Upload folder using huggingface_hub

.gitattributes

@@ -106,3 +106,4 @@ checkpoints-v1.0e-discrete-condition/checkpoint-15360/eval_state.json filter=lfs
 checkpoints-v1.0e-discrete-condition/checkpoint-21651/eval_state.json filter=lfs diff=lfs merge=lfs -text
 checkpoints-v1.0f-discrete-condition/checkpoint-15360/eval_state.json filter=lfs diff=lfs merge=lfs -text
 checkpoints-v1.0f-discrete-condition/checkpoint-21651/eval_state.json filter=lfs diff=lfs merge=lfs -text
+checkpoints-v2.0a-discrete-condition/checkpoint-4096/eval_state.json filter=lfs diff=lfs merge=lfs -text

checkpoints-v2.0a-discrete-condition/checkpoint-4096/eval_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:845d2e71903e48abd1666670aa6d6398235be8ff153f75093e1b45e4ed7c8600
+size 46081776

checkpoints-v2.0a-discrete-condition/checkpoint-4096/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a3c2becf5813595af681ff92d079acfe70c654158ec604cdf784c18d531dde
+size 15210032

checkpoints-v2.0a-discrete-condition/checkpoint-4096/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f49965c5d19f553ddded7715f5bbb968308301248d4c1f01b6f30f1c63c93fdf
+size 13675339

checkpoints-v2.0a-discrete-condition/checkpoint-4096/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f04c8bb33e8e4266c246f4329da29d6f1414224fc8a213228730fe476d54b784
+size 14645

checkpoints-v2.0a-discrete-condition/checkpoint-4096/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90078bef0ff08e77712ec862bc2a11b4989d3477480b20822129904ef078a3a3
+size 1383

checkpoints-v2.0a-discrete-condition/checkpoint-4096/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a96292f7ed2848651a48ddc440ca758838d3d5eb28c3ec2cae1ccbbb1dc4b1c
+size 1465

