+
"grad_norm": 0.11615636944770813,
|
| 1352 |
+
"learning_rate": 0.0004991515877302707,
|
| 1353 |
+
"loss": 0.3779,
|
| 1354 |
+
"step": 9550
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.5458267000227428,
|
| 1358 |
+
"grad_norm": 0.4005848467350006,
|
| 1359 |
+
"learning_rate": 0.0004991471457812145,
|
| 1360 |
+
"loss": 0.3745,
|
| 1361 |
+
"step": 9600
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.5486695474186946,
|
| 1365 |
+
"grad_norm": 0.12695498764514923,
|
| 1366 |
+
"learning_rate": 0.0004991427038321583,
|
| 1367 |
+
"loss": 0.3916,
|
| 1368 |
+
"step": 9650
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.5515123948146463,
|
| 1372 |
+
"grad_norm": 0.10009093582630157,
|
| 1373 |
+
"learning_rate": 0.0004991382618831021,
|
| 1374 |
+
"loss": 0.3798,
|
| 1375 |
+
"step": 9700
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.5543552422105982,
|
| 1379 |
+
"grad_norm": 0.1480248123407364,
|
| 1380 |
+
"learning_rate": 0.0004991338199340459,
|
| 1381 |
+
"loss": 0.3752,
|
| 1382 |
+
"step": 9750
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.5571980896065499,
|
| 1386 |
+
"grad_norm": 0.10428158193826675,
|
| 1387 |
+
"learning_rate": 0.0004991293779849897,
|
| 1388 |
+
"loss": 0.3787,
|
| 1389 |
+
"step": 9800
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.5600409370025017,
|
| 1393 |
+
"grad_norm": 0.1932564377784729,
|
| 1394 |
+
"learning_rate": 0.0004991249360359336,
|
| 1395 |
+
"loss": 0.3812,
|
| 1396 |
+
"step": 9850
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.5628837843984535,
|
| 1400 |
+
"grad_norm": 0.088712178170681,
|
| 1401 |
+
"learning_rate": 0.0004991204940868775,
|
| 1402 |
+
"loss": 0.3783,
|
| 1403 |
+
"step": 9900
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.5657266317944053,
|
| 1407 |
+
"grad_norm": 0.10896250605583191,
|
| 1408 |
+
"learning_rate": 0.0004991160521378213,
|
| 1409 |
+
"loss": 0.3782,
|
| 1410 |
+
"step": 9950
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.568569479190357,
|
| 1414 |
+
"grad_norm": 0.1077795922756195,
|
| 1415 |
+
"learning_rate": 0.0004991116101887651,
|
| 1416 |
+
"loss": 0.3773,
|
| 1417 |
+
"step": 10000
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.568569479190357,
|
| 1421 |
+
"eval_loss": 0.36588892340660095,
|
| 1422 |
+
"eval_runtime": 584.439,
|
| 1423 |
+
"eval_samples_per_second": 225.704,
|
| 1424 |
+
"eval_steps_per_second": 28.213,
|
| 1425 |
+
"step": 10000
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 0.5714123265863088,
|
| 1429 |
+
"grad_norm": 0.09190759807825089,
|
| 1430 |
+
"learning_rate": 0.0004991071682397089,
|
| 1431 |
+
"loss": 0.3785,
|
| 1432 |
+
"step": 10050
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 0.5742551739822607,
|
| 1436 |
+
"grad_norm": 0.11082971841096878,
|
| 1437 |
+
"learning_rate": 0.0004991027262906527,
|
| 1438 |
+
"loss": 0.3775,
|
| 1439 |
+
"step": 10100
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 0.5770980213782124,
|
| 1443 |
+
"grad_norm": 0.10099225491285324,
|
| 1444 |
+
"learning_rate": 0.0004990982843415965,
|
| 1445 |
+
"loss": 0.3775,
|
| 1446 |
+
"step": 10150
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 0.5799408687741642,
|
| 1450 |
+
"grad_norm": 0.1112075224518776,
|
| 1451 |
+
"learning_rate": 0.0004990938423925403,
|
| 1452 |
+
"loss": 0.3764,
|
| 1453 |
+
"step": 10200
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 0.582783716170116,
|
| 1457 |
+
"grad_norm": 0.09865789860486984,
|
| 1458 |
+
"learning_rate": 0.0004990894004434842,
|
| 1459 |
+
"loss": 0.3802,
|
| 1460 |
+
"step": 10250
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 0.5856265635660678,
|
| 1464 |
+
"grad_norm": 0.10351789742708206,
|
| 1465 |
+
"learning_rate": 0.000499084958494428,
|
| 1466 |
+
"loss": 0.3795,
|
| 1467 |
+
"step": 10300
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 0.5884694109620195,
|
| 1471 |
+
"grad_norm": 0.10376661270856857,
|
| 1472 |
+
"learning_rate": 0.0004990805165453719,
|
| 1473 |
+
"loss": 0.3753,
|
| 1474 |
+
"step": 10350
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 0.5913122583579713,
|
| 1478 |
+
"grad_norm": 0.09663544595241547,
|
| 1479 |
+
"learning_rate": 0.0004990760745963157,
|
| 1480 |
+
"loss": 0.3737,
|
| 1481 |
+
"step": 10400
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 0.5941551057539232,
|
| 1485 |
+
"grad_norm": 0.09701116383075714,
|
| 1486 |
+
"learning_rate": 0.0004990716326472595,
|
| 1487 |
+
"loss": 0.3737,
|
| 1488 |
+
"step": 10450
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 0.5969979531498749,
|
| 1492 |
+
"grad_norm": 0.1021418496966362,
|
| 1493 |
+
"learning_rate": 0.0004990671906982033,
|
| 1494 |
+
"loss": 0.3728,
|
| 1495 |
+
"step": 10500
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 0.5998408005458267,
|
| 1499 |
+
"grad_norm": 0.12170026451349258,
|
| 1500 |
+
"learning_rate": 0.0004990627487491472,
|
| 1501 |
+
"loss": 0.3755,
|
| 1502 |
+
"step": 10550
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 0.6026836479417785,
|
| 1506 |
+
"grad_norm": 0.1142646074295044,
|
| 1507 |
+
"learning_rate": 0.000499058306800091,
|
| 1508 |
+
"loss": 0.378,
|
| 1509 |
+
"step": 10600
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 0.6055264953377303,
|
| 1513 |
+
"grad_norm": 0.09568295627832413,
|
| 1514 |
+
"learning_rate": 0.0004990538648510348,
|
| 1515 |
+
"loss": 0.3742,
|
| 1516 |
+
"step": 10650
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 0.608369342733682,
|
| 1520 |
+
"grad_norm": 0.11586258560419083,
|
| 1521 |
+
"learning_rate": 0.0004990494229019786,
|
| 1522 |
+
"loss": 0.3731,
|
| 1523 |
+
"step": 10700
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 0.6112121901296338,
|
| 1527 |
+
"grad_norm": 0.0984320268034935,
|
| 1528 |
+
"learning_rate": 0.0004990449809529224,
|
| 1529 |
+
"loss": 0.3767,
|
| 1530 |
+
"step": 10750
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 0.6140550375255857,
|
| 1534 |
+
"grad_norm": 0.10665503889322281,
|
| 1535 |
+
"learning_rate": 0.0004990405390038662,
|
| 1536 |
+
"loss": 0.3756,
|
| 1537 |
+
"step": 10800
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 0.6168978849215374,
|
| 1541 |
+
"grad_norm": 0.10374121367931366,
|
| 1542 |
+
"learning_rate": 0.0004990360970548102,
|
| 1543 |
+
"loss": 0.376,
|
| 1544 |
+
"step": 10850
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 0.6197407323174892,
|
| 1548 |
+
"grad_norm": 0.10508013516664505,
|
| 1549 |
+
"learning_rate": 0.000499031655105754,
|
| 1550 |
+
"loss": 0.3717,
|
| 1551 |
+
"step": 10900
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 0.622583579713441,
|
| 1555 |
+
"grad_norm": 0.10919308662414551,
|
| 1556 |
+
"learning_rate": 0.0004990272131566978,
|
| 1557 |
+
"loss": 0.3746,
|
| 1558 |
+
"step": 10950
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 0.6254264271093928,
|
| 1562 |
+
"grad_norm": 0.09990997612476349,
|
| 1563 |
+
"learning_rate": 0.0004990227712076416,
|
| 1564 |
+
"loss": 0.3738,
|
| 1565 |
+
"step": 11000
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 0.6282692745053445,
|
| 1569 |
+
"grad_norm": 0.10817346721887589,
|
| 1570 |
+
"learning_rate": 0.0004990183292585854,
|
| 1571 |
+
"loss": 0.3688,
|
| 1572 |
+
"step": 11050
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 0.6311121219012963,
|
| 1576 |
+
"grad_norm": 0.0922752320766449,
|
| 1577 |
+
"learning_rate": 0.0004990138873095292,
|
| 1578 |
+
"loss": 0.3751,
|
| 1579 |
+
"step": 11100
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 0.6339549692972481,
|
| 1583 |
+
"grad_norm": 0.09761642664670944,
|
| 1584 |
+
"learning_rate": 0.000499009445360473,
|
| 1585 |
+
"loss": 0.3724,
|
| 1586 |
+
"step": 11150
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 0.6367978166931999,
|
| 1590 |
+
"grad_norm": 0.09401151537895203,
|
| 1591 |
+
"learning_rate": 0.0004990050034114168,
|
| 1592 |
+
"loss": 0.3717,
|
| 1593 |
+
"step": 11200
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 0.6396406640891517,
|
| 1597 |
+
"grad_norm": 0.10084612667560577,
|
| 1598 |
+
"learning_rate": 0.0004990005614623607,
|
| 1599 |
+
"loss": 0.3711,
|
| 1600 |
+
"step": 11250
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 0.6424835114851035,
|
| 1604 |
+
"grad_norm": 0.11709214001893997,
|
| 1605 |
+
"learning_rate": 0.0004989961195133046,
|
| 1606 |
+
"loss": 0.3739,
|
| 1607 |
+
"step": 11300
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 0.6453263588810553,
|
| 1611 |
+
"grad_norm": 0.1035287156701088,
|
| 1612 |
+
"learning_rate": 0.0004989916775642484,
|
| 1613 |
+
"loss": 0.3684,
|
| 1614 |
+
"step": 11350
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 0.648169206277007,
|
| 1618 |
+
"grad_norm": 0.09968025982379913,
|
| 1619 |
+
"learning_rate": 0.0004989872356151922,
|
| 1620 |
+
"loss": 0.3749,
|
| 1621 |
+
"step": 11400
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 0.6510120536729589,
|
| 1625 |
+
"grad_norm": 0.1003747433423996,
|
| 1626 |
+
"learning_rate": 0.000498982793666136,
|
| 1627 |
+
"loss": 0.3721,
|
| 1628 |
+
"step": 11450
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 0.6538549010689106,
