Upload folder using huggingface_hub

checkpoint-700/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-700/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6360c6a9127342f0bf83a6b2b8b9742c6a1d60eebb0de956649de38d5fd5d666
+size 437955572

checkpoint-700/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a1b16efb8234d643ef0984060cdb3aa1da309fcf2ea774720cc39735f9278e
+size 876032250

checkpoint-700/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8142e7505788be9614fece6d9e7494673947881136ae0f4b3862a3093331437
+size 14244

checkpoint-700/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21403d5a03b1fcf9048c6478c3efaf09d7b8ea4d82cd726bd9f2e78d5628ac37
+size 1064

checkpoint-700/trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 45.52845528455285,
+  "eval_steps": 100,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.252032520325203,
+      "grad_norm": 146.2987823486328,
+      "learning_rate": 2.25e-05,
+      "loss": 3.7155,
+      "step": 50
+    },
+    {
+      "epoch": 6.504065040650406,
+      "grad_norm": 25.606613159179688,
+      "learning_rate": 4.75e-05,
+      "loss": 0.3122,
+      "step": 100
+    },
+    {
+      "epoch": 6.504065040650406,
+      "eval_loss": 0.06210774928331375,
+      "eval_runtime": 0.4632,
+      "eval_samples_per_second": 118.733,
+      "eval_steps_per_second": 30.223,
+      "step": 100
+    },
+    {
+      "epoch": 9.75609756097561,
+      "grad_norm": 70.79466247558594,
+      "learning_rate": 4.653846153846154e-05,
+      "loss": 0.0857,
+      "step": 150
+    },
+    {
+      "epoch": 13.008130081300813,
+      "grad_norm": 24.777908325195312,
+      "learning_rate": 4.269230769230769e-05,
+      "loss": 0.0344,
+      "step": 200
+    },
+    {
+      "epoch": 13.008130081300813,
+      "eval_loss": 0.02328495681285858,
+      "eval_runtime": 0.4673,
+      "eval_samples_per_second": 117.696,
+      "eval_steps_per_second": 29.959,
+      "step": 200
+    },
+    {
+      "epoch": 16.260162601626018,
+      "grad_norm": 8.731575012207031,
+      "learning_rate": 3.884615384615385e-05,
+      "loss": 0.0301,
+      "step": 250
+    },
+    {
+      "epoch": 19.51219512195122,
+      "grad_norm": 4.41317081451416,
+      "learning_rate": 3.5e-05,
+      "loss": 0.0213,
+      "step": 300
+    },
+    {
+      "epoch": 19.51219512195122,
+      "eval_loss": 0.021754104644060135,
+      "eval_runtime": 0.4593,
+      "eval_samples_per_second": 119.74,
+      "eval_steps_per_second": 30.479,
+      "step": 300
+    },
+    {
+      "epoch": 22.764227642276424,
+      "grad_norm": 4.309276580810547,
+      "learning_rate": 3.115384615384615e-05,
+      "loss": 0.0173,
+      "step": 350
+    },
+    {
+      "epoch": 26.016260162601625,
+      "grad_norm": 4.0787177085876465,
+      "learning_rate": 2.7307692307692305e-05,
+      "loss": 0.0133,
+      "step": 400
+    },
+    {
+      "epoch": 26.016260162601625,
+      "eval_loss": 0.007923820987343788,
+      "eval_runtime": 0.466,
+      "eval_samples_per_second": 118.03,
+      "eval_steps_per_second": 30.044,
+      "step": 400
+    },
+    {
+      "epoch": 29.26829268292683,
+      "grad_norm": 2.8265419006347656,
+      "learning_rate": 2.3461538461538464e-05,
+      "loss": 0.0128,
+      "step": 450
+    },
+    {
+      "epoch": 32.520325203252035,
+      "grad_norm": 3.378178358078003,
+      "learning_rate": 1.9615384615384617e-05,
+      "loss": 0.0106,
+      "step": 500
+    },
+    {
+      "epoch": 32.520325203252035,
+      "eval_loss": 0.009708667173981667,
+      "eval_runtime": 0.4796,
+      "eval_samples_per_second": 114.679,
+      "eval_steps_per_second": 29.191,
+      "step": 500
+    },
+    {
+      "epoch": 35.77235772357724,
+      "grad_norm": 8.75239086151123,
+      "learning_rate": 1.576923076923077e-05,
+      "loss": 0.0084,
+      "step": 550
+    },
+    {
+      "epoch": 39.02439024390244,
+      "grad_norm": 6.199377059936523,
+      "learning_rate": 1.1923076923076925e-05,
+      "loss": 0.0077,
+      "step": 600
+    },
+    {
+      "epoch": 39.02439024390244,
+      "eval_loss": 0.010460535995662212,
+      "eval_runtime": 0.456,
+      "eval_samples_per_second": 120.603,
+      "eval_steps_per_second": 30.699,
+      "step": 600
+    },
+    {
+      "epoch": 42.27642276422764,
+      "grad_norm": 4.703422546386719,
+      "learning_rate": 8.076923076923077e-06,
+      "loss": 0.0065,
+      "step": 650
+    },
+    {
+      "epoch": 45.52845528455285,
+      "grad_norm": 3.5736358165740967,
+      "learning_rate": 4.230769230769231e-06,
+      "loss": 0.0054,
+      "step": 700
+    },
+    {
+      "epoch": 45.52845528455285,
+      "eval_loss": 0.00792544987052679,
+      "eval_runtime": 0.4594,
+      "eval_samples_per_second": 119.722,
+      "eval_steps_per_second": 30.475,
+      "step": 700
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5881794831836160.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-700/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5d456a9b82954adbf560ec2a0a497c07cc203010e4d45e32fef528674631e04
+size 5240

