Upload folder using huggingface_hub

checkpoint-2148/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30522
+}

checkpoint-2148/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1dcde95259d76e9911c90ff1375db08a9c81fc73433921e397a1e321292a0a
+size 267832560

checkpoint-2148/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a3eddf7295c468a928caa39ae2c19b7a4b87535e7c1d0d3e2c318f0ff3829f
+size 535727290

checkpoint-2148/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d309d756613e1a1ed977bf34cfc3da77bd9b88feadff65b217ad2875ecb39a8a
+size 14244

checkpoint-2148/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed6ad272294e3eac7ad7e1a757cdc49a6c0cfefb8a9d6f9c700db60838f2e33
+size 1064

checkpoint-2148/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-2148/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-2148/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": 0.16297364234924316,
+  "best_model_checkpoint": "/home/paperspace/distilbert_distilbert-base-uncased_cpt_f80627ff/checkpoint-2148",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2148,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.418063314711358e-07,
+      "loss": 0.5529,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 8.836126629422719e-07,
+      "loss": 0.2622,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 8.254189944134078e-07,
+      "loss": 0.1843,
+      "step": 1500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 7.672253258845437e-07,
+      "loss": 0.1707,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9436447582835416,
+      "eval_f1": 0.9439168742293816,
+      "eval_loss": 0.16297364234924316,
+      "eval_precision": 0.944853339492281,
+      "eval_recall": 0.9436447582835416,
+      "eval_runtime": 3.7301,
+      "eval_samples_per_second": 1974.215,
+      "eval_steps_per_second": 123.59,
+      "step": 2148
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8592,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 435621110283360.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2148/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2821a1fa25b9649959a66726e89f881537d33d8e4c2c0b30139409929b84dff
+size 4664

checkpoint-4296/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30522
+}

checkpoint-4296/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b699e20f8a1271fd101f0c484841eae3a59406556c16035e124d4e19fa78576
+size 267832560

checkpoint-4296/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fdfabb4ad88c7631c6e79984cc151d4146675b7efb258e008535316281ca126
+size 535727290

checkpoint-4296/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a04043bdf2761c555a27dd8b57cabd49b51b69de40f84c0bbe7fe685268a3739
+size 14244

checkpoint-4296/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40cd7351ba38f4388eb1f376daf7a5da66cfdcb89e0ca8b214ef24cfa58f1b10
+size 1064

checkpoint-4296/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-4296/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-4296/trainer_state.json

@@ -0,0 +1,91 @@
+{
+  "best_metric": 0.15333020687103271,
+  "best_model_checkpoint": "/home/paperspace/distilbert_distilbert-base-uncased_cpt_f80627ff/checkpoint-4296",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4296,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.418063314711358e-07,
+      "loss": 0.5529,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 8.836126629422719e-07,
+      "loss": 0.2622,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 8.254189944134078e-07,
+      "loss": 0.1843,
+      "step": 1500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 7.672253258845437e-07,
+      "loss": 0.1707,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9436447582835416,
+      "eval_f1": 0.9439168742293816,
+      "eval_loss": 0.16297364234924316,
+      "eval_precision": 0.944853339492281,
+      "eval_recall": 0.9436447582835416,
+      "eval_runtime": 3.7301,
+      "eval_samples_per_second": 1974.215,
+      "eval_steps_per_second": 123.59,
+      "step": 2148
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.090316573556797e-07,
+      "loss": 0.165,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 6.508379888268156e-07,
+      "loss": 0.1518,
+      "step": 3000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5.926443202979516e-07,
+      "loss": 0.1561,
+      "step": 3500
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 5.344506517690875e-07,
+      "loss": 0.15,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9496197718631179,
+      "eval_f1": 0.9497706506636553,
+      "eval_loss": 0.15333020687103271,
+      "eval_precision": 0.9501640547936412,
+      "eval_recall": 0.9496197718631179,
+      "eval_runtime": 3.7323,
+      "eval_samples_per_second": 1973.021,
+      "eval_steps_per_second": 123.515,
+      "step": 4296
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8592,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 876399393725724.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4296/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2821a1fa25b9649959a66726e89f881537d33d8e4c2c0b30139409929b84dff
+size 4664

checkpoint-6444/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30522
+}

checkpoint-6444/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0324132e9ebad8b20a89225f548ca18d623ed623962cc3c54a68e947e7ea36a
+size 267832560

checkpoint-6444/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:220527c43253501438dc37c40575361afc2fb42a1f54f5ab3fe69fab68170737
+size 535727290

checkpoint-6444/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:100fc9d431a4598eb1fe768a696101e86663de5fb64a78ad8d4d4e7a723ab3f3
+size 14244

checkpoint-6444/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a745cd9a9445926812b9b4f370727d536f8f79a39cd163ff667254b510b54e9f
+size 1064