|
| 1632 |
+
"grad_norm": 0.09462849795818329,
|
| 1633 |
+
"learning_rate": 0.0004989783517170798,
|
| 1634 |
+
"loss": 0.3687,
|
| 1635 |
+
"step": 11500
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 0.6566977484648624,
|
| 1639 |
+
"grad_norm": 0.10089970380067825,
|
| 1640 |
+
"learning_rate": 0.0004989739097680236,
|
| 1641 |
+
"loss": 0.3724,
|
| 1642 |
+
"step": 11550
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 0.6595405958608141,
|
| 1646 |
+
"grad_norm": 0.11282893270254135,
|
| 1647 |
+
"learning_rate": 0.0004989694678189675,
|
| 1648 |
+
"loss": 0.3726,
|
| 1649 |
+
"step": 11600
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 0.662383443256766,
|
| 1653 |
+
"grad_norm": 0.12321527302265167,
|
| 1654 |
+
"learning_rate": 0.0004989650258699113,
|
| 1655 |
+
"loss": 0.3704,
|
| 1656 |
+
"step": 11650
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 0.6652262906527178,
|
| 1660 |
+
"grad_norm": 0.10225247591733932,
|
| 1661 |
+
"learning_rate": 0.0004989605839208551,
|
| 1662 |
+
"loss": 0.3717,
|
| 1663 |
+
"step": 11700
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 0.6680691380486695,
|
| 1667 |
+
"grad_norm": 0.09634348750114441,
|
| 1668 |
+
"learning_rate": 0.000498956141971799,
|
| 1669 |
+
"loss": 0.3731,
|
| 1670 |
+
"step": 11750
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 0.6709119854446214,
|
| 1674 |
+
"grad_norm": 0.09670031815767288,
|
| 1675 |
+
"learning_rate": 0.0004989517000227428,
|
| 1676 |
+
"loss": 0.3697,
|
| 1677 |
+
"step": 11800
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 0.6737548328405731,
|
| 1681 |
+
"grad_norm": 0.11874838918447495,
|
| 1682 |
+
"learning_rate": 0.0004989472580736867,
|
| 1683 |
+
"loss": 0.3717,
|
| 1684 |
+
"step": 11850
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 0.6765976802365249,
|
| 1688 |
+
"grad_norm": 0.1474309116601944,
|
| 1689 |
+
"learning_rate": 0.0004989428161246305,
|
| 1690 |
+
"loss": 0.3719,
|
| 1691 |
+
"step": 11900
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 0.6794405276324766,
|
| 1695 |
+
"grad_norm": 0.0953158363699913,
|
| 1696 |
+
"learning_rate": 0.0004989383741755743,
|
| 1697 |
+
"loss": 0.3698,
|
| 1698 |
+
"step": 11950
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 0.6822833750284285,
|
| 1702 |
+
"grad_norm": 0.07613354921340942,
|
| 1703 |
+
"learning_rate": 0.0004989339322265181,
|
| 1704 |
+
"loss": 0.372,
|
| 1705 |
+
"step": 12000
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 0.6851262224243803,
|
| 1709 |
+
"grad_norm": 0.10099935531616211,
|
| 1710 |
+
"learning_rate": 0.0004989294902774619,
|
| 1711 |
+
"loss": 0.3715,
|
| 1712 |
+
"step": 12050
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 0.687969069820332,
|
| 1716 |
+
"grad_norm": 0.1142035722732544,
|
| 1717 |
+
"learning_rate": 0.0004989250483284057,
|
| 1718 |
+
"loss": 0.371,
|
| 1719 |
+
"step": 12100
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 0.6908119172162839,
|
| 1723 |
+
"grad_norm": 0.11868602782487869,
|
| 1724 |
+
"learning_rate": 0.0004989206063793495,
|
| 1725 |
+
"loss": 0.3718,
|
| 1726 |
+
"step": 12150
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 0.6936547646122356,
|
| 1730 |
+
"grad_norm": 0.11403531581163406,
|
| 1731 |
+
"learning_rate": 0.0004989161644302935,
|
| 1732 |
+
"loss": 0.37,
|
| 1733 |
+
"step": 12200
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 0.6964976120081874,
|
| 1737 |
+
"grad_norm": 0.10048527270555496,
|
| 1738 |
+
"learning_rate": 0.0004989117224812373,
|
| 1739 |
+
"loss": 0.3689,
|
| 1740 |
+
"step": 12250
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 0.6993404594041391,
|
| 1744 |
+
"grad_norm": 0.0894421935081482,
|
| 1745 |
+
"learning_rate": 0.0004989072805321811,
|
| 1746 |
+
"loss": 0.3675,
|
| 1747 |
+
"step": 12300
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 0.702183306800091,
|
| 1751 |
+
"grad_norm": 0.10465215891599655,
|
| 1752 |
+
"learning_rate": 0.0004989028385831249,
|
| 1753 |
+
"loss": 0.3707,
|
| 1754 |
+
"step": 12350
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 0.7050261541960428,
|
| 1758 |
+
"grad_norm": 0.10983111709356308,
|
| 1759 |
+
"learning_rate": 0.0004988983966340687,
|
| 1760 |
+
"loss": 0.3713,
|
| 1761 |
+
"step": 12400
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.7078690015919945,
|
| 1765 |
+
"grad_norm": 0.11033093929290771,
|
| 1766 |
+
"learning_rate": 0.0004988939546850125,
|
| 1767 |
+
"loss": 0.3723,
|
| 1768 |
+
"step": 12450
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 0.7107118489879464,
|
| 1772 |
+
"grad_norm": 0.11053282022476196,
|
| 1773 |
+
"learning_rate": 0.0004988895127359563,
|
| 1774 |
+
"loss": 0.3701,
|
| 1775 |
+
"step": 12500
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 0.7135546963838981,
|
| 1779 |
+
"grad_norm": 0.09599506109952927,
|
| 1780 |
+
"learning_rate": 0.0004988850707869001,
|
| 1781 |
+
"loss": 0.3696,
|
| 1782 |
+
"step": 12550
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 0.7163975437798499,
|
| 1786 |
+
"grad_norm": 0.10971349477767944,
|
| 1787 |
+
"learning_rate": 0.000498880628837844,
|
| 1788 |
+
"loss": 0.3692,
|
| 1789 |
+
"step": 12600
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 0.7192403911758016,
|
| 1793 |
+
"grad_norm": 0.09890740364789963,
|
| 1794 |
+
"learning_rate": 0.0004988761868887879,
|
| 1795 |
+
"loss": 0.3671,
|
| 1796 |
+
"step": 12650
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 0.7220832385717535,
|
| 1800 |
+
"grad_norm": 0.09667664021253586,
|
| 1801 |
+
"learning_rate": 0.0004988717449397317,
|
| 1802 |
+
"loss": 0.3708,
|
| 1803 |
+
"step": 12700
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 0.7249260859677052,
|
| 1807 |
+
"grad_norm": 0.08852635324001312,
|
| 1808 |
+
"learning_rate": 0.0004988673029906755,
|
| 1809 |
+
"loss": 0.3704,
|
| 1810 |
+
"step": 12750
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 0.727768933363657,
|
| 1814 |
+
"grad_norm": 0.08930686861276627,
|
| 1815 |
+
"learning_rate": 0.0004988628610416193,
|
| 1816 |
+
"loss": 0.3676,
|
| 1817 |
+
"step": 12800
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 0.7306117807596089,
|
| 1821 |
+
"grad_norm": 0.10307100415229797,
|
| 1822 |
+
"learning_rate": 0.0004988584190925631,
|
| 1823 |
+
"loss": 0.3702,
|
| 1824 |
+
"step": 12850
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 0.7334546281555606,
|
| 1828 |
+
"grad_norm": 0.09995568543672562,
|
| 1829 |
+
"learning_rate": 0.0004988539771435069,
|
| 1830 |
+
"loss": 0.367,
|
| 1831 |
+
"step": 12900
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 0.7362974755515124,
|
| 1835 |
+
"grad_norm": 0.09159702807664871,
|
| 1836 |
+
"learning_rate": 0.0004988495351944507,
|
| 1837 |
+
"loss": 0.3661,
|
| 1838 |
+
"step": 12950
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 0.7391403229474642,
|
| 1842 |
+
"grad_norm": 0.0963875874876976,
|
| 1843 |
+
"learning_rate": 0.0004988450932453946,
|
| 1844 |
+
"loss": 0.3667,
|
| 1845 |
+
"step": 13000
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 0.741983170343416,
|
| 1849 |
+
"grad_norm": 0.09584073722362518,
|
| 1850 |
+
"learning_rate": 0.0004988406512963384,
|
| 1851 |
+
"loss": 0.3697,
|
| 1852 |
+
"step": 13050
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 0.7448260177393677,
|
| 1856 |
+
"grad_norm": 0.09499222785234451,
|
| 1857 |
+
"learning_rate": 0.0004988362093472822,
|
| 1858 |
+
"loss": 0.3692,
|
| 1859 |
+
"step": 13100
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 0.7476688651353195,
|
| 1863 |
+
"grad_norm": 0.10076665878295898,
|
| 1864 |
+
"learning_rate": 0.0004988317673982261,
|
| 1865 |
+
"loss": 0.3672,
|
| 1866 |
+
"step": 13150
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 0.7505117125312714,
|
| 1870 |
+
"grad_norm": 0.1046692505478859,
|
| 1871 |
+
"learning_rate": 0.00049882732544917,
|
| 1872 |
+
"loss": 0.3669,
|
| 1873 |
+
"step": 13200
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 0.7533545599272231,
|
| 1877 |
+
"grad_norm": 0.11345544457435608,
|
| 1878 |
+
"learning_rate": 0.0004988228835001138,
|
| 1879 |
+
"loss": 0.3676,
|
| 1880 |
+
"step": 13250
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 0.7561974073231749,
|
| 1884 |
+
"grad_norm": 0.09689969569444656,
|
| 1885 |
+
"learning_rate": 0.0004988184415510576,
|
| 1886 |
+
"loss": 0.367,
|
| 1887 |
+
"step": 13300
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 0.7590402547191267,
|
| 1891 |
+
"grad_norm": 0.10489045083522797,
|
| 1892 |
+
"learning_rate": 0.0004988139996020014,
|
| 1893 |
+
"loss": 0.3681,
|
| 1894 |
+
"step": 13350
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 0.7618831021150785,
|
| 1898 |
+
"grad_norm": 0.09123999625444412,
|
| 1899 |
+
"learning_rate": 0.0004988095576529452,
|
| 1900 |
+
"loss": 0.3687,
|
| 1901 |
+
"step": 13400
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 0.7647259495110302,
|
| 1905 |
+
"grad_norm": 0.09405972063541412,
|
| 1906 |
+
"learning_rate": 0.000498805115703889,
|
| 1907 |
+
"loss": 0.3715,
|
| 1908 |
+
"step": 13450