checkpoints-v2.0a-discrete-condition/checkpoint-4096/trainer_state.json

@@ -0,0 +1,238 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.18918294766985358,
+  "eval_steps": 1024,
+  "global_step": 4096,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011823934229365849,
+      "grad_norm": 0.3142397999763489,
+      "learning_rate": 0.000498046875,
+      "loss": 2.5664353370666504,
+      "step": 256
+    },
+    {
+      "epoch": 0.023647868458731697,
+      "grad_norm": 0.7134925127029419,
+      "learning_rate": 0.000998046875,
+      "loss": 1.9098931550979614,
+      "step": 512
+    },
+    {
+      "epoch": 0.03547180268809755,
+      "grad_norm": 1.1968424320220947,
+      "learning_rate": 0.000999640996023194,
+      "loss": 1.6245745420455933,
+      "step": 768
+    },
+    {
+      "epoch": 0.047295736917463395,
+      "grad_norm": 0.9976363182067871,
+      "learning_rate": 0.0009985588674043958,
+      "loss": 1.4784010648727417,
+      "step": 1024
+    },
+    {
+      "epoch": 0.047295736917463395,
+      "eval_bleu": 0.0011133109477885134,
+      "eval_cos0_loss": 0.35662247560339977,
+      "eval_cos_loss": 0.3775373704765485,
+      "eval_loss": 1.4111966779242913,
+      "eval_mse0_loss": 1.4443081268981166,
+      "eval_mse_loss": 1.3780852248679558,
+      "step": 1024
+    },
+    {
+      "epoch": 0.047295736917463395,
+      "eval_bleu": 0.0011133109477885134,
+      "eval_cos0_loss": 0.35662247560339977,
+      "eval_cos_loss": 0.3775373704765485,
+      "eval_loss": 1.4111966779242913,
+      "eval_mse0_loss": 1.4443081268981166,
+      "eval_mse_loss": 1.3780852248679558,
+      "eval_runtime": 559.8994,
+      "eval_samples_per_second": 49.996,
+      "eval_steps_per_second": 0.782,
+      "step": 1024
+    },
+    {
+      "epoch": 0.05911967114682925,
+      "grad_norm": 0.9691009521484375,
+      "learning_rate": 0.0009967551747861387,
+      "loss": 1.3725448846817017,
+      "step": 1280
+    },
+    {
+      "epoch": 0.0709436053761951,
+      "grad_norm": 1.2567791938781738,
+      "learning_rate": 0.000994232528651847,
+      "loss": 1.3024182319641113,
+      "step": 1536
+    },
+    {
+      "epoch": 0.08276753960556095,
+      "grad_norm": 0.9418615698814392,
+      "learning_rate": 0.0009909945800260092,
+      "loss": 1.2219008207321167,
+      "step": 1792
+    },
+    {
+      "epoch": 0.09459147383492679,
+      "grad_norm": 1.0366237163543701,
+      "learning_rate": 0.0009870460151900522,
+      "loss": 1.166050672531128,
+      "step": 2048
+    },
+    {
+      "epoch": 0.09459147383492679,
+      "eval_bleu": 0.007989488547135068,
+      "eval_cos0_loss": 0.2812547723860501,
+      "eval_cos_loss": 0.33213963383408984,
+      "eval_loss": 1.1427442649183752,
+      "eval_mse0_loss": 1.098496745166169,
+      "eval_mse_loss": 1.1869917854870835,
+      "step": 2048
+    },
+    {
+      "epoch": 0.09459147383492679,
+      "eval_bleu": 0.007989488547135068,
+      "eval_cos0_loss": 0.2812547723860501,
+      "eval_cos_loss": 0.33213963383408984,
+      "eval_loss": 1.1427442649183752,
+      "eval_mse0_loss": 1.098496745166169,
+      "eval_mse_loss": 1.1869917854870835,
+      "eval_runtime": 556.0835,
+      "eval_samples_per_second": 50.34,
+      "eval_steps_per_second": 0.788,
+      "step": 2048
+    },
+    {
+      "epoch": 0.10641540806429264,
+      "grad_norm": 1.2856756448745728,
+      "learning_rate": 0.0009823925488998885,
+      "loss": 1.1258903741836548,
+      "step": 2304
+    },
+    {
+      "epoch": 0.1182393422936585,
+      "grad_norm": 1.1996031999588013,
+      "learning_rate": 0.0009770409161149525,
+      "loss": 1.0752795934677124,
+      "step": 2560
+    },
+    {
+      "epoch": 0.13006327652302435,
+      "grad_norm": 1.0043145418167114,
+      "learning_rate": 0.0009709988622506973,
+      "loss": 1.034059762954712,
+      "step": 2816
+    },
+    {
+      "epoch": 0.1418872107523902,
+      "grad_norm": 1.327103853225708,
+      "learning_rate": 0.000964275131968659,
+      "loss": 0.9963141083717346,
+      "step": 3072
+    },
+    {
+      "epoch": 0.1418872107523902,
+      "eval_bleu": 0.024982546797062154,
+      "eval_cos0_loss": 0.23017472596881597,
+      "eval_cos_loss": 0.3040819166729984,
+      "eval_loss": 0.9821336078861532,
+      "eval_mse0_loss": 0.8859744953782591,
+      "eval_mse_loss": 1.0782927214827167,
+      "step": 3072
+    },
+    {
+      "epoch": 0.1418872107523902,
+      "eval_bleu": 0.024982546797062154,
+      "eval_cos0_loss": 0.23017472596881597,
+      "eval_cos_loss": 0.3040819166729984,
+      "eval_loss": 0.9821336078861532,
+      "eval_mse0_loss": 0.8859744953782591,
+      "eval_mse_loss": 1.0782927214827167,
+      "eval_runtime": 554.8091,
+      "eval_samples_per_second": 50.455,
+      "eval_steps_per_second": 0.789,
+      "step": 3072
+    },
+    {
+      "epoch": 0.15371114498175603,
+      "grad_norm": 1.20012366771698,
+      "learning_rate": 0.0009568794565203123,
+      "loss": 0.9632707238197327,
+      "step": 3328
+    },
+    {
+      "epoch": 0.1655350792111219,
+      "grad_norm": 1.1331790685653687,
+      "learning_rate": 0.0009488225396630347,
+      "loss": 0.9331204891204834,
+      "step": 3584
+    },
+    {
+      "epoch": 0.17735901344048774,
+      "grad_norm": 1.2750242948532104,
+      "learning_rate": 0.0009401160421685646,
+      "loss": 0.9070082306861877,
+      "step": 3840
+    },
+    {
+      "epoch": 0.18918294766985358,
+      "grad_norm": 1.2876979112625122,
+      "learning_rate": 0.0009307725649463714,
+      "loss": 0.885317325592041,
+      "step": 4096
+    },
+    {
+      "epoch": 0.18918294766985358,
+      "eval_bleu": 0.06063932312714804,
+      "eval_cos0_loss": 0.20171181510572564,
+      "eval_cos_loss": 0.28187595001638754,
+      "eval_loss": 0.8752339045478873,
+      "eval_mse0_loss": 0.7643582605880145,
+      "eval_mse_loss": 0.9861095474190908,
+      "step": 4096
+    },
+    {
+      "epoch": 0.18918294766985358,
+      "eval_bleu": 0.06063932312714804,
+      "eval_cos0_loss": 0.20171181510572564,
+      "eval_cos_loss": 0.28187595001638754,
+      "eval_loss": 0.8752339045478873,
+      "eval_mse0_loss": 0.7643582605880145,
+      "eval_mse_loss": 0.9861095474190908,
+      "eval_runtime": 557.2308,
+      "eval_samples_per_second": 50.236,
+      "eval_steps_per_second": 0.786,
+      "step": 4096
+    }
+  ],
+  "logging_steps": 256,
+  "max_steps": 21651,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1024,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints-v2.0a-discrete-condition/checkpoint-4096/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f63a8a711fb280c6320e95476c532b75c862f31d6a218a0d05079e32411a5ae1
+size 5201