Hugging Face's logo

Subject-Emu-5259
/
NeuralAI

Text Generation
PEFT
Safetensors
English
llama
lora
conversational
smollm2
dpo
fine-tuned
Model card Files
xet
 Community
Subject-Emu-5259 commited on
Commit
2e24fb9
·
verified ·
1 Parent(s): 39150cc

Sync LoRA adapter: trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +100 -0
trainer_state.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 69,
3
+ "best_metric": 0.7231942415237427,
4
+ "best_model_checkpoint": "/home/workspace/Projects/NeuralAI/checkpoints/v2_model/checkpoint-69",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 69,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.44077134986225897,
14
+ "grad_norm": 0.8227247595787048,
15
+ "learning_rate": 3.6e-05,
16
+ "loss": 2.102004623413086,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.8815426997245179,
21
+ "grad_norm": 0.770205557346344,
22
+ "learning_rate": 7.6e-05,
23
+ "loss": 1.942721176147461,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 1.0,
28
+ "eval_loss": 1.6713197231292725,
29
+ "eval_runtime": 23.3461,
30
+ "eval_samples_per_second": 1.756,
31
+ "eval_steps_per_second": 1.756,
32
+ "step": 23
33
+ },
34
+ {
35
+ "epoch": 1.3085399449035813,
36
+ "grad_norm": 0.45185327529907227,
37
+ "learning_rate": 0.000116,
38
+ "loss": 1.6010663986206055,
39
+ "step": 30
40
+ },
41
+ {
42
+ "epoch": 1.7493112947658402,
43
+ "grad_norm": 0.3300871253013611,
44
+ "learning_rate": 0.00015600000000000002,
45
+ "loss": 1.1151976585388184,
46
+ "step": 40
47
+ },
48
+ {
49
+ "epoch": 2.0,
50
+ "eval_loss": 0.896889865398407,
51
+ "eval_runtime": 17.5969,
52
+ "eval_samples_per_second": 2.33,
53
+ "eval_steps_per_second": 2.33,
54
+ "step": 46
55
+ },
56
+ {
57
+ "epoch": 2.1763085399449036,
58
+ "grad_norm": 0.31101763248443604,
59
+ "learning_rate": 0.000196,
60
+ "loss": 0.9162005424499512,
61
+ "step": 50
62
+ },
63
+ {
64
+ "epoch": 2.6170798898071626,
65
+ "grad_norm": 0.32379862666130066,
66
+ "learning_rate": 0.00010825793454723325,
67
+ "loss": 0.7014970779418945,
68
+ "step": 60
69
+ },
70
+ {
71
+ "epoch": 3.0,
72
+ "eval_loss": 0.7231942415237427,
73
+ "eval_runtime": 17.6154,
74
+ "eval_samples_per_second": 2.328,
75
+ "eval_steps_per_second": 2.328,
76
+ "step": 69
77
+ }
78
+ ],
79
+ "logging_steps": 10,
80
+ "max_steps": 69,
81
+ "num_input_tokens_seen": 0,
82
+ "num_train_epochs": 3,
83
+ "save_steps": 500,
84
+ "stateful_callbacks": {
85
+ "TrainerControl": {
86
+ "args": {
87
+ "should_epoch_stop": false,
88
+ "should_evaluate": false,
89
+ "should_log": false,
90
+ "should_save": true,
91
+ "should_training_stop": true
92
+ },
93
+ "attributes": {}
94
+ }
95
+ },
96
+ "total_flos": 134948060628480.0,
97
+ "train_batch_size": 1,
98
+ "trial_name": null,
99
+ "trial_params": null
100
+ }