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 0.767568796906982,
|
| 1912 |
+
"grad_norm": 0.08794659376144409,
|
| 1913 |
+
"learning_rate": 0.0004988006737548328,
|
| 1914 |
+
"loss": 0.3653,
|
| 1915 |
+
"step": 13500
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 0.7704116443029339,
|
| 1919 |
+
"grad_norm": 0.11547774076461792,
|
| 1920 |
+
"learning_rate": 0.0004987962318057766,
|
| 1921 |
+
"loss": 0.3677,
|
| 1922 |
+
"step": 13550
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 0.7732544916988856,
|
| 1926 |
+
"grad_norm": 0.0955629050731659,
|
| 1927 |
+
"learning_rate": 0.0004987917898567206,
|
| 1928 |
+
"loss": 0.369,
|
| 1929 |
+
"step": 13600
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 0.7760973390948374,
|
| 1933 |
+
"grad_norm": 0.10582061856985092,
|
| 1934 |
+
"learning_rate": 0.0004987873479076644,
|
| 1935 |
+
"loss": 0.3696,
|
| 1936 |
+
"step": 13650
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 0.7789401864907892,
|
| 1940 |
+
"grad_norm": 0.11626145988702774,
|
| 1941 |
+
"learning_rate": 0.0004987829059586082,
|
| 1942 |
+
"loss": 0.369,
|
| 1943 |
+
"step": 13700
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 0.781783033886741,
|
| 1947 |
+
"grad_norm": 0.08376283198595047,
|
| 1948 |
+
"learning_rate": 0.000498778464009552,
|
| 1949 |
+
"loss": 0.3686,
|
| 1950 |
+
"step": 13750
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"epoch": 0.7846258812826927,
|
| 1954 |
+
"grad_norm": 0.09740207344293594,
|
| 1955 |
+
"learning_rate": 0.0004987740220604958,
|
| 1956 |
+
"loss": 0.3649,
|
| 1957 |
+
"step": 13800
|
| 1958 |
+
},
|
| 1959 |
+
{
|
| 1960 |
+
"epoch": 0.7874687286786445,
|
| 1961 |
+
"grad_norm": 0.08660556375980377,
|
| 1962 |
+
"learning_rate": 0.0004987695801114396,
|
| 1963 |
+
"loss": 0.3654,
|
| 1964 |
+
"step": 13850
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 0.7903115760745963,
|
| 1968 |
+
"grad_norm": 0.09063564240932465,
|
| 1969 |
+
"learning_rate": 0.0004987651381623834,
|
| 1970 |
+
"loss": 0.3671,
|
| 1971 |
+
"step": 13900
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 0.7931544234705481,
|
| 1975 |
+
"grad_norm": 0.12205325812101364,
|
| 1976 |
+
"learning_rate": 0.0004987606962133272,
|
| 1977 |
+
"loss": 0.3667,
|
| 1978 |
+
"step": 13950
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 0.7959972708664999,
|
| 1982 |
+
"grad_norm": 0.1259283423423767,
|
| 1983 |
+
"learning_rate": 0.0004987562542642711,
|
| 1984 |
+
"loss": 0.3611,
|
| 1985 |
+
"step": 14000
|
| 1986 |
+
},
|
| 1987 |
+
{
|
| 1988 |
+
"epoch": 0.7988401182624517,
|
| 1989 |
+
"grad_norm": 0.0938865914940834,
|
| 1990 |
+
"learning_rate": 0.000498751812315215,
|
| 1991 |
+
"loss": 0.3666,
|
| 1992 |
+
"step": 14050
|
| 1993 |
+
},
|
| 1994 |
+
{
|
| 1995 |
+
"epoch": 0.8016829656584035,
|
| 1996 |
+
"grad_norm": 0.10185267776250839,
|
| 1997 |
+
"learning_rate": 0.0004987473703661588,
|
| 1998 |
+
"loss": 0.3648,
|
| 1999 |
+
"step": 14100
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 0.8045258130543552,
|
| 2003 |
+
"grad_norm": 0.11661996692419052,
|
| 2004 |
+
"learning_rate": 0.0004987429284171026,
|
| 2005 |
+
"loss": 0.3657,
|
| 2006 |
+
"step": 14150
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 0.807368660450307,
|
| 2010 |
+
"grad_norm": 0.0994558110833168,
|
| 2011 |
+
"learning_rate": 0.0004987384864680464,
|
| 2012 |
+
"loss": 0.3639,
|
| 2013 |
+
"step": 14200
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 0.8102115078462588,
|
| 2017 |
+
"grad_norm": 0.09819088876247406,
|
| 2018 |
+
"learning_rate": 0.0004987340445189902,
|
| 2019 |
+
"loss": 0.3642,
|
| 2020 |
+
"step": 14250
|
| 2021 |
+
},
|
| 2022 |
+
{
|
| 2023 |
+
"epoch": 0.8130543552422106,
|
| 2024 |
+
"grad_norm": 0.09436295926570892,
|
| 2025 |
+
"learning_rate": 0.000498729602569934,
|
| 2026 |
+
"loss": 0.3677,
|
| 2027 |
+
"step": 14300
|
| 2028 |
+
},
|
| 2029 |
+
{
|
| 2030 |
+
"epoch": 0.8158972026381623,
|
| 2031 |
+
"grad_norm": 0.12002996355295181,
|
| 2032 |
+
"learning_rate": 0.0004987251606208778,
|
| 2033 |
+
"loss": 0.366,
|
| 2034 |
+
"step": 14350
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 0.8187400500341142,
|
| 2038 |
+
"grad_norm": 0.08650200068950653,
|
| 2039 |
+
"learning_rate": 0.0004987207186718217,
|
| 2040 |
+
"loss": 0.3645,
|
| 2041 |
+
"step": 14400
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 0.821582897430066,
|
| 2045 |
+
"grad_norm": 0.1826743632555008,
|
| 2046 |
+
"learning_rate": 0.0004987162767227655,
|
| 2047 |
+
"loss": 0.3681,
|
| 2048 |
+
"step": 14450
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 0.8244257448260177,
|
| 2052 |
+
"grad_norm": 0.10164210200309753,
|
| 2053 |
+
"learning_rate": 0.0004987118347737093,
|
| 2054 |
+
"loss": 0.3706,
|
| 2055 |
+
"step": 14500
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 0.8272685922219696,
|
| 2059 |
+
"grad_norm": 0.09652096033096313,
|
| 2060 |
+
"learning_rate": 0.0004987073928246532,
|
| 2061 |
+
"loss": 0.364,
|
| 2062 |
+
"step": 14550
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 0.8301114396179213,
|
| 2066 |
+
"grad_norm": 0.1318165808916092,
|
| 2067 |
+
"learning_rate": 0.0004987029508755971,
|
| 2068 |
+
"loss": 0.3651,
|
| 2069 |
+
"step": 14600
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 0.8329542870138731,
|
| 2073 |
+
"grad_norm": 0.09845109283924103,
|
| 2074 |
+
"learning_rate": 0.0004986985089265409,
|
| 2075 |
+
"loss": 0.3636,
|
| 2076 |
+
"step": 14650
|
| 2077 |
+
},
|
| 2078 |
+
{
|
| 2079 |
+
"epoch": 0.8357971344098248,
|
| 2080 |
+
"grad_norm": 0.12955370545387268,
|
| 2081 |
+
"learning_rate": 0.0004986940669774847,
|
| 2082 |
+
"loss": 0.3641,
|
| 2083 |
+
"step": 14700
|
| 2084 |
+
},
|
| 2085 |
+
{
|
| 2086 |
+
"epoch": 0.8386399818057767,
|
| 2087 |
+
"grad_norm": 0.10223904252052307,
|
| 2088 |
+
"learning_rate": 0.0004986896250284285,
|
| 2089 |
+
"loss": 0.363,
|
| 2090 |
+
"step": 14750
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 0.8414828292017285,
|
| 2094 |
+
"grad_norm": 0.09701918810606003,
|
| 2095 |
+
"learning_rate": 0.0004986851830793723,
|
| 2096 |
+
"loss": 0.3627,
|
| 2097 |
+
"step": 14800
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 0.8443256765976802,
|
| 2101 |
+
"grad_norm": 0.0875435471534729,
|
| 2102 |
+
"learning_rate": 0.0004986807411303161,
|
| 2103 |
+
"loss": 0.3651,
|
| 2104 |
+
"step": 14850
|
| 2105 |
+
},
|
| 2106 |
+
{
|
| 2107 |
+
"epoch": 0.8471685239936321,
|
| 2108 |
+
"grad_norm": 0.09006401896476746,
|
| 2109 |
+
"learning_rate": 0.0004986762991812599,
|
| 2110 |
+
"loss": 0.3632,
|
| 2111 |
+
"step": 14900
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"epoch": 0.8500113713895838,
|
| 2115 |
+
"grad_norm": 0.09841691702604294,
|
| 2116 |
+
"learning_rate": 0.0004986718572322037,
|
| 2117 |
+
"loss": 0.3641,
|
| 2118 |
+
"step": 14950
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"epoch": 0.8528542187855356,
|
| 2122 |
+
"grad_norm": 0.11014077812433243,
|
| 2123 |
+
"learning_rate": 0.0004986674152831477,
|
| 2124 |
+
"loss": 0.3654,
|
| 2125 |
+
"step": 15000
|
| 2126 |
+
},
|
| 2127 |
+
{
|
| 2128 |
+
"epoch": 0.8528542187855356,
|
| 2129 |
+
"eval_loss": 0.3545059561729431,
|
| 2130 |
+
"eval_runtime": 572.3313,
|
| 2131 |
+
"eval_samples_per_second": 230.478,
|
| 2132 |
+
"eval_steps_per_second": 28.81,
|
| 2133 |
+
"step": 15000
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 0.8556970661814873,
|
| 2137 |
+
"grad_norm": 0.11560770869255066,
|
| 2138 |
+
"learning_rate": 0.0004986629733340915,
|
| 2139 |
+
"loss": 0.3644,
|
| 2140 |
+
"step": 15050
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"epoch": 0.8585399135774392,
|
| 2144 |
+
"grad_norm": 0.08875507861375809,
|
| 2145 |
+
"learning_rate": 0.0004986585313850353,
|
| 2146 |
+
"loss": 0.3637,
|
| 2147 |
+
"step": 15100
|
| 2148 |
+
},
|
| 2149 |
+
{
|
| 2150 |
+
"epoch": 0.861382760973391,
|
| 2151 |
+
"grad_norm": 0.09458891302347183,
|
| 2152 |
+
"learning_rate": 0.0004986540894359791,
|
| 2153 |
+
"loss": 0.3638,
|
| 2154 |
+
"step": 15150
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 0.8642256083693427,
|
| 2158 |
+
"grad_norm": 0.10495459288358688,
|
| 2159 |
+
"learning_rate": 0.0004986496474869229,
|
| 2160 |
+
"loss": 0.3647,
|
| 2161 |
+
"step": 15200
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 0.8670684557652946,
|
| 2165 |
+
"grad_norm": 0.10532251745462418,
|
| 2166 |
+
"learning_rate": 0.0004986452055378667,
|
| 2167 |
+
"loss": 0.3664,
|
| 2168 |
+
"step": 15250
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 0.8699113031612463,
|
| 2172 |
+
"grad_norm": 0.09231790155172348,
|
| 2173 |
+
"learning_rate": 0.0004986407635888105,
|
| 2174 |
+
"loss": 0.3643,
|
| 2175 |
+
"step": 15300
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 0.8727541505571981,
|
| 2179 |
+
"grad_norm": 0.09325330704450607,
|
| 2180 |
+
"learning_rate": 0.0004986363216397543,
|
| 2181 |
+
"loss": 0.3659,
|
| 2182 |
+
"step": 15350
|
| 2183 |
+
},
|
| 2184 |
+
{
|
| 2185 |
+
"epoch": 0.8755969979531498,
|
| 2186 |
+
"grad_norm": 0.11519546806812286,
|
| 2187 |
+
