dzungpham commited on Apr 17

Commit

7343966

verified ·

1 Parent(s): 26476e0

upload best checkpoints 100 graphcodebert mixcode fft

Browse files

This view is limited to 50 files because it contains too many changes. See raw diff

Files changed (50) hide show

graphcodebert-mixcode-fft/checkpoint-100/config.json +29 -0
graphcodebert-mixcode-fft/checkpoint-100/merges.txt +0 -0
graphcodebert-mixcode-fft/checkpoint-100/model.safetensors +3 -0
graphcodebert-mixcode-fft/checkpoint-100/optimizer.pt +3 -0
graphcodebert-mixcode-fft/checkpoint-100/rng_state.pth +3 -0
graphcodebert-mixcode-fft/checkpoint-100/scaler.pt +3 -0
graphcodebert-mixcode-fft/checkpoint-100/scheduler.pt +3 -0
graphcodebert-mixcode-fft/checkpoint-100/special_tokens_map.json +51 -0
graphcodebert-mixcode-fft/checkpoint-100/tokenizer.json +0 -0
graphcodebert-mixcode-fft/checkpoint-100/tokenizer_config.json +58 -0
graphcodebert-mixcode-fft/checkpoint-100/trainer_state.json +113 -0
graphcodebert-mixcode-fft/checkpoint-100/training_args.bin +3 -0
graphcodebert-mixcode-fft/checkpoint-100/vocab.json +0 -0
graphcodebert-mixcode-fft/checkpoint-200/config.json +29 -0
graphcodebert-mixcode-fft/checkpoint-200/merges.txt +0 -0
graphcodebert-mixcode-fft/checkpoint-200/model.safetensors +3 -0
graphcodebert-mixcode-fft/checkpoint-200/optimizer.pt +3 -0
graphcodebert-mixcode-fft/checkpoint-200/rng_state.pth +3 -0
graphcodebert-mixcode-fft/checkpoint-200/scaler.pt +3 -0
graphcodebert-mixcode-fft/checkpoint-200/scheduler.pt +3 -0
graphcodebert-mixcode-fft/checkpoint-200/special_tokens_map.json +51 -0
graphcodebert-mixcode-fft/checkpoint-200/tokenizer.json +0 -0
graphcodebert-mixcode-fft/checkpoint-200/tokenizer_config.json +58 -0
graphcodebert-mixcode-fft/checkpoint-200/trainer_state.json +183 -0
graphcodebert-mixcode-fft/checkpoint-200/training_args.bin +3 -0
graphcodebert-mixcode-fft/checkpoint-200/vocab.json +0 -0
graphcodebert-mixcode-fft/checkpoint-300/config.json +29 -0
graphcodebert-mixcode-fft/checkpoint-300/merges.txt +0 -0
graphcodebert-mixcode-fft/checkpoint-300/model.safetensors +3 -0
graphcodebert-mixcode-fft/checkpoint-300/optimizer.pt +3 -0
graphcodebert-mixcode-fft/checkpoint-300/rng_state.pth +3 -0
graphcodebert-mixcode-fft/checkpoint-300/scaler.pt +3 -0
graphcodebert-mixcode-fft/checkpoint-300/scheduler.pt +3 -0
graphcodebert-mixcode-fft/checkpoint-300/special_tokens_map.json +51 -0
graphcodebert-mixcode-fft/checkpoint-300/tokenizer.json +0 -0
graphcodebert-mixcode-fft/checkpoint-300/tokenizer_config.json +58 -0
graphcodebert-mixcode-fft/checkpoint-300/trainer_state.json +253 -0
graphcodebert-mixcode-fft/checkpoint-300/training_args.bin +3 -0
graphcodebert-mixcode-fft/checkpoint-300/vocab.json +0 -0
graphcodebert-mixcode-fft/checkpoint-400/config.json +29 -0
graphcodebert-mixcode-fft/checkpoint-400/merges.txt +0 -0
graphcodebert-mixcode-fft/checkpoint-400/model.safetensors +3 -0
graphcodebert-mixcode-fft/checkpoint-400/optimizer.pt +3 -0
graphcodebert-mixcode-fft/checkpoint-400/rng_state.pth +3 -0
graphcodebert-mixcode-fft/checkpoint-400/scaler.pt +3 -0
graphcodebert-mixcode-fft/checkpoint-400/scheduler.pt +3 -0
graphcodebert-mixcode-fft/checkpoint-400/special_tokens_map.json +51 -0
graphcodebert-mixcode-fft/checkpoint-400/tokenizer.json +0 -0
graphcodebert-mixcode-fft/checkpoint-400/tokenizer_config.json +58 -0
graphcodebert-mixcode-fft/checkpoint-400/trainer_state.json +323 -0