checkpoint-6444/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-6444/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-6444/trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_metric": 0.15110179781913757,
+  "best_model_checkpoint": "/home/paperspace/distilbert_distilbert-base-uncased_cpt_f80627ff/checkpoint-6444",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6444,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.418063314711358e-07,
+      "loss": 0.5529,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 8.836126629422719e-07,
+      "loss": 0.2622,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 8.254189944134078e-07,
+      "loss": 0.1843,
+      "step": 1500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 7.672253258845437e-07,
+      "loss": 0.1707,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9436447582835416,
+      "eval_f1": 0.9439168742293816,
+      "eval_loss": 0.16297364234924316,
+      "eval_precision": 0.944853339492281,
+      "eval_recall": 0.9436447582835416,
+      "eval_runtime": 3.7301,
+      "eval_samples_per_second": 1974.215,
+      "eval_steps_per_second": 123.59,
+      "step": 2148
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.090316573556797e-07,
+      "loss": 0.165,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 6.508379888268156e-07,
+      "loss": 0.1518,
+      "step": 3000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5.926443202979516e-07,
+      "loss": 0.1561,
+      "step": 3500
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 5.344506517690875e-07,
+      "loss": 0.15,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9496197718631179,
+      "eval_f1": 0.9497706506636553,
+      "eval_loss": 0.15333020687103271,
+      "eval_precision": 0.9501640547936412,
+      "eval_recall": 0.9496197718631179,
+      "eval_runtime": 3.7323,
+      "eval_samples_per_second": 1973.021,
+      "eval_steps_per_second": 123.515,
+      "step": 4296
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.7625698324022343e-07,
+      "loss": 0.1467,
+      "step": 4500
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 4.1806331471135937e-07,
+      "loss": 0.1454,
+      "step": 5000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 3.598696461824953e-07,
+      "loss": 0.1536,
+      "step": 5500
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 3.016759776536313e-07,
+      "loss": 0.1474,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9505703422053232,
+      "eval_f1": 0.950777849389015,
+      "eval_loss": 0.15110179781913757,
+      "eval_precision": 0.9514811036756906,
+      "eval_recall": 0.9505703422053232,
+      "eval_runtime": 3.7273,
+      "eval_samples_per_second": 1975.7,
+      "eval_steps_per_second": 123.682,
+      "step": 6444
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8592,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1314366625827468.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6444/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2821a1fa25b9649959a66726e89f881537d33d8e4c2c0b30139409929b84dff
+size 4664

checkpoint-8592/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30522
+}

checkpoint-8592/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9eda0614794521654484f2bf77f1950e979cabd5dd29f14b8749c5dde2ac678
+size 267832560

checkpoint-8592/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66be16ce42bcc7e30c66380d5f4862b639a850215744329ba34ffc65df51164a
+size 535727290

checkpoint-8592/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f7773063c3339e633f7b7bce9e1c8aca9f0464ea763aa89f087c291754868a
+size 14244

checkpoint-8592/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1af71e4a7895768398dd0411313910c8b20c8660d7aef81e08c9d4d13be8ea2
+size 1064

checkpoint-8592/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-8592/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-8592/trainer_state.json

@@ -0,0 +1,169 @@
+{
+  "best_metric": 0.1497994363307953,
+  "best_model_checkpoint": "/home/paperspace/distilbert_distilbert-base-uncased_cpt_f80627ff/checkpoint-8592",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 8592,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.418063314711358e-07,
+      "loss": 0.5529,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 8.836126629422719e-07,
+      "loss": 0.2622,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 8.254189944134078e-07,
+      "loss": 0.1843,
+      "step": 1500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 7.672253258845437e-07,
+      "loss": 0.1707,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9436447582835416,
+      "eval_f1": 0.9439168742293816,
+      "eval_loss": 0.16297364234924316,
+      "eval_precision": 0.944853339492281,
+      "eval_recall": 0.9436447582835416,
+      "eval_runtime": 3.7301,
+      "eval_samples_per_second": 1974.215,
+      "eval_steps_per_second": 123.59,
+      "step": 2148
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.090316573556797e-07,
+      "loss": 0.165,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 6.508379888268156e-07,
+      "loss": 0.1518,
+      "step": 3000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5.926443202979516e-07,
+      "loss": 0.1561,
+      "step": 3500
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 5.344506517690875e-07,
+      "loss": 0.15,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9496197718631179,
+      "eval_f1": 0.9497706506636553,
+      "eval_loss": 0.15333020687103271,
+      "eval_precision": 0.9501640547936412,
+      "eval_recall": 0.9496197718631179,
+      "eval_runtime": 3.7323,
+      "eval_samples_per_second": 1973.021,
+      "eval_steps_per_second": 123.515,
+      "step": 4296
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.7625698324022343e-07,
+      "loss": 0.1467,
+      "step": 4500
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 4.1806331471135937e-07,
+      "loss": 0.1454,
+      "step": 5000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 3.598696461824953e-07,
+      "loss": 0.1536,
+      "step": 5500
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 3.016759776536313e-07,
+      "loss": 0.1474,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9505703422053232,
+      "eval_f1": 0.950777849389015,
+      "eval_loss": 0.15110179781913757,
+      "eval_precision": 0.9514811036756906,
+      "eval_recall": 0.9505703422053232,
+      "eval_runtime": 3.7273,
+      "eval_samples_per_second": 1975.7,
+      "eval_steps_per_second": 123.682,
+      "step": 6444
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 2.4348230912476723e-07,
+      "loss": 0.1481,
+      "step": 6500
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 1.8528864059590317e-07,
+      "loss": 0.1325,
+      "step": 7000
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 1.270949720670391e-07,
+      "loss": 0.1521,
+      "step": 7500
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 6.890130353817504e-08,
+      "loss": 0.1482,
+      "step": 8000
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 1.0707635009310987e-08,
+      "loss": 0.1417,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9507061379684953,
+      "eval_f1": 0.950911417495333,
+      "eval_loss": 0.1497994363307953,
+      "eval_precision": 0.951604073542191,
+      "eval_recall": 0.9507061379684953,
+      "eval_runtime": 3.7541,
+      "eval_samples_per_second": 1961.603,
+      "eval_steps_per_second": 122.8,
+      "step": 8592
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8592,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1751875913992452.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-8592/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2821a1fa25b9649959a66726e89f881537d33d8e4c2c0b30139409929b84dff
+size 4664