"learning_rate": 0.0004986318796906982,
|
| 2188 |
+
"loss": 0.3654,
|
| 2189 |
+
"step": 15400
|
| 2190 |
+
},
|
| 2191 |
+
{
|
| 2192 |
+
"epoch": 0.8784398453491017,
|
| 2193 |
+
"grad_norm": 0.08858964592218399,
|
| 2194 |
+
"learning_rate": 0.0004986274377416421,
|
| 2195 |
+
"loss": 0.3647,
|
| 2196 |
+
"step": 15450
|
| 2197 |
+
},
|
| 2198 |
+
{
|
| 2199 |
+
"epoch": 0.8812826927450534,
|
| 2200 |
+
"grad_norm": 0.11211369931697845,
|
| 2201 |
+
"learning_rate": 0.0004986229957925859,
|
| 2202 |
+
"loss": 0.3646,
|
| 2203 |
+
"step": 15500
|
| 2204 |
+
},
|
| 2205 |
+
{
|
| 2206 |
+
"epoch": 0.8841255401410052,
|
| 2207 |
+
"grad_norm": 0.09691707044839859,
|
| 2208 |
+
"learning_rate": 0.0004986185538435297,
|
| 2209 |
+
"loss": 0.3633,
|
| 2210 |
+
"step": 15550
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 0.8869683875369571,
|
| 2214 |
+
"grad_norm": 0.09831210970878601,
|
| 2215 |
+
"learning_rate": 0.0004986141118944735,
|
| 2216 |
+
"loss": 0.3644,
|
| 2217 |
+
"step": 15600
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 0.8898112349329088,
|
| 2221 |
+
"grad_norm": 0.10148192197084427,
|
| 2222 |
+
"learning_rate": 0.0004986096699454173,
|
| 2223 |
+
"loss": 0.3613,
|
| 2224 |
+
"step": 15650
|
| 2225 |
+
},
|
| 2226 |
+
{
|
| 2227 |
+
"epoch": 0.8926540823288606,
|
| 2228 |
+
"grad_norm": 0.0974993035197258,
|
| 2229 |
+
"learning_rate": 0.0004986052279963611,
|
| 2230 |
+
"loss": 0.3648,
|
| 2231 |
+
"step": 15700
|
| 2232 |
+
},
|
| 2233 |
+
{
|
| 2234 |
+
"epoch": 0.8954969297248123,
|
| 2235 |
+
"grad_norm": 0.09062571078538895,
|
| 2236 |
+
"learning_rate": 0.0004986007860473049,
|
| 2237 |
+
"loss": 0.3622,
|
| 2238 |
+
"step": 15750
|
| 2239 |
+
},
|
| 2240 |
+
{
|
| 2241 |
+
"epoch": 0.8983397771207642,
|
| 2242 |
+
"grad_norm": 0.11505638062953949,
|
| 2243 |
+
"learning_rate": 0.0004985963440982488,
|
| 2244 |
+
"loss": 0.3647,
|
| 2245 |
+
"step": 15800
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 0.9011826245167159,
|
| 2249 |
+
"grad_norm": 0.10409519821405411,
|
| 2250 |
+
"learning_rate": 0.0004985919021491926,
|
| 2251 |
+
"loss": 0.3684,
|
| 2252 |
+
"step": 15850
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 0.9040254719126677,
|
| 2256 |
+
"grad_norm": 0.09695091098546982,
|
| 2257 |
+
"learning_rate": 0.0004985874602001365,
|
| 2258 |
+
"loss": 0.3627,
|
| 2259 |
+
"step": 15900
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 0.9068683193086196,
|
| 2263 |
+
"grad_norm": 0.10802540183067322,
|
| 2264 |
+
"learning_rate": 0.0004985830182510803,
|
| 2265 |
+
"loss": 0.363,
|
| 2266 |
+
"step": 15950
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 0.9097111667045713,
|
| 2270 |
+
"grad_norm": 0.08416867256164551,
|
| 2271 |
+
"learning_rate": 0.0004985785763020242,
|
| 2272 |
+
"loss": 0.3633,
|
| 2273 |
+
"step": 16000
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 0.9125540141005231,
|
| 2277 |
+
"grad_norm": 0.12350185215473175,
|
| 2278 |
+
"learning_rate": 0.000498574134352968,
|
| 2279 |
+
"loss": 0.3645,
|
| 2280 |
+
"step": 16050
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 0.9153968614964749,
|
| 2284 |
+
"grad_norm": 0.10537421703338623,
|
| 2285 |
+
"learning_rate": 0.0004985696924039118,
|
| 2286 |
+
"loss": 0.3635,
|
| 2287 |
+
"step": 16100
|
| 2288 |
+
},
|
| 2289 |
+
{
|
| 2290 |
+
"epoch": 0.9182397088924267,
|
| 2291 |
+
"grad_norm": 0.09744290262460709,
|
| 2292 |
+
"learning_rate": 0.0004985652504548556,
|
| 2293 |
+
"loss": 0.3623,
|
| 2294 |
+
"step": 16150
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 0.9210825562883784,
|
| 2298 |
+
"grad_norm": 0.09753882884979248,
|
| 2299 |
+
"learning_rate": 0.0004985608085057994,
|
| 2300 |
+
"loss": 0.3617,
|
| 2301 |
+
"step": 16200
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 0.9239254036843302,
|
| 2305 |
+
"grad_norm": 0.08662727475166321,
|
| 2306 |
+
"learning_rate": 0.0004985563665567432,
|
| 2307 |
+
"loss": 0.3624,
|
| 2308 |
+
"step": 16250
|
| 2309 |
+
},
|
| 2310 |
+
{
|
| 2311 |
+
"epoch": 0.926768251080282,
|
| 2312 |
+
"grad_norm": 0.09310087561607361,
|
| 2313 |
+
"learning_rate": 0.000498551924607687,
|
| 2314 |
+
"loss": 0.3631,
|
| 2315 |
+
"step": 16300
|
| 2316 |
+
},
|
| 2317 |
+
{
|
| 2318 |
+
"epoch": 0.9296110984762338,
|
| 2319 |
+
"grad_norm": 0.10131137073040009,
|
| 2320 |
+
"learning_rate": 0.0004985474826586308,
|
| 2321 |
+
"loss": 0.3593,
|
| 2322 |
+
"step": 16350
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 0.9324539458721856,
|
| 2326 |
+
"grad_norm": 0.09597592055797577,
|
| 2327 |
+
"learning_rate": 0.0004985430407095748,
|
| 2328 |
+
"loss": 0.3628,
|
| 2329 |
+
"step": 16400
|
| 2330 |
+
},
|
| 2331 |
+
{
|
| 2332 |
+
"epoch": 0.9352967932681374,
|
| 2333 |
+
"grad_norm": 0.09163256734609604,
|
| 2334 |
+
"learning_rate": 0.0004985385987605186,
|
| 2335 |
+
"loss": 0.3596,
|
| 2336 |
+
"step": 16450
|
| 2337 |
+
},
|
| 2338 |
+
{
|
| 2339 |
+
"epoch": 0.9381396406640892,
|
| 2340 |
+
"grad_norm": 0.11283744126558304,
|
| 2341 |
+
"learning_rate": 0.0004985341568114624,
|
| 2342 |
+
"loss": 0.3629,
|
| 2343 |
+
"step": 16500
|
| 2344 |
+
},
|
| 2345 |
+
{
|
| 2346 |
+
"epoch": 0.9409824880600409,
|
| 2347 |
+
"grad_norm": 0.1027892455458641,
|
| 2348 |
+
"learning_rate": 0.0004985297148624062,
|
| 2349 |
+
"loss": 0.3624,
|
| 2350 |
+
"step": 16550
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"epoch": 0.9438253354559927,
|
| 2354 |
+
"grad_norm": 0.09853541105985641,
|
| 2355 |
+
"learning_rate": 0.00049852527291335,
|
| 2356 |
+
"loss": 0.3606,
|
| 2357 |
+
"step": 16600
|
| 2358 |
+
},
|
| 2359 |
+
{
|
| 2360 |
+
"epoch": 0.9466681828519445,
|
| 2361 |
+
"grad_norm": 0.09280608594417572,
|
| 2362 |
+
"learning_rate": 0.0004985208309642938,
|
| 2363 |
+
"loss": 0.3626,
|
| 2364 |
+
"step": 16650
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 0.9495110302478963,
|
| 2368 |
+
"grad_norm": 0.09166574478149414,
|
| 2369 |
+
"learning_rate": 0.0004985163890152376,
|
| 2370 |
+
"loss": 0.3631,
|
| 2371 |
+
"step": 16700
|
| 2372 |
+
},
|
| 2373 |
+
{
|
| 2374 |
+
"epoch": 0.952353877643848,
|
| 2375 |
+
"grad_norm": 0.10630334913730621,
|
| 2376 |
+
"learning_rate": 0.0004985119470661814,
|
| 2377 |
+
"loss": 0.3611,
|
| 2378 |
+
"step": 16750
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 0.9551967250397999,
|
| 2382 |
+
"grad_norm": 0.09024935215711594,
|
| 2383 |
+
"learning_rate": 0.0004985075051171253,
|
| 2384 |
+
"loss": 0.3627,
|
| 2385 |
+
"step": 16800
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 0.9580395724357517,
|
| 2389 |
+
"grad_norm": 0.08191289007663727,
|
| 2390 |
+
"learning_rate": 0.0004985030631680692,
|
| 2391 |
+
"loss": 0.3586,
|
| 2392 |
+
"step": 16850
|
| 2393 |
+
},
|
| 2394 |
+
{
|
| 2395 |
+
"epoch": 0.9608824198317034,
|
| 2396 |
+
"grad_norm": 0.08423138409852982,
|
| 2397 |
+
"learning_rate": 0.000498498621219013,
|
| 2398 |
+
"loss": 0.3622,
|
| 2399 |
+
"step": 16900
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 0.9637252672276552,
|
| 2403 |
+
"grad_norm": 0.09373466670513153,
|
| 2404 |
+
"learning_rate": 0.0004984941792699568,
|
| 2405 |
+
"loss": 0.3611,
|
| 2406 |
+
"step": 16950
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 0.966568114623607,
|
| 2410 |
+
"grad_norm": 0.09812022745609283,
|
| 2411 |
+
"learning_rate": 0.0004984897373209006,
|
| 2412 |
+
"loss": 0.3627,
|
| 2413 |
+
"step": 17000
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 0.9694109620195588,
|
| 2417 |
+
"grad_norm": 0.09764017909765244,
|
| 2418 |
+
"learning_rate": 0.0004984852953718444,
|
| 2419 |
+
"loss": 0.3589,
|
| 2420 |
+
"step": 17050
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 0.9722538094155105,
|
| 2424 |
+
"grad_norm": 0.10176458954811096,
|
| 2425 |
+
"learning_rate": 0.0004984808534227883,
|
| 2426 |
+
"loss": 0.3594,
|
| 2427 |
+
"step": 17100
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 0.9750966568114624,
|
| 2431 |
+
"grad_norm": 0.10278456658124924,
|
| 2432 |
+
"learning_rate": 0.0004984764114737321,
|
| 2433 |
+
"loss": 0.3581,
|
| 2434 |
+
"step": 17150
|
| 2435 |
+
},
|
| 2436 |
+
{
|
| 2437 |
+
"epoch": 0.9779395042074142,
|
| 2438 |
+
"grad_norm": 0.1218334510922432,
|
| 2439 |
+
"learning_rate": 0.0004984719695246759,
|
| 2440 |
+
"loss": 0.3606,
|
| 2441 |
+
"step": 17200
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 0.9807823516033659,
|
| 2445 |
+
"grad_norm": 0.09451757371425629,
|
| 2446 |
+
"learning_rate": 0.0004984675275756197,
|
| 2447 |
+
"loss": 0.3614,
|
| 2448 |
+
"step": 17250
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 0.9836251989993177,
|
| 2452 |
+
"grad_norm": 0.10088694840669632,
|
| 2453 |
+
"learning_rate": 0.0004984630856265636,
|
| 2454 |
+
"loss": 0.3604,
|
| 2455 |
+
"step": 17300
|
| 2456 |
+
},
|
| 2457 |
+
{
|
| 2458 |
+
"epoch": 0.9864680463952695,
|
| 2459 |
+
"grad_norm": 0.10026043653488159,
|
| 2460 |
+
"learning_rate": 0.0004984586436775075,
|
| 2461 |
+
"loss": 0.3604,
|
| 2462 |
+
"step": 17350
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 0.9893108937912213,
|
| 2466 |
+
"grad_norm": 0.11412831395864487,