graphcodebert-mixcode-fft/checkpoint-100/config.json ADDED Viewed

	@@ -0,0 +1,29 @@

+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.56.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

graphcodebert-mixcode-fft/checkpoint-100/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

graphcodebert-mixcode-fft/checkpoint-100/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce9efb0838c3bb940be1057d74141678c8cc0e3a6a330ef621cf8aad644b455
+size 498612824

graphcodebert-mixcode-fft/checkpoint-100/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:78242f3b36c02c4ea7862a3f30665f7dabb9d0541c792048a92db69abafa08df
+size 4741923

graphcodebert-mixcode-fft/checkpoint-100/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b232f83566643a193c2dd2f6264f94bff1a7ec6bbe8ce3cd743b15c861fe154d
+size 14645

graphcodebert-mixcode-fft/checkpoint-100/scaler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c4393a84a3109995aa1202073b039b12062e3189ed89aa0b94ef0510ba843009
+size 1383

graphcodebert-mixcode-fft/checkpoint-100/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:73cb732442e2d829e594b5b61d500d80c02db855b5b504235793fe2f865f5954
+size 1465

graphcodebert-mixcode-fft/checkpoint-100/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

graphcodebert-mixcode-fft/checkpoint-100/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

graphcodebert-mixcode-fft/checkpoint-100/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

graphcodebert-mixcode-fft/checkpoint-100/trainer_state.json ADDED Viewed

	@@ -0,0 +1,113 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.012799180852425445,
+  "eval_steps": 1000,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0012799180852425445,
+      "grad_norm": 1.2002202272415161,
+      "learning_rate": 1.4404609475032012e-07,
+      "loss": 0.714,
+      "step": 10
+    },
+    {
+      "epoch": 0.002559836170485089,
+      "grad_norm": 1.0710716247558594,
+      "learning_rate": 3.040973111395647e-07,
+      "loss": 0.7181,
+      "step": 20
+    },
+    {
+      "epoch": 0.0038397542557276334,
+      "grad_norm": 1.0631524324417114,
+      "learning_rate": 4.641485275288093e-07,
+      "loss": 0.7114,
+      "step": 30
+    },
+    {
+      "epoch": 0.005119672340970178,
+      "grad_norm": 1.1470946073532104,
+      "learning_rate": 6.241997439180538e-07,
+      "loss": 0.7083,
+      "step": 40
+    },
+    {
+      "epoch": 0.006399590426212722,
+      "grad_norm": 1.1680080890655518,
+      "learning_rate": 7.842509603072984e-07,
+      "loss": 0.7109,
+      "step": 50
+    },
+    {
+      "epoch": 0.007679508511455267,
+      "grad_norm": 0.6832358241081238,
+      "learning_rate": 9.44302176696543e-07,
+      "loss": 0.7131,
+      "step": 60
+    },
+    {
+      "epoch": 0.008959426596697812,
+      "grad_norm": 1.8029249906539917,
+      "learning_rate": 1.1043533930857875e-06,
+      "loss": 0.7092,
+      "step": 70
+    },
+    {
+      "epoch": 0.010239344681940356,
+      "grad_norm": 1.795204758644104,
+      "learning_rate": 1.264404609475032e-06,
+      "loss": 0.7063,
+      "step": 80
+    },
+    {
+      "epoch": 0.011519262767182901,
+      "grad_norm": 1.2713547945022583,
+      "learning_rate": 1.4244558258642767e-06,
+      "loss": 0.7126,
+      "step": 90
+    },
+    {
+      "epoch": 0.012799180852425445,
+      "grad_norm": 1.2709708213806152,
+      "learning_rate": 1.5845070422535212e-06,
+      "loss": 0.7069,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 31252,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1683910754304000.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