checkpoint-750/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-750/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c6e5ccc9edbaa8f1faa4afa4f758aa85112fb842c4155822267ed720f1139ce
+size 437955572

checkpoint-750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8ae4e2e485c256840d46661719ca0ecab3a1d96b6ec7058baf0a3205731a577
+size 876032250

checkpoint-750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b45a236ad6cc86e8d7a8a2b4c917dc53a8af640c7e1770cf245a9de3869566d6
+size 14244

checkpoint-750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f29d69aec3ca2fcf9f341b05f5651afb3339d2916402e7b67843eda3443defa
+size 1064

checkpoint-750/trainer_state.json

@@ -0,0 +1,194 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 48.78048780487805,
+  "eval_steps": 100,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.252032520325203,
+      "grad_norm": 146.2987823486328,
+      "learning_rate": 2.25e-05,
+      "loss": 3.7155,
+      "step": 50
+    },
+    {
+      "epoch": 6.504065040650406,
+      "grad_norm": 25.606613159179688,
+      "learning_rate": 4.75e-05,
+      "loss": 0.3122,
+      "step": 100
+    },
+    {
+      "epoch": 6.504065040650406,
+      "eval_loss": 0.06210774928331375,
+      "eval_runtime": 0.4632,
+      "eval_samples_per_second": 118.733,
+      "eval_steps_per_second": 30.223,
+      "step": 100
+    },
+    {
+      "epoch": 9.75609756097561,
+      "grad_norm": 70.79466247558594,
+      "learning_rate": 4.653846153846154e-05,
+      "loss": 0.0857,
+      "step": 150
+    },
+    {
+      "epoch": 13.008130081300813,
+      "grad_norm": 24.777908325195312,
+      "learning_rate": 4.269230769230769e-05,
+      "loss": 0.0344,
+      "step": 200
+    },
+    {
+      "epoch": 13.008130081300813,
+      "eval_loss": 0.02328495681285858,
+      "eval_runtime": 0.4673,
+      "eval_samples_per_second": 117.696,
+      "eval_steps_per_second": 29.959,
+      "step": 200
+    },
+    {
+      "epoch": 16.260162601626018,
+      "grad_norm": 8.731575012207031,
+      "learning_rate": 3.884615384615385e-05,
+      "loss": 0.0301,
+      "step": 250
+    },
+    {
+      "epoch": 19.51219512195122,
+      "grad_norm": 4.41317081451416,
+      "learning_rate": 3.5e-05,
+      "loss": 0.0213,
+      "step": 300
+    },
+    {
+      "epoch": 19.51219512195122,
+      "eval_loss": 0.021754104644060135,
+      "eval_runtime": 0.4593,
+      "eval_samples_per_second": 119.74,
+      "eval_steps_per_second": 30.479,
+      "step": 300
+    },
+    {
+      "epoch": 22.764227642276424,
+      "grad_norm": 4.309276580810547,
+      "learning_rate": 3.115384615384615e-05,
+      "loss": 0.0173,
+      "step": 350
+    },
+    {
+      "epoch": 26.016260162601625,
+      "grad_norm": 4.0787177085876465,