|
| 2467 |
+
"learning_rate": 0.0004984542017284513,
|
| 2468 |
+
"loss": 0.3608,
|
| 2469 |
+
"step": 17400
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 0.992153741187173,
|
| 2473 |
+
"grad_norm": 0.10250277817249298,
|
| 2474 |
+
"learning_rate": 0.0004984497597793951,
|
| 2475 |
+
"loss": 0.3597,
|
| 2476 |
+
"step": 17450
|
| 2477 |
+
},
|
| 2478 |
+
{
|
| 2479 |
+
"epoch": 0.9949965885831249,
|
| 2480 |
+
"grad_norm": 0.10922574251890182,
|
| 2481 |
+
"learning_rate": 0.0004984453178303389,
|
| 2482 |
+
"loss": 0.3611,
|
| 2483 |
+
"step": 17500
|
| 2484 |
+
},
|
| 2485 |
+
{
|
| 2486 |
+
"epoch": 0.9978394359790766,
|
| 2487 |
+
"grad_norm": 0.09554197639226913,
|
| 2488 |
+
"learning_rate": 0.0004984408758812827,
|
| 2489 |
+
"loss": 0.3596,
|
| 2490 |
+
"step": 17550
|
| 2491 |
+
},
|
| 2492 |
+
{
|
| 2493 |
+
"epoch": 1.0006822833750284,
|
| 2494 |
+
"grad_norm": 0.11213108897209167,
|
| 2495 |
+
"learning_rate": 0.0004984364339322265,
|
| 2496 |
+
"loss": 0.3617,
|
| 2497 |
+
"step": 17600
|
| 2498 |
+
},
|
| 2499 |
+
{
|
| 2500 |
+
"epoch": 1.0035251307709803,
|
| 2501 |
+
"grad_norm": 0.13735197484493256,
|
| 2502 |
+
"learning_rate": 0.0004984319919831703,
|
| 2503 |
+
"loss": 0.3528,
|
| 2504 |
+
"step": 17650
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 1.006367978166932,
|
| 2508 |
+
"grad_norm": 0.10477373749017715,
|
| 2509 |
+
"learning_rate": 0.0004984275500341141,
|
| 2510 |
+
"loss": 0.3561,
|
| 2511 |
+
"step": 17700
|
| 2512 |
+
},
|
| 2513 |
+
{
|
| 2514 |
+
"epoch": 1.0092108255628838,
|
| 2515 |
+
"grad_norm": 0.10232077538967133,
|
| 2516 |
+
"learning_rate": 0.0004984231080850581,
|
| 2517 |
+
"loss": 0.3563,
|
| 2518 |
+
"step": 17750
|
| 2519 |
+
},
|
| 2520 |
+
{
|
| 2521 |
+
"epoch": 1.0120536729588356,
|
| 2522 |
+
"grad_norm": 0.11949522793292999,
|
| 2523 |
+
"learning_rate": 0.0004984186661360019,
|
| 2524 |
+
"loss": 0.3534,
|
| 2525 |
+
"step": 17800
|
| 2526 |
+
},
|
| 2527 |
+
{
|
| 2528 |
+
"epoch": 1.0148965203547873,
|
| 2529 |
+
"grad_norm": 0.10367763787508011,
|
| 2530 |
+
"learning_rate": 0.0004984142241869457,
|
| 2531 |
+
"loss": 0.3564,
|
| 2532 |
+
"step": 17850
|
| 2533 |
+
},
|
| 2534 |
+
{
|
| 2535 |
+
"epoch": 1.0177393677507391,
|
| 2536 |
+
"grad_norm": 0.11785215884447098,
|
| 2537 |
+
"learning_rate": 0.0004984097822378895,
|
| 2538 |
+
"loss": 0.3584,
|
| 2539 |
+
"step": 17900
|
| 2540 |
+
},
|
| 2541 |
+
{
|
| 2542 |
+
"epoch": 1.020582215146691,
|
| 2543 |
+
"grad_norm": 0.09687703847885132,
|
| 2544 |
+
"learning_rate": 0.0004984053402888333,
|
| 2545 |
+
"loss": 0.356,
|
| 2546 |
+
"step": 17950
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 1.0234250625426426,
|
| 2550 |
+
"grad_norm": 0.1126837283372879,
|
| 2551 |
+
"learning_rate": 0.0004984008983397771,
|
| 2552 |
+
"loss": 0.3545,
|
| 2553 |
+
"step": 18000
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 1.0262679099385945,
|
| 2557 |
+
"grad_norm": 0.0994856208562851,
|
| 2558 |
+
"learning_rate": 0.0004983964563907209,
|
| 2559 |
+
"loss": 0.3556,
|
| 2560 |
+
"step": 18050
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 1.0291107573345464,
|
| 2564 |
+
"grad_norm": 0.09857575595378876,
|
| 2565 |
+
"learning_rate": 0.0004983920144416647,
|
| 2566 |
+
"loss": 0.3596,
|
| 2567 |
+
"step": 18100
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 1.031953604730498,
|
| 2571 |
+
"grad_norm": 0.10661829262971878,
|
| 2572 |
+
"learning_rate": 0.0004983875724926086,
|
| 2573 |
+
"loss": 0.3557,
|
| 2574 |
+
"step": 18150
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 1.0347964521264499,
|
| 2578 |
+
"grad_norm": 0.08805033564567566,
|
| 2579 |
+
"learning_rate": 0.0004983831305435525,
|
| 2580 |
+
"loss": 0.3552,
|
| 2581 |
+
"step": 18200
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 1.0376392995224015,
|
| 2585 |
+
"grad_norm": 0.09851615130901337,
|
| 2586 |
+
"learning_rate": 0.0004983786885944963,
|
| 2587 |
+
"loss": 0.3595,
|
| 2588 |
+
"step": 18250
|
| 2589 |
+
},
|
| 2590 |
+
{
|
| 2591 |
+
"epoch": 1.0404821469183534,
|
| 2592 |
+
"grad_norm": 0.10526396334171295,
|
| 2593 |
+
"learning_rate": 0.0004983742466454401,
|
| 2594 |
+
"loss": 0.3557,
|
| 2595 |
+
"step": 18300
|
| 2596 |
+
},
|
| 2597 |
+
{
|
| 2598 |
+
"epoch": 1.0433249943143053,
|
| 2599 |
+
"grad_norm": 0.10095933824777603,
|
| 2600 |
+
"learning_rate": 0.0004983698046963839,
|
| 2601 |
+
"loss": 0.3545,
|
| 2602 |
+
"step": 18350
|
| 2603 |
+
},
|
| 2604 |
+
{
|
| 2605 |
+
"epoch": 1.046167841710257,
|
| 2606 |
+
"grad_norm": 0.0906311646103859,
|
| 2607 |
+
"learning_rate": 0.0004983653627473278,
|
| 2608 |
+
"loss": 0.3539,
|
| 2609 |
+
"step": 18400
|
| 2610 |
+
},
|
| 2611 |
+
{
|
| 2612 |
+
"epoch": 1.0490106891062088,
|
| 2613 |
+
"grad_norm": 0.10459648072719574,
|
| 2614 |
+
"learning_rate": 0.0004983609207982716,
|
| 2615 |
+
"loss": 0.3551,
|
| 2616 |
+
"step": 18450
|
| 2617 |
+
},
|
| 2618 |
+
{
|
| 2619 |
+
"epoch": 1.0518535365021606,
|
| 2620 |
+
"grad_norm": 0.08786173164844513,
|
| 2621 |
+
"learning_rate": 0.0004983564788492154,
|
| 2622 |
+
"loss": 0.3534,
|
| 2623 |
+
"step": 18500
|
| 2624 |
+
},
|
| 2625 |
+
{
|
| 2626 |
+
"epoch": 1.0546963838981123,
|
| 2627 |
+
"grad_norm": 0.10580555349588394,
|
| 2628 |
+
"learning_rate": 0.0004983520369001592,
|
| 2629 |
+
"loss": 0.3552,
|
| 2630 |
+
"step": 18550
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 1.0575392312940641,
|
| 2634 |
+
"grad_norm": 0.09845657646656036,
|
| 2635 |
+
"learning_rate": 0.000498347594951103,
|
| 2636 |
+
"loss": 0.3567,
|
| 2637 |
+
"step": 18600
|
| 2638 |
+
},
|
| 2639 |
+
{
|
| 2640 |
+
"epoch": 1.060382078690016,
|
| 2641 |
+
"grad_norm": 0.09070323407649994,
|
| 2642 |
+
"learning_rate": 0.0004983431530020468,
|
| 2643 |
+
"loss": 0.3572,
|
| 2644 |
+
"step": 18650
|
| 2645 |
+
},
|
| 2646 |
+
{
|
| 2647 |
+
"epoch": 1.0632249260859676,
|
| 2648 |
+
"grad_norm": 0.11504799127578735,
|
| 2649 |
+
"learning_rate": 0.0004983387110529907,
|
| 2650 |
+
"loss": 0.3546,
|
| 2651 |
+
"step": 18700
|
| 2652 |
+
},
|
| 2653 |
+
{
|
| 2654 |
+
"epoch": 1.0660677734819195,
|
| 2655 |
+
"grad_norm": 0.0939740464091301,
|
| 2656 |
+
"learning_rate": 0.0004983342691039346,
|
| 2657 |
+
"loss": 0.3572,
|
| 2658 |
+
"step": 18750
|
| 2659 |
+
},
|
| 2660 |
+
{
|
| 2661 |
+
"epoch": 1.0689106208778714,
|
| 2662 |
+
"grad_norm": 0.11082996428012848,
|
| 2663 |
+
"learning_rate": 0.0004983298271548784,
|
| 2664 |
+
"loss": 0.357,
|
| 2665 |
+
"step": 18800
|
| 2666 |
+
},
|
| 2667 |
+
{
|
| 2668 |
+
"epoch": 1.071753468273823,
|
| 2669 |
+
"grad_norm": 0.09426229447126389,
|
| 2670 |
+
"learning_rate": 0.0004983253852058222,
|
| 2671 |
+
"loss": 0.3552,
|
| 2672 |
+
"step": 18850
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 1.0745963156697749,
|
| 2676 |
+
"grad_norm": 0.09430352598428726,
|
| 2677 |
+
"learning_rate": 0.000498320943256766,
|
| 2678 |
+
"loss": 0.3559,
|
| 2679 |
+
"step": 18900
|
| 2680 |
+
},
|
| 2681 |
+
{
|
| 2682 |
+
"epoch": 1.0774391630657267,
|
| 2683 |
+
"grad_norm": 0.11377741396427155,
|
| 2684 |
+
"learning_rate": 0.0004983165013077098,
|
| 2685 |
+
"loss": 0.3517,
|
| 2686 |
+
"step": 18950
|
| 2687 |
+
},
|
| 2688 |
+
{
|
| 2689 |
+
"epoch": 1.0802820104616784,
|
| 2690 |
+
"grad_norm": 0.0836120992898941,
|
| 2691 |
+
"learning_rate": 0.0004983120593586536,
|
| 2692 |
+
"loss": 0.3546,
|
| 2693 |
+
"step": 19000
|
| 2694 |
+
},
|
| 2695 |
+
{
|
| 2696 |
+
"epoch": 1.0831248578576302,
|
| 2697 |
+
"grad_norm": 0.09483205527067184,
|
| 2698 |
+
"learning_rate": 0.0004983076174095974,
|
| 2699 |
+
"loss": 0.354,
|
| 2700 |
+
"step": 19050
|
| 2701 |
+
},
|
| 2702 |
+
{
|
| 2703 |
+
"epoch": 1.0859677052535819,
|
| 2704 |
+
"grad_norm": 0.08619007468223572,
|
| 2705 |
+
"learning_rate": 0.0004983031754605412,
|
| 2706 |
+
"loss": 0.3526,
|
| 2707 |
+
"step": 19100
|
| 2708 |
+
},
|
| 2709 |
+
{
|
| 2710 |
+
"epoch": 1.0888105526495337,
|
| 2711 |
+
"grad_norm": 0.09521963447332382,
|
| 2712 |
+
"learning_rate": 0.0004982987335114852,
|
| 2713 |
+
"loss": 0.3542,
|
| 2714 |
+
"step": 19150
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 1.0916534000454856,
|
| 2718 |
+
"grad_norm": 0.08765676617622375,
|
| 2719 |
+
"learning_rate": 0.000498294291562429,
|
| 2720 |
+
"loss": 0.3542,
|
| 2721 |
+
"step": 19200
|
| 2722 |
+
},
|
| 2723 |
+
{
|
| 2724 |
+
"epoch": 1.0944962474414373,
|
| 2725 |
+
"grad_norm": 0.10146308690309525,
|
| 2726 |
+
"learning_rate": 0.0004982898496133728,
|
| 2727 |
+
"loss": 0.3559,
|
| 2728 |
+
"step": 19250
|
| 2729 |
+
},
|
| 2730 |
+
{
|
| 2731 |
+
"epoch": 1.0973390948373891,
|
| 2732 |
+
"grad_norm": 0.09321428835391998,
|
| 2733 |
+
"learning_rate": 0.0004982854076643166,
|
| 2734 |
+
"loss": 0.3576,
|
| 2735 |
+
"step": 19300
|
| 2736 |
+
},
|
| 2737 |
+
{
|
| 2738 |
+
"epoch": 1.100181942233341,
|
| 2739 |
+
"grad_norm": 0.11401006579399109,
|
| 2740 |
+
"learning_rate": 0.0004982809657152604,
|
| 2741 |
+
"loss": 0.3549,
|
| 2742 |
+
"step": 19350
|
| 2743 |
+
},
|
| 2744 |
+
{
|
| 2745 |
+
"epoch": 1.1030247896292926,
|
| 2746 |
+
"grad_norm": 0.11573155969381332,