graphcodebert-mixcode-fft/checkpoint-100/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:55e805564976941c69ed81dd4f57f02f704352ee18e811a5a0c0eac53999ccb7
+size 5841

graphcodebert-mixcode-fft/checkpoint-100/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

graphcodebert-mixcode-fft/checkpoint-200/config.json ADDED Viewed

	@@ -0,0 +1,29 @@

+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.56.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

graphcodebert-mixcode-fft/checkpoint-200/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

graphcodebert-mixcode-fft/checkpoint-200/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9c44ac861ac2b8fa337d7fb36dbec3be1474c43bf7e3cd7ab7daad107f775dc3
+size 498612824

graphcodebert-mixcode-fft/checkpoint-200/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8f717867bc2c783e925375ba468503dfe9d122ce9405c04cfa35dbce370d3459
+size 4741923

graphcodebert-mixcode-fft/checkpoint-200/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:75929b49feda2c26b98cb95caa4f592fcde58476e5e3fbab317258120c864ff5
+size 14645

graphcodebert-mixcode-fft/checkpoint-200/scaler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:124625e167eb28acbfc793cfcb3e8a08b32e7fea06501462bc9e420a5e1beb2a
+size 1383

graphcodebert-mixcode-fft/checkpoint-200/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cd38f8e3e508bdf1564c9d172c1f6108f72c5a5e2aab032c520bda4f2426d436
+size 1465

graphcodebert-mixcode-fft/checkpoint-200/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

graphcodebert-mixcode-fft/checkpoint-200/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

graphcodebert-mixcode-fft/checkpoint-200/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

graphcodebert-mixcode-fft/checkpoint-200/trainer_state.json ADDED Viewed

	@@ -0,0 +1,183 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.02559836170485089,
+  "eval_steps": 1000,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0012799180852425445,
+      "grad_norm": 1.2002202272415161,
+      "learning_rate": 1.4404609475032012e-07,
+      "loss": 0.714,
+      "step": 10
+    },
+    {
+      "epoch": 0.002559836170485089,
+      "grad_norm": 1.0710716247558594,
+      "learning_rate": 3.040973111395647e-07,
+      "loss": 0.7181,
+      "step": 20
+    },
+    {
+      "epoch": 0.0038397542557276334,
+      "grad_norm": 1.0631524324417114,
+      "learning_rate": 4.641485275288093e-07,
+      "loss": 0.7114,
+      "step": 30
+    },
+    {
+      "epoch": 0.005119672340970178,
+      "grad_norm": 1.1470946073532104,
+      "learning_rate": 6.241997439180538e-07,
+      "loss": 0.7083,
+      "step": 40
+    },
+    {
+      "epoch": 0.006399590426212722,
+      "grad_norm": 1.1680080890655518,
+      "learning_rate": 7.842509603072984e-07,
+      "loss": 0.7109,
+      "step": 50
+    },
+    {
+      "epoch": 0.007679508511455267,
+      "grad_norm": 0.6832358241081238,
+      "learning_rate": 9.44302176696543e-07,
+      "loss": 0.7131,
+      "step": 60
+    },
+    {
+      "epoch": 0.008959426596697812,
+      "grad_norm": 1.8029249906539917,
+      "learning_rate": 1.1043533930857875e-06,
+      "loss": 0.7092,
+      "step": 70
+    },
+    {
+      "epoch": 0.010239344681940356,
+      "grad_norm": 1.795204758644104,
+      "learning_rate": 1.264404609475032e-06,
+      "loss": 0.7063,
+      "step": 80
+    },
+    {
+      "epoch": 0.011519262767182901,
+      "grad_norm": 1.2713547945022583,
+      "learning_rate": 1.4244558258642767e-06,
+      "loss": 0.7126,
+      "step": 90
+    },
+    {
+      "epoch": 0.012799180852425445,
+      "grad_norm": 1.2709708213806152,
+      "learning_rate": 1.5845070422535212e-06,
+      "loss": 0.7069,
+      "step": 100
+    },
+    {
+      "epoch": 0.01407909893766799,
+      "grad_norm": 0.8230543732643127,
+      "learning_rate": 1.7445582586427658e-06,
+      "loss": 0.7036,
+      "step": 110
+    },
+    {
+      "epoch": 0.015359017022910534,
+      "grad_norm": 0.7209059596061707,
+      "learning_rate": 1.9046094750320101e-06,
+      "loss": 0.7058,
+      "step": 120
+    },
+    {
+      "epoch": 0.016638935108153077,
+      "grad_norm": 0.7314836978912354,
+      "learning_rate": 2.064660691421255e-06,
+      "loss": 0.7046,
+      "step": 130
+    },
+    {
+      "epoch": 0.017918853193395624,
+      "grad_norm": 0.7659752368927002,
+      "learning_rate": 2.2247119078104993e-06,
+      "loss": 0.6989,
+      "step": 140
+    },
+    {
+      "epoch": 0.019198771278638168,
+      "grad_norm": 0.9008486866950989,
+      "learning_rate": 2.384763124199744e-06,
+      "loss": 0.6998,
+      "step": 150
+    },
+    {
+      "epoch": 0.02047868936388071,
+      "grad_norm": 1.0409601926803589,
+      "learning_rate": 2.5448143405889883e-06,
+      "loss": 0.7016,
+      "step": 160
+    },
+    {
+      "epoch": 0.021758607449123255,
+      "grad_norm": 0.8855634927749634,
+      "learning_rate": 2.704865556978233e-06,
+      "loss": 0.6947,
+      "step": 170
+    },
+    {
+      "epoch": 0.023038525534365802,
+      "grad_norm": 0.798701286315918,
+      "learning_rate": 2.8649167733674777e-06,
+      "loss": 0.6935,
+      "step": 180
+    },
+    {
+      "epoch": 0.024318443619608346,
+      "grad_norm": 1.1289243698120117,
+      "learning_rate": 3.024967989756722e-06,
+      "loss": 0.6937,
+      "step": 190
+    },
+    {
+      "epoch": 0.02559836170485089,
+      "grad_norm": 1.4480715990066528,
+      "learning_rate": 3.185019206145967e-06,
+      "loss": 0.6948,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 31252,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3367821508608000.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