+      "learning_rate": 2.7307692307692305e-05,
+      "loss": 0.0133,
+      "step": 400
+    },
+    {
+      "epoch": 26.016260162601625,
+      "eval_loss": 0.007923820987343788,
+      "eval_runtime": 0.466,
+      "eval_samples_per_second": 118.03,
+      "eval_steps_per_second": 30.044,
+      "step": 400
+    },
+    {
+      "epoch": 29.26829268292683,
+      "grad_norm": 2.8265419006347656,
+      "learning_rate": 2.3461538461538464e-05,
+      "loss": 0.0128,
+      "step": 450
+    },
+    {
+      "epoch": 32.520325203252035,
+      "grad_norm": 3.378178358078003,
+      "learning_rate": 1.9615384615384617e-05,
+      "loss": 0.0106,
+      "step": 500
+    },
+    {
+      "epoch": 32.520325203252035,
+      "eval_loss": 0.009708667173981667,
+      "eval_runtime": 0.4796,
+      "eval_samples_per_second": 114.679,
+      "eval_steps_per_second": 29.191,
+      "step": 500
+    },
+    {
+      "epoch": 35.77235772357724,
+      "grad_norm": 8.75239086151123,
+      "learning_rate": 1.576923076923077e-05,
+      "loss": 0.0084,
+      "step": 550
+    },
+    {
+      "epoch": 39.02439024390244,
+      "grad_norm": 6.199377059936523,
+      "learning_rate": 1.1923076923076925e-05,
+      "loss": 0.0077,
+      "step": 600
+    },
+    {
+      "epoch": 39.02439024390244,
+      "eval_loss": 0.010460535995662212,
+      "eval_runtime": 0.456,
+      "eval_samples_per_second": 120.603,
+      "eval_steps_per_second": 30.699,
+      "step": 600
+    },
+    {
+      "epoch": 42.27642276422764,
+      "grad_norm": 4.703422546386719,
+      "learning_rate": 8.076923076923077e-06,
+      "loss": 0.0065,
+      "step": 650
+    },
+    {
+      "epoch": 45.52845528455285,
+      "grad_norm": 3.5736358165740967,
+      "learning_rate": 4.230769230769231e-06,
+      "loss": 0.0054,
+      "step": 700
+    },
+    {
+      "epoch": 45.52845528455285,
+      "eval_loss": 0.00792544987052679,
+      "eval_runtime": 0.4594,
+      "eval_samples_per_second": 119.722,
+      "eval_steps_per_second": 30.475,
+      "step": 700
+    },
+    {
+      "epoch": 48.78048780487805,
+      "grad_norm": 3.0123989582061768,
+      "learning_rate": 3.846153846153847e-07,
+      "loss": 0.0049,
+      "step": 750
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6301979414544384.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5d456a9b82954adbf560ec2a0a497c07cc203010e4d45e32fef528674631e04
+size 5240

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c6e5ccc9edbaa8f1faa4afa4f758aa85112fb842c4155822267ed720f1139ce
+size 437955572

special_tokens_map.json

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

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": false,
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}