|
| 2747 |
+
"learning_rate": 0.0004982765237662042,
|
| 2748 |
+
"loss": 0.3569,
|
| 2749 |
+
"step": 19400
|
| 2750 |
+
},
|
| 2751 |
+
{
|
| 2752 |
+
"epoch": 1.1058676370252445,
|
| 2753 |
+
"grad_norm": 0.08966556191444397,
|
| 2754 |
+
"learning_rate": 0.000498272081817148,
|
| 2755 |
+
"loss": 0.3603,
|
| 2756 |
+
"step": 19450
|
| 2757 |
+
},
|
| 2758 |
+
{
|
| 2759 |
+
"epoch": 1.1087104844211964,
|
| 2760 |
+
"grad_norm": 0.12934494018554688,
|
| 2761 |
+
"learning_rate": 0.0004982676398680918,
|
| 2762 |
+
"loss": 0.3533,
|
| 2763 |
+
"step": 19500
|
| 2764 |
+
},
|
| 2765 |
+
{
|
| 2766 |
+
"epoch": 1.111553331817148,
|
| 2767 |
+
"grad_norm": 0.13741086423397064,
|
| 2768 |
+
"learning_rate": 0.0004982631979190357,
|
| 2769 |
+
"loss": 0.3542,
|
| 2770 |
+
"step": 19550
|
| 2771 |
+
},
|
| 2772 |
+
{
|
| 2773 |
+
"epoch": 1.1143961792130999,
|
| 2774 |
+
"grad_norm": 0.10928856581449509,
|
| 2775 |
+
"learning_rate": 0.0004982587559699796,
|
| 2776 |
+
"loss": 0.3559,
|
| 2777 |
+
"step": 19600
|
| 2778 |
+
},
|
| 2779 |
+
{
|
| 2780 |
+
"epoch": 1.1172390266090517,
|
| 2781 |
+
"grad_norm": 0.09697018563747406,
|
| 2782 |
+
"learning_rate": 0.0004982543140209234,
|
| 2783 |
+
"loss": 0.3559,
|
| 2784 |
+
"step": 19650
|
| 2785 |
+
},
|
| 2786 |
+
{
|
| 2787 |
+
"epoch": 1.1200818740050034,
|
| 2788 |
+
"grad_norm": 0.09221459925174713,
|
| 2789 |
+
"learning_rate": 0.0004982498720718672,
|
| 2790 |
+
"loss": 0.3554,
|
| 2791 |
+
"step": 19700
|
| 2792 |
+
},
|
| 2793 |
+
{
|
| 2794 |
+
"epoch": 1.1229247214009552,
|
| 2795 |
+
"grad_norm": 0.091732919216156,
|
| 2796 |
+
"learning_rate": 0.0004982454301228111,
|
| 2797 |
+
"loss": 0.352,
|
| 2798 |
+
"step": 19750
|
| 2799 |
+
},
|
| 2800 |
+
{
|
| 2801 |
+
"epoch": 1.125767568796907,
|
| 2802 |
+
"grad_norm": 0.10662009567022324,
|
| 2803 |
+
"learning_rate": 0.0004982409881737549,
|
| 2804 |
+
"loss": 0.3582,
|
| 2805 |
+
"step": 19800
|
| 2806 |
+
},
|
| 2807 |
+
{
|
| 2808 |
+
"epoch": 1.1286104161928587,
|
| 2809 |
+
"grad_norm": 0.08810966461896896,
|
| 2810 |
+
"learning_rate": 0.0004982365462246987,
|
| 2811 |
+
"loss": 0.3534,
|
| 2812 |
+
"step": 19850
|
| 2813 |
+
},
|
| 2814 |
+
{
|
| 2815 |
+
"epoch": 1.1314532635888106,
|
| 2816 |
+
"grad_norm": 0.10295290499925613,
|
| 2817 |
+
"learning_rate": 0.0004982321042756425,
|
| 2818 |
+
"loss": 0.3577,
|
| 2819 |
+
"step": 19900
|
| 2820 |
+
},
|
| 2821 |
+
{
|
| 2822 |
+
"epoch": 1.1342961109847622,
|
| 2823 |
+
"grad_norm": 0.08759327977895737,
|
| 2824 |
+
"learning_rate": 0.0004982276623265863,
|
| 2825 |
+
"loss": 0.3529,
|
| 2826 |
+
"step": 19950
|
| 2827 |
+
},
|
| 2828 |
+
{
|
| 2829 |
+
"epoch": 1.137138958380714,
|
| 2830 |
+
"grad_norm": 0.08622145652770996,
|
| 2831 |
+
"learning_rate": 0.0004982232203775301,
|
| 2832 |
+
"loss": 0.3541,
|
| 2833 |
+
"step": 20000
|
| 2834 |
+
},
|
| 2835 |
+
{
|
| 2836 |
+
"epoch": 1.137138958380714,
|
| 2837 |
+
"eval_loss": 0.3468220829963684,
|
| 2838 |
+
"eval_runtime": 575.5127,
|
| 2839 |
+
"eval_samples_per_second": 229.204,
|
| 2840 |
+
"eval_steps_per_second": 28.651,
|
| 2841 |
+
"step": 20000
|
| 2842 |
+
},
|
| 2843 |
+
{
|
| 2844 |
+
"epoch": 1.139981805776666,
|
| 2845 |
+
"grad_norm": 0.09593155980110168,
|
| 2846 |
+
"learning_rate": 0.000498218778428474,
|
| 2847 |
+
"loss": 0.3533,
|
| 2848 |
+
"step": 20050
|
| 2849 |
+
},
|
| 2850 |
+
{
|
| 2851 |
+
"epoch": 1.1428246531726176,
|
| 2852 |
+
"grad_norm": 0.1172272190451622,
|
| 2853 |
+
"learning_rate": 0.0004982143364794178,
|
| 2854 |
+
"loss": 0.3513,
|
| 2855 |
+
"step": 20100
|
| 2856 |
+
},
|
| 2857 |
+
{
|
| 2858 |
+
"epoch": 1.1456675005685695,
|
| 2859 |
+
"grad_norm": 0.10402148216962814,
|
| 2860 |
+
"learning_rate": 0.0004982098945303617,
|
| 2861 |
+
"loss": 0.3587,
|
| 2862 |
+
"step": 20150
|
| 2863 |
+
},
|
| 2864 |
+
{
|
| 2865 |
+
"epoch": 1.1485103479645213,
|
| 2866 |
+
"grad_norm": 0.14057371020317078,
|
| 2867 |
+
"learning_rate": 0.0004982054525813055,
|
| 2868 |
+
"loss": 0.3525,
|
| 2869 |
+
"step": 20200
|
| 2870 |
+
},
|
| 2871 |
+
{
|
| 2872 |
+
"epoch": 1.151353195360473,
|
| 2873 |
+
"grad_norm": 0.11363080888986588,
|
| 2874 |
+
"learning_rate": 0.0004982010106322493,
|
| 2875 |
+
"loss": 0.3527,
|
| 2876 |
+
"step": 20250
|
| 2877 |
+
},
|
| 2878 |
+
{
|
| 2879 |
+
"epoch": 1.1541960427564248,
|
| 2880 |
+
"grad_norm": 0.10476770997047424,
|
| 2881 |
+
"learning_rate": 0.0004981965686831931,
|
| 2882 |
+
"loss": 0.354,
|
| 2883 |
+
"step": 20300
|
| 2884 |
+
},
|
| 2885 |
+
{
|
| 2886 |
+
"epoch": 1.1570388901523767,
|
| 2887 |
+
"grad_norm": 0.11272389441728592,
|
| 2888 |
+
"learning_rate": 0.0004981921267341369,
|
| 2889 |
+
"loss": 0.3562,
|
| 2890 |
+
"step": 20350
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"epoch": 1.1598817375483284,
|
| 2894 |
+
"grad_norm": 0.0867941826581955,
|
| 2895 |
+
"learning_rate": 0.0004981876847850807,
|
| 2896 |
+
"loss": 0.3531,
|
| 2897 |
+
"step": 20400
|
| 2898 |
+
},
|
| 2899 |
+
{
|
| 2900 |
+
"epoch": 1.1627245849442802,
|
| 2901 |
+
"grad_norm": 0.12125921249389648,
|
| 2902 |
+
"learning_rate": 0.0004981832428360245,
|
| 2903 |
+
"loss": 0.3523,
|
| 2904 |
+
"step": 20450
|
| 2905 |
+
},
|
| 2906 |
+
{
|
| 2907 |
+
"epoch": 1.1655674323402319,
|
| 2908 |
+
"grad_norm": 0.09518919885158539,
|
| 2909 |
+
"learning_rate": 0.0004981788008869683,
|
| 2910 |
+
"loss": 0.3562,
|
| 2911 |
+
"step": 20500
|
| 2912 |
+
},
|
| 2913 |
+
{
|
| 2914 |
+
"epoch": 1.1684102797361837,
|
| 2915 |
+
"grad_norm": 0.09472860395908356,
|
| 2916 |
+
"learning_rate": 0.0004981743589379123,
|
| 2917 |
+
"loss": 0.3555,
|
| 2918 |
+
"step": 20550
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 1.1712531271321356,
|
| 2922 |
+
"grad_norm": 0.09812992066144943,
|
| 2923 |
+
"learning_rate": 0.0004981699169888561,
|
| 2924 |
+
"loss": 0.3559,
|
| 2925 |
+
"step": 20600
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 1.1740959745280874,
|
| 2929 |
+
"grad_norm": 0.09982824325561523,
|
| 2930 |
+
"learning_rate": 0.0004981654750397999,
|
| 2931 |
+
"loss": 0.3511,
|
| 2932 |
+
"step": 20650
|
| 2933 |
+
},
|
| 2934 |
+
{
|
| 2935 |
+
"epoch": 1.176938821924039,
|
| 2936 |
+
"grad_norm": 0.11572203040122986,
|
| 2937 |
+
"learning_rate": 0.0004981610330907437,
|
| 2938 |
+
"loss": 0.3524,
|
| 2939 |
+
"step": 20700
|
| 2940 |
+
},
|
| 2941 |
+
{
|
| 2942 |
+
"epoch": 1.179781669319991,
|
| 2943 |
+
"grad_norm": 0.113502636551857,
|
| 2944 |
+
"learning_rate": 0.0004981565911416875,
|
| 2945 |
+
"loss": 0.3526,
|
| 2946 |
+
"step": 20750
|
| 2947 |
+
},
|
| 2948 |
+
{
|
| 2949 |
+
"epoch": 1.1826245167159426,
|
| 2950 |
+
"grad_norm": 0.09475291520357132,
|
| 2951 |
+
"learning_rate": 0.0004981521491926313,
|
| 2952 |
+
"loss": 0.3536,
|
| 2953 |
+
"step": 20800
|
| 2954 |
+
},
|
| 2955 |
+
{
|
| 2956 |
+
"epoch": 1.1854673641118945,
|
| 2957 |
+
"grad_norm": 0.09980995953083038,
|
| 2958 |
+
"learning_rate": 0.0004981477072435751,
|
| 2959 |
+
"loss": 0.3525,
|
| 2960 |
+
"step": 20850
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"epoch": 1.1883102115078463,
|
| 2964 |
+
"grad_norm": 0.09389813244342804,
|
| 2965 |
+
"learning_rate": 0.0004981432652945189,
|
| 2966 |
+
"loss": 0.3536,
|
| 2967 |
+
"step": 20900
|
| 2968 |
+
},
|
| 2969 |
+
{
|
| 2970 |
+
"epoch": 1.191153058903798,
|
| 2971 |
+
"grad_norm": 0.09969864040613174,
|
| 2972 |
+
"learning_rate": 0.0004981388233454628,
|
| 2973 |
+
"loss": 0.3536,
|
| 2974 |
+
"step": 20950
|
| 2975 |
+
},
|
| 2976 |
+
{
|
| 2977 |
+
"epoch": 1.1939959062997498,
|
| 2978 |
+
"grad_norm": 0.08675362169742584,
|
| 2979 |
+
"learning_rate": 0.0004981343813964067,
|
| 2980 |
+
"loss": 0.3538,
|
| 2981 |
+
"step": 21000
|
| 2982 |
+
},
|
| 2983 |
+
{
|
| 2984 |
+
"epoch": 1.1968387536957017,
|
| 2985 |
+
"grad_norm": 0.13347360491752625,
|
| 2986 |
+
"learning_rate": 0.0004981299394473505,
|
| 2987 |
+
"loss": 0.3536,
|
| 2988 |
+
"step": 21050
|
| 2989 |
+
},
|
| 2990 |
+
{
|
| 2991 |
+
"epoch": 1.1996816010916533,
|
| 2992 |
+
"grad_norm": 0.1156553402543068,
|
| 2993 |
+
"learning_rate": 0.0004981254974982943,
|
| 2994 |
+
"loss": 0.3516,
|
| 2995 |
+
"step": 21100
|
| 2996 |
+
},
|
| 2997 |
+
{
|
| 2998 |
+
"epoch": 1.2025244484876052,
|
| 2999 |
+
"grad_norm": 0.08983340859413147,
|
| 3000 |
+
"learning_rate": 0.0004981210555492382,
|
| 3001 |
+
"loss": 0.3537,
|
| 3002 |
+
"step": 21150
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 1.205367295883557,
|
| 3006 |
+
"grad_norm": 0.0790681466460228,
|
| 3007 |
+
"learning_rate": 0.000498116613600182,
|
| 3008 |
+
"loss": 0.3527,
|
| 3009 |
+
"step": 21200
|
| 3010 |
+
},
|
| 3011 |
+
{
|
| 3012 |
+
"epoch": 1.2082101432795087,
|
| 3013 |
+
"grad_norm": 0.12216062098741531,
|
| 3014 |
+
"learning_rate": 0.0004981121716511258,
|
| 3015 |
+
"loss": 0.3535,
|
| 3016 |
+
"step": 21250
|
| 3017 |
+
},
|
| 3018 |
+
{
|
| 3019 |
+
"epoch": 1.2110529906754606,
|
| 3020 |
+
"grad_norm": 0.08232084661722183,
|
| 3021 |
+
"learning_rate": 0.0004981077297020696,
|
| 3022 |
+
"loss": 0.3543,
|
| 3023 |
+
"step": 21300
|
| 3024 |
+
},
|
| 3025 |
+
{
|
| 3026 |
+