graphcodebert-mixcode-fft/checkpoint-200/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:55e805564976941c69ed81dd4f57f02f704352ee18e811a5a0c0eac53999ccb7
+size 5841

graphcodebert-mixcode-fft/checkpoint-200/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

graphcodebert-mixcode-fft/checkpoint-300/config.json ADDED Viewed

	@@ -0,0 +1,29 @@

+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.56.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

graphcodebert-mixcode-fft/checkpoint-300/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

graphcodebert-mixcode-fft/checkpoint-300/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a41da2975d5c8da45f72c323b62d6ec84e08f45380ee8e46aa9264e93f3c009f
+size 498612824

graphcodebert-mixcode-fft/checkpoint-300/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3e0f890ee01e658e09411ac4671fa7e6acf6add3a66c2dbe04247a90ddcb4106
+size 4741923

graphcodebert-mixcode-fft/checkpoint-300/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e1dfb987e1a050c893d93290f8e85866cd8c1fac4f3944f09511cfe099a3e447
+size 14645

graphcodebert-mixcode-fft/checkpoint-300/scaler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:30af866df24edce708e1eb20700878b402fa05707fa9bc5f332496baf440dbbb
+size 1383

graphcodebert-mixcode-fft/checkpoint-300/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f8e119b4cd3f8598a5af51d58c37b3dbd9b0034a064c6718afecaa6a4b129a23
+size 1465

graphcodebert-mixcode-fft/checkpoint-300/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

graphcodebert-mixcode-fft/checkpoint-300/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

graphcodebert-mixcode-fft/checkpoint-300/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

graphcodebert-mixcode-fft/checkpoint-300/trainer_state.json ADDED Viewed

	@@ -0,0 +1,253 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.038397542557276336,
+  "eval_steps": 1000,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0012799180852425445,
+      "grad_norm": 1.2002202272415161,
+      "learning_rate": 1.4404609475032012e-07,
+      "loss": 0.714,
+      "step": 10
+    },
+    {
+      "epoch": 0.002559836170485089,
+      "grad_norm": 1.0710716247558594,
+      "learning_rate": 3.040973111395647e-07,
+      "loss": 0.7181,
+      "step": 20
+    },
+    {
+      "epoch": 0.0038397542557276334,
+      "grad_norm": 1.0631524324417114,
+      "learning_rate": 4.641485275288093e-07,
+      "loss": 0.7114,
+      "step": 30
+    },
+    {
+      "epoch": 0.005119672340970178,
+      "grad_norm": 1.1470946073532104,
+      "learning_rate": 6.241997439180538e-07,
+      "loss": 0.7083,
+      "step": 40
+    },
+    {
+      "epoch": 0.006399590426212722,
+      "grad_norm": 1.1680080890655518,
+      "learning_rate": 7.842509603072984e-07,
+      "loss": 0.7109,
+      "step": 50
+    },
+    {
+      "epoch": 0.007679508511455267,
+      "grad_norm": 0.6832358241081238,
+      "learning_rate": 9.44302176696543e-07,
+      "loss": 0.7131,
+      "step": 60
+    },
+    {
+      "epoch": 0.008959426596697812,
+      "grad_norm": 1.8029249906539917,
+      "learning_rate": 1.1043533930857875e-06,
+      "loss": 0.7092,
+      "step": 70
+    },
+    {
+      "epoch": 0.010239344681940356,
+      "grad_norm": 1.795204758644104,
+      "learning_rate": 1.264404609475032e-06,
+      "loss": 0.7063,
+      "step": 80
+    },
+    {
+      "epoch": 0.011519262767182901,
+      "grad_norm": 1.2713547945022583,
+      "learning_rate": 1.4244558258642767e-06,
+      "loss": 0.7126,
+      "step": 90
+    },
+    {
+      "epoch": 0.012799180852425445,
+      "grad_norm": 1.2709708213806152,
+      "learning_rate": 1.5845070422535212e-06,
+      "loss": 0.7069,
+      "step": 100
+    },
+    {
+      "epoch": 0.01407909893766799,
+      "grad_norm": 0.8230543732643127,
+      "learning_rate": 1.7445582586427658e-06,
+      "loss": 0.7036,
+      "step": 110
+    },
+    {
+      "epoch": 0.015359017022910534,
+      "grad_norm": 0.7209059596061707,
+      "learning_rate": 1.9046094750320101e-06,
+      "loss": 0.7058,
+      "step": 120
+    },
+    {
+      "epoch": 0.016638935108153077,
+      "grad_norm": 0.7314836978912354,
+      "learning_rate": 2.064660691421255e-06,
+      "loss": 0.7046,
+      "step": 130
+    },
+    {
+      "epoch": 0.017918853193395624,
+      "grad_norm": 0.7659752368927002,
+      "learning_rate": 2.2247119078104993e-06,
+      "loss": 0.6989,
+      "step": 140
+    },
+    {
+      "epoch": 0.019198771278638168,
+      "grad_norm": 0.9008486866950989,
+      "learning_rate": 2.384763124199744e-06,
+      "loss": 0.6998,
+      "step": 150
+    },
+    {
+      "epoch": 0.02047868936388071,
+      "grad_norm": 1.0409601926803589,
+      "learning_rate": 2.5448143405889883e-06,
+      "loss": 0.7016,
+      "step": 160
+    },
+    {
+      "epoch": 0.021758607449123255,
+      "grad_norm": 0.8855634927749634,
+      "learning_rate": 2.704865556978233e-06,
+      "loss": 0.6947,
+      "step": 170
+    },
+    {
+      "epoch": 0.023038525534365802,
+      "grad_norm": 0.798701286315918,
+      "learning_rate": 2.8649167733674777e-06,
+      "loss": 0.6935,
+      "step": 180
+    },
+    {
+      "epoch": 0.024318443619608346,
+      "grad_norm": 1.1289243698120117,
+      "learning_rate": 3.024967989756722e-06,
+      "loss": 0.6937,
+      "step": 190
+    },
+    {
+      "epoch": 0.02559836170485089,
+      "grad_norm": 1.4480715990066528,
+      "learning_rate": 3.185019206145967e-06,
+      "loss": 0.6948,
+      "step": 200
+    },
+    {
+      "epoch": 0.026878279790093433,
+      "grad_norm": 0.6359772682189941,
+      "learning_rate": 3.3450704225352113e-06,
+      "loss": 0.6904,
+      "step": 210
+    },
+    {
+      "epoch": 0.02815819787533598,
+      "grad_norm": 1.1023344993591309,
+      "learning_rate": 3.5051216389244556e-06,
+      "loss": 0.6873,
+      "step": 220
+    },
+    {
+      "epoch": 0.029438115960578524,
+      "grad_norm": 0.8251340389251709,
+      "learning_rate": 3.6651728553137003e-06,
+      "loss": 0.6859,
+      "step": 230
+    },
+    {
+      "epoch": 0.030718034045821067,
+      "grad_norm": 0.7032744288444519,
+      "learning_rate": 3.825224071702945e-06,
+      "loss": 0.6804,
+      "step": 240
+    },
+    {
+      "epoch": 0.031997952131063614,
+      "grad_norm": 0.7794032096862793,
+      "learning_rate": 3.98527528809219e-06,
+      "loss": 0.6831,
+      "step": 250
+    },
+    {
+      "epoch": 0.033277870216306155,
+      "grad_norm": 0.6654011607170105,
+      "learning_rate": 4.145326504481434e-06,
+      "loss": 0.6813,
+      "step": 260
+    },
+    {
+      "epoch": 0.0345577883015487,
+      "grad_norm": 1.7002371549606323,
+      "learning_rate": 4.3053777208706795e-06,
+      "loss": 0.6793,
+      "step": 270
+    },
+    {
+      "epoch": 0.03583770638679125,
+      "grad_norm": 1.0438320636749268,
+      "learning_rate": 4.465428937259923e-06,
+      "loss": 0.6758,
+      "step": 280
+    },
+    {
+      "epoch": 0.03711762447203379,
+      "grad_norm": 0.6591306924819946,
+      "learning_rate": 4.625480153649168e-06,
+      "loss": 0.6758,
+      "step": 290
+    },
+    {
+      "epoch": 0.038397542557276336,
+      "grad_norm": 0.5876058340072632,
+      "learning_rate": 4.785531370038412e-06,
+      "loss": 0.6742,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 31252,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5051732262912000.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