"epoch": 1.2138958380714122,
|
| 3027 |
+
"grad_norm": 0.09808045625686646,
|
| 3028 |
+
"learning_rate": 0.0004981032877530134,
|
| 3029 |
+
"loss": 0.3526,
|
| 3030 |
+
"step": 21350
|
| 3031 |
+
},
|
| 3032 |
+
{
|
| 3033 |
+
"epoch": 1.216738685467364,
|
| 3034 |
+
"grad_norm": 0.0974017009139061,
|
| 3035 |
+
"learning_rate": 0.0004980988458039572,
|
| 3036 |
+
"loss": 0.3518,
|
| 3037 |
+
"step": 21400
|
| 3038 |
+
},
|
| 3039 |
+
{
|
| 3040 |
+
"epoch": 1.219581532863316,
|
| 3041 |
+
"grad_norm": 0.11234429478645325,
|
| 3042 |
+
"learning_rate": 0.000498094403854901,
|
| 3043 |
+
"loss": 0.3549,
|
| 3044 |
+
"step": 21450
|
| 3045 |
+
},
|
| 3046 |
+
{
|
| 3047 |
+
"epoch": 1.2224243802592678,
|
| 3048 |
+
"grad_norm": 0.0913853719830513,
|
| 3049 |
+
"learning_rate": 0.0004980899619058449,
|
| 3050 |
+
"loss": 0.3572,
|
| 3051 |
+
"step": 21500
|
| 3052 |
+
},
|
| 3053 |
+
{
|
| 3054 |
+
"epoch": 1.2252672276552194,
|
| 3055 |
+
"grad_norm": 0.11108215898275375,
|
| 3056 |
+
"learning_rate": 0.0004980855199567888,
|
| 3057 |
+
"loss": 0.3532,
|
| 3058 |
+
"step": 21550
|
| 3059 |
+
},
|
| 3060 |
+
{
|
| 3061 |
+
"epoch": 1.2281100750511713,
|
| 3062 |
+
"grad_norm": 0.09476979076862335,
|
| 3063 |
+
"learning_rate": 0.0004980810780077326,
|
| 3064 |
+
"loss": 0.3557,
|
| 3065 |
+
"step": 21600
|
| 3066 |
+
},
|
| 3067 |
+
{
|
| 3068 |
+
"epoch": 1.230952922447123,
|
| 3069 |
+
"grad_norm": 0.0904000923037529,
|
| 3070 |
+
"learning_rate": 0.0004980766360586764,
|
| 3071 |
+
"loss": 0.3512,
|
| 3072 |
+
"step": 21650
|
| 3073 |
+
},
|
| 3074 |
+
{
|
| 3075 |
+
"epoch": 1.2337957698430748,
|
| 3076 |
+
"grad_norm": 0.09948475658893585,
|
| 3077 |
+
"learning_rate": 0.0004980721941096202,
|
| 3078 |
+
"loss": 0.3533,
|
| 3079 |
+
"step": 21700
|
| 3080 |
+
},
|
| 3081 |
+
{
|
| 3082 |
+
"epoch": 1.2366386172390267,
|
| 3083 |
+
"grad_norm": 0.0987270325422287,
|
| 3084 |
+
"learning_rate": 0.000498067752160564,
|
| 3085 |
+
"loss": 0.354,
|
| 3086 |
+
"step": 21750
|
| 3087 |
+
},
|
| 3088 |
+
{
|
| 3089 |
+
"epoch": 1.2394814646349783,
|
| 3090 |
+
"grad_norm": 0.10672775655984879,
|
| 3091 |
+
"learning_rate": 0.0004980633102115078,
|
| 3092 |
+
"loss": 0.3521,
|
| 3093 |
+
"step": 21800
|
| 3094 |
+
},
|
| 3095 |
+
{
|
| 3096 |
+
"epoch": 1.2423243120309302,
|
| 3097 |
+
"grad_norm": 0.11016605794429779,
|
| 3098 |
+
"learning_rate": 0.0004980588682624516,
|
| 3099 |
+
"loss": 0.3519,
|
| 3100 |
+
"step": 21850
|
| 3101 |
+
},
|
| 3102 |
+
{
|
| 3103 |
+
"epoch": 1.245167159426882,
|
| 3104 |
+
"grad_norm": 0.11307205259799957,
|
| 3105 |
+
"learning_rate": 0.0004980544263133954,
|
| 3106 |
+
"loss": 0.3545,
|
| 3107 |
+
"step": 21900
|
| 3108 |
+
},
|
| 3109 |
+
{
|
| 3110 |
+
"epoch": 1.2480100068228337,
|
| 3111 |
+
"grad_norm": 0.09647481143474579,
|
| 3112 |
+
"learning_rate": 0.0004980499843643394,
|
| 3113 |
+
"loss": 0.3497,
|
| 3114 |
+
"step": 21950
|
| 3115 |
+
},
|
| 3116 |
+
{
|
| 3117 |
+
"epoch": 1.2508528542187856,
|
| 3118 |
+
"grad_norm": 0.11781589686870575,
|
| 3119 |
+
"learning_rate": 0.0004980455424152832,
|
| 3120 |
+
"loss": 0.3527,
|
| 3121 |
+
"step": 22000
|
| 3122 |
+
},
|
| 3123 |
+
{
|
| 3124 |
+
"epoch": 1.2536957016147374,
|
| 3125 |
+
"grad_norm": 0.09155919402837753,
|
| 3126 |
+
"learning_rate": 0.000498041100466227,
|
| 3127 |
+
"loss": 0.3541,
|
| 3128 |
+
"step": 22050
|
| 3129 |
+
},
|
| 3130 |
+
{
|
| 3131 |
+
"epoch": 1.256538549010689,
|
| 3132 |
+
"grad_norm": 0.09770865738391876,
|
| 3133 |
+
"learning_rate": 0.0004980366585171708,
|
| 3134 |
+
"loss": 0.351,
|
| 3135 |
+
"step": 22100
|
| 3136 |
+
},
|
| 3137 |
+
{
|
| 3138 |
+
"epoch": 1.259381396406641,
|
| 3139 |
+
"grad_norm": 0.09057383239269257,
|
| 3140 |
+
"learning_rate": 0.0004980322165681146,
|
| 3141 |
+
"loss": 0.3526,
|
| 3142 |
+
"step": 22150
|
| 3143 |
+
},
|
| 3144 |
+
{
|
| 3145 |
+
"epoch": 1.2622242438025926,
|
| 3146 |
+
"grad_norm": 0.10171497613191605,
|
| 3147 |
+
"learning_rate": 0.0004980277746190584,
|
| 3148 |
+
"loss": 0.3516,
|
| 3149 |
+
"step": 22200
|
| 3150 |
+
},
|
| 3151 |
+
{
|
| 3152 |
+
"epoch": 1.2650670911985444,
|
| 3153 |
+
"grad_norm": 0.12109605222940445,
|
| 3154 |
+
"learning_rate": 0.0004980233326700022,
|
| 3155 |
+
"loss": 0.3479,
|
| 3156 |
+
"step": 22250
|
| 3157 |
+
},
|
| 3158 |
+
{
|
| 3159 |
+
"epoch": 1.2679099385944963,
|
| 3160 |
+
"grad_norm": 0.08494057506322861,
|
| 3161 |
+
"learning_rate": 0.000498018890720946,
|
| 3162 |
+
"loss": 0.3536,
|
| 3163 |
+
"step": 22300
|
| 3164 |
+
},
|
| 3165 |
+
{
|
| 3166 |
+
"epoch": 1.2707527859904482,
|
| 3167 |
+
"grad_norm": 0.10715505480766296,
|
| 3168 |
+
"learning_rate": 0.00049801444877189,
|
| 3169 |
+
"loss": 0.354,
|
| 3170 |
+
"step": 22350
|
| 3171 |
+
},
|
| 3172 |
+
{
|
| 3173 |
+
"epoch": 1.2735956333863998,
|
| 3174 |
+
"grad_norm": 0.09710002690553665,
|
| 3175 |
+
"learning_rate": 0.0004980100068228338,
|
| 3176 |
+
"loss": 0.3504,
|
| 3177 |
+
"step": 22400
|
| 3178 |
+
},
|
| 3179 |
+
{
|
| 3180 |
+
"epoch": 1.2764384807823517,
|
| 3181 |
+
"grad_norm": 0.10588357597589493,
|
| 3182 |
+
"learning_rate": 0.0004980055648737776,
|
| 3183 |
+
"loss": 0.3552,
|
| 3184 |
+
"step": 22450
|
| 3185 |
+
},
|
| 3186 |
+
{
|
| 3187 |
+
"epoch": 1.2792813281783033,
|
| 3188 |
+
"grad_norm": 0.09577326476573944,
|
| 3189 |
+
"learning_rate": 0.0004980011229247214,
|
| 3190 |
+
"loss": 0.3523,
|
| 3191 |
+
"step": 22500
|
| 3192 |
+
},
|
| 3193 |
+
{
|
| 3194 |
+
"epoch": 1.2821241755742552,
|
| 3195 |
+
"grad_norm": 0.0960511788725853,
|
| 3196 |
+
"learning_rate": 0.0004979966809756653,
|
| 3197 |
+
"loss": 0.3496,
|
| 3198 |
+
"step": 22550
|
| 3199 |
+
},
|
| 3200 |
+
{
|
| 3201 |
+
"epoch": 1.284967022970207,
|
| 3202 |
+
"grad_norm": 0.09112073481082916,
|
| 3203 |
+
"learning_rate": 0.0004979922390266091,
|
| 3204 |
+
"loss": 0.3516,
|
| 3205 |
+
"step": 22600
|
| 3206 |
+
},
|
| 3207 |
+
{
|
| 3208 |
+
"epoch": 1.2878098703661587,
|
| 3209 |
+
"grad_norm": 0.11254040151834488,
|
| 3210 |
+
"learning_rate": 0.0004979877970775529,
|
| 3211 |
+
"loss": 0.3508,
|
| 3212 |
+
"step": 22650
|
| 3213 |
+
},
|
| 3214 |
+
{
|
| 3215 |
+
"epoch": 1.2906527177621105,
|
| 3216 |
+
"grad_norm": 0.1305217444896698,
|
| 3217 |
+
"learning_rate": 0.0004979833551284967,
|
| 3218 |
+
"loss": 0.3484,
|
| 3219 |
+
"step": 22700
|
| 3220 |
+
},
|
| 3221 |
+
{
|
| 3222 |
+
"epoch": 1.2934955651580622,
|
| 3223 |
+
"grad_norm": 0.11914518475532532,
|
| 3224 |
+
"learning_rate": 0.0004979789131794405,
|
| 3225 |
+
"loss": 0.3492,
|
| 3226 |
+
"step": 22750
|
| 3227 |
+
},
|
| 3228 |
+
{
|
| 3229 |
+
"epoch": 1.296338412554014,
|
| 3230 |
+
"grad_norm": 0.10428331047296524,
|
| 3231 |
+
"learning_rate": 0.0004979744712303843,
|
| 3232 |
+
"loss": 0.3516,
|
| 3233 |
+
"step": 22800
|
| 3234 |
+
},
|
| 3235 |
+
{
|
| 3236 |
+
"epoch": 1.299181259949966,
|
| 3237 |
+
"grad_norm": 0.10348132997751236,
|
| 3238 |
+
"learning_rate": 0.0004979700292813282,
|
| 3239 |
+
"loss": 0.3497,
|
| 3240 |
+
"step": 22850
|
| 3241 |
+
},
|
| 3242 |
+
{
|
| 3243 |
+
"epoch": 1.3020241073459178,
|
| 3244 |
+
"grad_norm": 0.08855703473091125,
|
| 3245 |
+
"learning_rate": 0.0004979655873322721,
|
| 3246 |
+
"loss": 0.3516,
|
| 3247 |
+
"step": 22900
|
| 3248 |
+
},
|
| 3249 |
+
{
|
| 3250 |
+
"epoch": 1.3048669547418694,
|
| 3251 |
+
"grad_norm": 0.11277921497821808,
|
| 3252 |
+
"learning_rate": 0.0004979611453832159,
|
| 3253 |
+
"loss": 0.3473,
|
| 3254 |
+
"step": 22950
|
| 3255 |
+
},
|
| 3256 |
+
{
|
| 3257 |
+
"epoch": 1.3077098021378213,
|
| 3258 |
+
"grad_norm": 0.092954620718956,
|
| 3259 |
+
"learning_rate": 0.0004979567034341597,
|
| 3260 |
+
"loss": 0.3483,
|
| 3261 |
+
"step": 23000
|
| 3262 |
+
},
|
| 3263 |
+
{
|
| 3264 |
+
"epoch": 1.310552649533773,
|
| 3265 |
+
"grad_norm": 0.11179167777299881,
|
| 3266 |
+
"learning_rate": 0.0004979522614851035,
|
| 3267 |
+
"loss": 0.3512,
|
| 3268 |
+
"step": 23050
|
| 3269 |
+
},
|
| 3270 |
+
{
|
| 3271 |
+
"epoch": 1.3133954969297248,
|
| 3272 |
+
"grad_norm": 0.09125496447086334,
|
| 3273 |
+
"learning_rate": 0.0004979478195360473,
|
| 3274 |
+
"loss": 0.3508,
|
| 3275 |
+
"step": 23100
|
| 3276 |
+
},
|
| 3277 |
+
{
|
| 3278 |
+
"epoch": 1.3162383443256767,
|
| 3279 |
+
"grad_norm": 0.0916043147444725,
|
| 3280 |
+
"learning_rate": 0.0004979433775869911,
|
| 3281 |
+
"loss": 0.3523,
|
| 3282 |
+
"step": 23150
|
| 3283 |
+
},
|
| 3284 |
+
{
|
| 3285 |
+
"epoch": 1.3190811917216285,
|
| 3286 |
+
"grad_norm": 0.09685220569372177,
|
| 3287 |
+
"learning_rate": 0.0004979389356379349,
|
| 3288 |
+
"loss": 0.3546,
|
| 3289 |
+
"step": 23200
|
| 3290 |
+
},
|
| 3291 |
+
{
|
| 3292 |
+
"epoch": 1.3219240391175802,
|
| 3293 |
+
"grad_norm": 0.10811689496040344,
|
| 3294 |
+
"learning_rate": 0.0004979344936888787,
|
| 3295 |
+
"loss": 0.3498,
|
| 3296 |
+
"step": 23250
|
| 3297 |
+
},
|
| 3298 |
+
{
|
| 3299 |
+
"epoch": 1.324766886513532,
|
| 3300 |
+
"grad_norm": 0.08741540461778641,
|
| 3301 |
+
"learning_rate": 0.0004979300517398227,
|
| 3302 |
+
"loss": 0.3493,
|
| 3303 |
+
"step": 23300
|
| 3304 |
+
},
|
| 3305 |
+
{
|
| 3306 |
+
"epoch": 1.3276097339094837,