graphcodebert-mixcode-fft/checkpoint-300/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:55e805564976941c69ed81dd4f57f02f704352ee18e811a5a0c0eac53999ccb7
+size 5841

graphcodebert-mixcode-fft/checkpoint-300/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

graphcodebert-mixcode-fft/checkpoint-400/config.json ADDED Viewed

	@@ -0,0 +1,29 @@

+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.56.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

graphcodebert-mixcode-fft/checkpoint-400/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

graphcodebert-mixcode-fft/checkpoint-400/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cb004030b417087d9b64cc619b04cd237979a2d778adc3d15ee5d99f51943936
+size 498612824

graphcodebert-mixcode-fft/checkpoint-400/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8bbf5f814de5ac459e2a381ea282bdad423668e458706b7dbcc21cd3919662de
+size 4741923

graphcodebert-mixcode-fft/checkpoint-400/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:767451645f91f6b3b01eeb7b622f9415eb0e210eaf2f1868fd8984c503d39ac3
+size 14645

graphcodebert-mixcode-fft/checkpoint-400/scaler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:30858f23bcb22d0baef45bd4add9d6fa474141308c12653c706077b87d932e49
+size 1383

graphcodebert-mixcode-fft/checkpoint-400/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:96aef0834a2bf334a9c09519b222fef1c3fbdcfbb4b3962aeae8d3e2cd7b8901
+size 1465

graphcodebert-mixcode-fft/checkpoint-400/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

graphcodebert-mixcode-fft/checkpoint-400/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

graphcodebert-mixcode-fft/checkpoint-400/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

graphcodebert-mixcode-fft/checkpoint-400/trainer_state.json ADDED Viewed

	@@ -0,0 +1,323 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.05119672340970178,
+  "eval_steps": 1000,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0012799180852425445,
+      "grad_norm": 1.2002202272415161,
+      "learning_rate": 1.4404609475032012e-07,
+      "loss": 0.714,
+      "step": 10
+    },
+    {
+      "epoch": 0.002559836170485089,
+      "grad_norm": 1.0710716247558594,
+      "learning_rate": 3.040973111395647e-07,
+      "loss": 0.7181,
+      "step": 20
+    },
+    {
+      "epoch": 0.0038397542557276334,
+      "grad_norm": 1.0631524324417114,
+      "learning_rate": 4.641485275288093e-07,
+      "loss": 0.7114,
+      "step": 30
+    },
+    {
+      "epoch": 0.005119672340970178,
+      "grad_norm": 1.1470946073532104,
+      "learning_rate": 6.241997439180538e-07,
+      "loss": 0.7083,
+      "step": 40
+    },
+    {
+      "epoch": 0.006399590426212722,
+      "grad_norm": 1.1680080890655518,
+      "learning_rate": 7.842509603072984e-07,
+      "loss": 0.7109,
+      "step": 50
+    },
+    {
+      "epoch": 0.007679508511455267,
+      "grad_norm": 0.6832358241081238,
+      "learning_rate": 9.44302176696543e-07,
+      "loss": 0.7131,
+      "step": 60
+    },
+    {
+      "epoch": 0.008959426596697812,
+      "grad_norm": 1.8029249906539917,
+      "learning_rate": 1.1043533930857875e-06,
+      "loss": 0.7092,
+      "step": 70
+    },
+    {
+      "epoch": 0.010239344681940356,
+      "grad_norm": 1.795204758644104,
+      "learning_rate": 1.264404609475032e-06,
+      "loss": 0.7063,
+      "step": 80
+    },
+    {
+      "epoch": 0.011519262767182901,
+      "grad_norm": 1.2713547945022583,
+      "learning_rate": 1.4244558258642767e-06,
+      "loss": 0.7126,
+      "step": 90
+    },
+    {
+      "epoch": 0.012799180852425445,
+      "grad_norm": 1.2709708213806152,
+      "learning_rate": 1.5845070422535212e-06,
+      "loss": 0.7069,
+      "step": 100
+    },
+    {
+      "epoch": 0.01407909893766799,
+      "grad_norm": 0.8230543732643127,
+      "learning_rate": 1.7445582586427658e-06,
+      "loss": 0.7036,
+      "step": 110
+    },
+    {
+      "epoch": 0.015359017022910534,
+      "grad_norm": 0.7209059596061707,
+      "learning_rate": 1.9046094750320101e-06,
+      "loss": 0.7058,
+      "step": 120
+    },
+    {
+      "epoch": 0.016638935108153077,
+      "grad_norm": 0.7314836978912354,
+      "learning_rate": 2.064660691421255e-06,
+      "loss": 0.7046,
+      "step": 130
+    },
+    {
+      "epoch": 0.017918853193395624,
+      "grad_norm": 0.7659752368927002,
+      "learning_rate": 2.2247119078104993e-06,
+      "loss": 0.6989,
+      "step": 140
+    },
+    {
+      "epoch": 0.019198771278638168,
+      "grad_norm": 0.9008486866950989,
+      "learning_rate": 2.384763124199744e-06,
+      "loss": 0.6998,
+      "step": 150
+    },
+    {
+      "epoch": 0.02047868936388071,
+      "grad_norm": 1.0409601926803589,
+      "learning_rate": 2.5448143405889883e-06,
+      "loss": 0.7016,
+      "step": 160
+    },
+    {
+      "epoch": 0.021758607449123255,
+      "grad_norm": 0.8855634927749634,
+      "learning_rate": 2.704865556978233e-06,
+      "loss": 0.6947,
+      "step": 170
+    },
+    {
+      "epoch": 0.023038525534365802,
+      "grad_norm": 0.798701286315918,
+      "learning_rate": 2.8649167733674777e-06,
+      "loss": 0.6935,
+      "step": 180
+    },
+    {
+      "epoch": 0.024318443619608346,
+      "grad_norm": 1.1289243698120117,
+      "learning_rate": 3.024967989756722e-06,
+      "loss": 0.6937,
+      "step": 190
+    },
+    {
+      "epoch": 0.02559836170485089,
+      "grad_norm": 1.4480715990066528,
+      "learning_rate": 3.185019206145967e-06,
+      "loss": 0.6948,