|
| 3307 |
+
"grad_norm": 0.08877366036176682,
|
| 3308 |
+
"learning_rate": 0.0004979256097907665,
|
| 3309 |
+
"loss": 0.3527,
|
| 3310 |
+
"step": 23350
|
| 3311 |
+
},
|
| 3312 |
+
{
|
| 3313 |
+
"epoch": 1.3304525813054355,
|
| 3314 |
+
"grad_norm": 0.1235891655087471,
|
| 3315 |
+
"learning_rate": 0.0004979211678417103,
|
| 3316 |
+
"loss": 0.3525,
|
| 3317 |
+
"step": 23400
|
| 3318 |
+
},
|
| 3319 |
+
{
|
| 3320 |
+
"epoch": 1.3332954287013874,
|
| 3321 |
+
"grad_norm": 0.0945284515619278,
|
| 3322 |
+
"learning_rate": 0.0004979167258926541,
|
| 3323 |
+
"loss": 0.354,
|
| 3324 |
+
"step": 23450
|
| 3325 |
+
},
|
| 3326 |
+
{
|
| 3327 |
+
"epoch": 1.336138276097339,
|
| 3328 |
+
"grad_norm": 0.08477913588285446,
|
| 3329 |
+
"learning_rate": 0.0004979122839435979,
|
| 3330 |
+
"loss": 0.3515,
|
| 3331 |
+
"step": 23500
|
| 3332 |
+
},
|
| 3333 |
+
{
|
| 3334 |
+
"epoch": 1.338981123493291,
|
| 3335 |
+
"grad_norm": 0.09075385332107544,
|
| 3336 |
+
"learning_rate": 0.0004979078419945417,
|
| 3337 |
+
"loss": 0.3515,
|
| 3338 |
+
"step": 23550
|
| 3339 |
+
},
|
| 3340 |
+
{
|
| 3341 |
+
"epoch": 1.3418239708892425,
|
| 3342 |
+
"grad_norm": 0.08231678605079651,
|
| 3343 |
+
"learning_rate": 0.0004979034000454855,
|
| 3344 |
+
"loss": 0.3506,
|
| 3345 |
+
"step": 23600
|
| 3346 |
+
},
|
| 3347 |
+
{
|
| 3348 |
+
"epoch": 1.3446668182851944,
|
| 3349 |
+
"grad_norm": 0.08512122184038162,
|
| 3350 |
+
"learning_rate": 0.0004978989580964293,
|
| 3351 |
+
"loss": 0.3506,
|
| 3352 |
+
"step": 23650
|
| 3353 |
+
},
|
| 3354 |
+
{
|
| 3355 |
+
"epoch": 1.3475096656811463,
|
| 3356 |
+
"grad_norm": 0.09195214509963989,
|
| 3357 |
+
"learning_rate": 0.0004978945161473732,
|
| 3358 |
+
"loss": 0.3493,
|
| 3359 |
+
"step": 23700
|
| 3360 |
+
},
|
| 3361 |
+
{
|
| 3362 |
+
"epoch": 1.3503525130770981,
|
| 3363 |
+
"grad_norm": 0.09307179600000381,
|
| 3364 |
+
"learning_rate": 0.000497890074198317,
|
| 3365 |
+
"loss": 0.3466,
|
| 3366 |
+
"step": 23750
|
| 3367 |
+
},
|
| 3368 |
+
{
|
| 3369 |
+
"epoch": 1.3531953604730498,
|
| 3370 |
+
"grad_norm": 0.08473914861679077,
|
| 3371 |
+
"learning_rate": 0.0004978856322492609,
|
| 3372 |
+
"loss": 0.3512,
|
| 3373 |
+
"step": 23800
|
| 3374 |
+
},
|
| 3375 |
+
{
|
| 3376 |
+
"epoch": 1.3560382078690016,
|
| 3377 |
+
"grad_norm": 0.09676692634820938,
|
| 3378 |
+
"learning_rate": 0.0004978811903002047,
|
| 3379 |
+
"loss": 0.3495,
|
| 3380 |
+
"step": 23850
|
| 3381 |
+
},
|
| 3382 |
+
{
|
| 3383 |
+
"epoch": 1.3588810552649533,
|
| 3384 |
+
"grad_norm": 0.08961619436740875,
|
| 3385 |
+
"learning_rate": 0.0004978767483511486,
|
| 3386 |
+
"loss": 0.3493,
|
| 3387 |
+
"step": 23900
|
| 3388 |
+
},
|
| 3389 |
+
{
|
| 3390 |
+
"epoch": 1.3617239026609051,
|
| 3391 |
+
"grad_norm": 0.10256984084844589,
|
| 3392 |
+
"learning_rate": 0.0004978723064020924,
|
| 3393 |
+
"loss": 0.3519,
|
| 3394 |
+
"step": 23950
|
| 3395 |
+
},
|
| 3396 |
+
{
|
| 3397 |
+
"epoch": 1.364566750056857,
|
| 3398 |
+
"grad_norm": 0.09426955133676529,
|
| 3399 |
+
"learning_rate": 0.0004978678644530362,
|
| 3400 |
+
"loss": 0.3496,
|
| 3401 |
+
"step": 24000
|
| 3402 |
+
},
|
| 3403 |
+
{
|
| 3404 |
+
"epoch": 1.3674095974528087,
|
| 3405 |
+
"grad_norm": 0.09407513588666916,
|
| 3406 |
+
"learning_rate": 0.00049786342250398,
|
| 3407 |
+
"loss": 0.35,
|
| 3408 |
+
"step": 24050
|
| 3409 |
+
},
|
| 3410 |
+
{
|
| 3411 |
+
"epoch": 1.3702524448487605,
|
| 3412 |
+
"grad_norm": 0.11077912896871567,
|
| 3413 |
+
"learning_rate": 0.0004978589805549238,
|
| 3414 |
+
"loss": 0.3499,
|
| 3415 |
+
"step": 24100
|
| 3416 |
+
},
|
| 3417 |
+
{
|
| 3418 |
+
"epoch": 1.3730952922447124,
|
| 3419 |
+
"grad_norm": 0.09664590656757355,
|
| 3420 |
+
"learning_rate": 0.0004978545386058676,
|
| 3421 |
+
"loss": 0.3509,
|
| 3422 |
+
"step": 24150
|
| 3423 |
+
},
|
| 3424 |
+
{
|
| 3425 |
+
"epoch": 1.375938139640664,
|
| 3426 |
+
"grad_norm": 0.08676467835903168,
|
| 3427 |
+
"learning_rate": 0.0004978500966568114,
|
| 3428 |
+
"loss": 0.3498,
|
| 3429 |
+
"step": 24200
|
| 3430 |
+
},
|
| 3431 |
+
{
|
| 3432 |
+
"epoch": 1.378780987036616,
|
| 3433 |
+
"grad_norm": 0.07996726781129837,
|
| 3434 |
+
"learning_rate": 0.0004978456547077553,
|
| 3435 |
+
"loss": 0.3525,
|
| 3436 |
+
"step": 24250
|
| 3437 |
+
},
|
| 3438 |
+
{
|
| 3439 |
+
"epoch": 1.3816238344325678,
|
| 3440 |
+
"grad_norm": 0.1071229949593544,
|
| 3441 |
+
"learning_rate": 0.0004978412127586992,
|
| 3442 |
+
"loss": 0.3529,
|
| 3443 |
+
"step": 24300
|
| 3444 |
+
},
|
| 3445 |
+
{
|
| 3446 |
+
"epoch": 1.3844666818285194,
|
| 3447 |
+
"grad_norm": 0.09521368145942688,
|
| 3448 |
+
"learning_rate": 0.000497836770809643,
|
| 3449 |
+
"loss": 0.3501,
|
| 3450 |
+
"step": 24350
|
| 3451 |
+
},
|
| 3452 |
+
{
|
| 3453 |
+
"epoch": 1.3873095292244713,
|
| 3454 |
+
"grad_norm": 0.10842622071504593,
|
| 3455 |
+
"learning_rate": 0.0004978323288605868,
|
| 3456 |
+
"loss": 0.3469,
|
| 3457 |
+
"step": 24400
|
| 3458 |
+
},
|
| 3459 |
+
{
|
| 3460 |
+
"epoch": 1.390152376620423,
|
| 3461 |
+
"grad_norm": 0.08254586160182953,
|
| 3462 |
+
"learning_rate": 0.0004978278869115306,
|
| 3463 |
+
"loss": 0.3481,
|
| 3464 |
+
"step": 24450
|
| 3465 |
+
},
|
| 3466 |
+
{
|
| 3467 |
+
"epoch": 1.3929952240163748,
|
| 3468 |
+
"grad_norm": 0.122976154088974,
|
| 3469 |
+
"learning_rate": 0.0004978234449624744,
|
| 3470 |
+
"loss": 0.3519,
|
| 3471 |
+
"step": 24500
|
| 3472 |
+
},
|
| 3473 |
+
{
|
| 3474 |
+
"epoch": 1.3958380714123266,
|
| 3475 |
+
"grad_norm": 0.10202399641275406,
|
| 3476 |
+
"learning_rate": 0.0004978190030134182,
|
| 3477 |
+
"loss": 0.3481,
|
| 3478 |
+
"step": 24550
|
| 3479 |
+
},
|
| 3480 |
+
{
|
| 3481 |
+
"epoch": 1.3986809188082785,
|
| 3482 |
+
"grad_norm": 0.09278547018766403,
|
| 3483 |
+
"learning_rate": 0.000497814561064362,
|
| 3484 |
+
"loss": 0.3477,
|
| 3485 |
+
"step": 24600
|
| 3486 |
+
},
|
| 3487 |
+
{
|
| 3488 |
+
"epoch": 1.4015237662042301,
|
| 3489 |
+
"grad_norm": 0.09204497933387756,
|
| 3490 |
+
"learning_rate": 0.0004978101191153058,
|
| 3491 |
+
"loss": 0.3487,
|
| 3492 |
+
"step": 24650
|
| 3493 |
+
},
|
| 3494 |
+
{
|
| 3495 |
+
"epoch": 1.404366613600182,
|
| 3496 |
+
"grad_norm": 0.09469152987003326,
|
| 3497 |
+
"learning_rate": 0.0004978056771662498,
|
| 3498 |
+
"loss": 0.352,
|
| 3499 |
+
"step": 24700
|
| 3500 |
+
},
|
| 3501 |
+
{
|
| 3502 |
+
"epoch": 1.4072094609961336,
|
| 3503 |
+
"grad_norm": 0.09524402767419815,
|
| 3504 |
+
"learning_rate": 0.0004978012352171936,
|
| 3505 |
+
"loss": 0.3502,
|
| 3506 |
+
"step": 24750
|
| 3507 |
+
},
|
| 3508 |
+
{
|
| 3509 |
+
"epoch": 1.4100523083920855,
|
| 3510 |
+
"grad_norm": 0.09983129799365997,
|
| 3511 |
+
"learning_rate": 0.0004977967932681374,
|
| 3512 |
+
"loss": 0.3491,
|
| 3513 |
+
"step": 24800
|
| 3514 |
+
},
|
| 3515 |
+
{
|
| 3516 |
+
"epoch": 1.4128951557880374,
|
| 3517 |
+
"grad_norm": 0.13477516174316406,
|
| 3518 |
+
"learning_rate": 0.0004977923513190812,
|
| 3519 |
+
"loss": 0.3505,
|
| 3520 |
+
"step": 24850
|
| 3521 |
+
},
|
| 3522 |
+
{
|
| 3523 |
+
"epoch": 1.415738003183989,
|
| 3524 |
+
"grad_norm": 0.09205208718776703,
|
| 3525 |
+
"learning_rate": 0.000497787909370025,
|
| 3526 |
+
"loss": 0.3505,
|
| 3527 |
+
"step": 24900
|
| 3528 |
+
},
|
| 3529 |
+
{
|
| 3530 |
+
"epoch": 1.4185808505799409,
|
| 3531 |
+
"grad_norm": 0.08766143023967743,
|
| 3532 |
+
"learning_rate": 0.0004977834674209688,
|
| 3533 |
+
"loss": 0.3508,
|
| 3534 |
+
"step": 24950
|
| 3535 |
+
},
|
| 3536 |
+
{
|
| 3537 |
+
"epoch": 1.4214236979758925,
|
| 3538 |
+
"grad_norm": 0.11106764525175095,
|
| 3539 |
+
"learning_rate": 0.0004977790254719127,
|
| 3540 |
+
"loss": 0.3501,
|
| 3541 |
+
"step": 25000
|
| 3542 |
+
},
|
| 3543 |
+
{
|
| 3544 |
+
"epoch": 1.4214236979758925,
|
| 3545 |
+
"eval_loss": 0.3424564003944397,
|
| 3546 |
+
"eval_runtime": 577.5935,
|
| 3547 |
+
"eval_samples_per_second": 228.379,
|
| 3548 |
+
"eval_steps_per_second": 28.548,
|
| 3549 |
+
"step": 25000
|
| 3550 |
+
}
|
| 3551 |
+
],
|
| 3552 |
+
"logging_steps": 50,
|
| 3553 |
+
"max_steps": 5628160,
|
| 3554 |
+
"num_input_tokens_seen": 0,
|
| 3555 |
+
"num_train_epochs": 320,
|
| 3556 |
+
"save_steps": 5000,
|
| 3557 |
+
"stateful_callbacks": {
|
| 3558 |
+
"EarlyStoppingCallback": {
|
| 3559 |
+
"args": {
|
| 3560 |
+
"early_stopping_patience": 3,
|
| 3561 |
+
"early_stopping_threshold": 0.0
|
| 3562 |
+
},
|
| 3563 |
+
"attributes": {
|
| 3564 |
+
"early_stopping_patience_counter": 0
|
| 3565 |
+
}
|
| 3566 |
+
},
|
| 3567 |
+
"TrainerControl": {
|
| 3568 |
+
"args": {
|
| 3569 |
+
"should_epoch_stop": false,
|
| 3570 |
+
"should_evaluate": false,
|
| 3571 |
+
"should_log": false,
|
| 3572 |
+
"should_save": true,
|
| 3573 |
+
"should_training_stop": false
|
| 3574 |
+
},
|
| 3575 |
+
"attributes": {}
|
| 3576 |
+
}
|
| 3577 |
+
},
|
| 3578 |
+
"total_flos": 9.134362268821094e+17,
|
| 3579 |
+
"train_batch_size": 120,
|
| 3580 |
+
"trial_name": null,
|
| 3581 |
+
"trial_params": null
|
| 3582 |
+
}
|
checkpoint-25000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:257309b599ffa995a9df1033ca99828b19066f75888fa49b64b10581dca97bb8
|
| 3 |
+
size 5304
|