+      "step": 200
+    },
+    {
+      "epoch": 0.026878279790093433,
+      "grad_norm": 0.6359772682189941,
+      "learning_rate": 3.3450704225352113e-06,
+      "loss": 0.6904,
+      "step": 210
+    },
+    {
+      "epoch": 0.02815819787533598,
+      "grad_norm": 1.1023344993591309,
+      "learning_rate": 3.5051216389244556e-06,
+      "loss": 0.6873,
+      "step": 220
+    },
+    {
+      "epoch": 0.029438115960578524,
+      "grad_norm": 0.8251340389251709,
+      "learning_rate": 3.6651728553137003e-06,
+      "loss": 0.6859,
+      "step": 230
+    },
+    {
+      "epoch": 0.030718034045821067,
+      "grad_norm": 0.7032744288444519,
+      "learning_rate": 3.825224071702945e-06,
+      "loss": 0.6804,
+      "step": 240
+    },
+    {
+      "epoch": 0.031997952131063614,
+      "grad_norm": 0.7794032096862793,
+      "learning_rate": 3.98527528809219e-06,
+      "loss": 0.6831,
+      "step": 250
+    },
+    {
+      "epoch": 0.033277870216306155,
+      "grad_norm": 0.6654011607170105,
+      "learning_rate": 4.145326504481434e-06,
+      "loss": 0.6813,
+      "step": 260
+    },
+    {
+      "epoch": 0.0345577883015487,
+      "grad_norm": 1.7002371549606323,
+      "learning_rate": 4.3053777208706795e-06,
+      "loss": 0.6793,
+      "step": 270
+    },
+    {
+      "epoch": 0.03583770638679125,
+      "grad_norm": 1.0438320636749268,
+      "learning_rate": 4.465428937259923e-06,
+      "loss": 0.6758,
+      "step": 280
+    },
+    {
+      "epoch": 0.03711762447203379,
+      "grad_norm": 0.6591306924819946,
+      "learning_rate": 4.625480153649168e-06,
+      "loss": 0.6758,
+      "step": 290
+    },
+    {
+      "epoch": 0.038397542557276336,
+      "grad_norm": 0.5876058340072632,
+      "learning_rate": 4.785531370038412e-06,
+      "loss": 0.6742,
+      "step": 300
+    },
+    {
+      "epoch": 0.039677460642518876,
+      "grad_norm": 0.5839381814002991,
+      "learning_rate": 4.9455825864276575e-06,
+      "loss": 0.6706,
+      "step": 310
+    },
+    {
+      "epoch": 0.04095737872776142,
+      "grad_norm": 1.3025041818618774,
+      "learning_rate": 5.105633802816902e-06,
+      "loss": 0.6658,
+      "step": 320
+    },
+    {
+      "epoch": 0.04223729681300397,
+      "grad_norm": 0.5543903708457947,
+      "learning_rate": 5.265685019206147e-06,
+      "loss": 0.6722,
+      "step": 330
+    },
+    {
+      "epoch": 0.04351721489824651,
+      "grad_norm": 0.5097215175628662,
+      "learning_rate": 5.425736235595391e-06,
+      "loss": 0.6704,
+      "step": 340
+    },
+    {
+      "epoch": 0.04479713298348906,
+      "grad_norm": 0.760080873966217,
+      "learning_rate": 5.585787451984635e-06,
+      "loss": 0.6652,
+      "step": 350
+    },
+    {
+      "epoch": 0.046077051068731605,
+      "grad_norm": 0.7467712759971619,
+      "learning_rate": 5.74583866837388e-06,
+      "loss": 0.668,
+      "step": 360
+    },
+    {
+      "epoch": 0.047356969153974145,
+      "grad_norm": 0.9601678848266602,
+      "learning_rate": 5.905889884763125e-06,
+      "loss": 0.6619,
+      "step": 370
+    },
+    {
+      "epoch": 0.04863688723921669,
+      "grad_norm": 0.7230914235115051,
+      "learning_rate": 6.065941101152369e-06,
+      "loss": 0.6585,
+      "step": 380
+    },
+    {
+      "epoch": 0.04991680532445923,
+      "grad_norm": 0.8606265783309937,
+      "learning_rate": 6.225992317541613e-06,
+      "loss": 0.6591,
+      "step": 390
+    },
+    {
+      "epoch": 0.05119672340970178,
+      "grad_norm": 0.6350621581077576,
+      "learning_rate": 6.386043533930858e-06,
+      "loss": 0.6575,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 31252,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6735643017216000.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}