Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bab364cbac0a1539fe33803469d620a932c42a7d2c2975c32cc5a98832170a08
+oid sha256:adbcc302472d25aee76016eb179994f445fcdbd94a26ae33ee417737b2f5dc9b
 size 437958648

run-0/checkpoint-211/config.json

@@ -0,0 +1,27 @@
+{
+  "_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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-211/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f10d889ef90da40a4463fccdc587a0c6f79b63c3043b981495c2ea2d8f71bb
+size 437958648

run-0/checkpoint-211/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaa862c841a7df91716ee85fd295a1e2f956d7f9076f0320b020ec6d301c9cbc
+size 876038394

run-0/checkpoint-211/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a314ae894ddcb4d0cea1aa65198ad385a976466f4a5187cda99b66039caaad20
+size 14180

run-0/checkpoint-211/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59b8214ece541ba3c5d50b144e25e7060386724b1fc63fe88b7f0db85fbd8158
+size 1064

run-0/checkpoint-211/special_tokens_map.json

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

run-0/checkpoint-211/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-211/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.9071100917431193,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-0/checkpoint-211",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 211,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9071100917431193,
+      "eval_loss": 0.2743072807788849,
+      "eval_runtime": 2.2589,
+      "eval_samples_per_second": 386.028,
+      "eval_steps_per_second": 24.348,
+      "step": 211
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 633,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.665224131389019e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 10
+  }
+}

run-0/checkpoint-211/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:680d0afe4db5f1404c33bdba3d7f7d0610baba4265733865b13f9ea27d8c6125
+size 4920

run-0/checkpoint-422/config.json

@@ -0,0 +1,27 @@
+{
+  "_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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-422/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94ecceae6658a1a4641475b655f745173a7c08d19e9608929be006e5ce6b53ff
+size 437958648

run-0/checkpoint-422/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74e1cd4b3c58f388cc0cb03d2cf34f05ae9ad805cdab61379c556657c57024a7
+size 876038394

run-0/checkpoint-422/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cf52b768d0a203ee46aaea643f3d63097fe317b40796319811627de017c5073
+size 14180

run-0/checkpoint-422/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b4f0569f59f9764ea647f346f4672b98fd2208bca9f7011197e469824c5d020
+size 1064

run-0/checkpoint-422/special_tokens_map.json

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

run-0/checkpoint-422/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-422/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.9094036697247706,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-0/checkpoint-422",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 422,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9071100917431193,
+      "eval_loss": 0.2743072807788849,
+      "eval_runtime": 2.2589,
+      "eval_samples_per_second": 386.028,
+      "eval_steps_per_second": 24.348,
+      "step": 211
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9094036697247706,
+      "eval_loss": 0.2763120234012604,
+      "eval_runtime": 2.3197,
+      "eval_samples_per_second": 375.903,
+      "eval_steps_per_second": 23.709,
+      "step": 422
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 633,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.665224131389019e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 10
+  }
+}

run-0/checkpoint-422/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:680d0afe4db5f1404c33bdba3d7f7d0610baba4265733865b13f9ea27d8c6125
+size 4920

run-0/checkpoint-633/config.json

@@ -0,0 +1,27 @@
+{
+  "_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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-633/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adbcc302472d25aee76016eb179994f445fcdbd94a26ae33ee417737b2f5dc9b
+size 437958648

run-0/checkpoint-633/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa419d3e2cf49798269dc18b08ca0f492d09580853ffba9b473fecf41de341c7
+size 876038394

run-0/checkpoint-633/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3877bc20881a028fb8f0f3c4014095e41b9ae91f5f5656d3162e66e6f23c0c7
+size 14180

run-0/checkpoint-633/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f4469f8244b171b3822666a91cc34d1dc6eb7f612e61ea627b06b4baa6d2b9f
+size 1064

run-0/checkpoint-633/special_tokens_map.json

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

run-0/checkpoint-633/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-633/trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_metric": 0.9094036697247706,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-0/checkpoint-422",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 633,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9071100917431193,
+      "eval_loss": 0.2743072807788849,
+      "eval_runtime": 2.2589,
+      "eval_samples_per_second": 386.028,
+      "eval_steps_per_second": 24.348,
+      "step": 211
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9094036697247706,
+      "eval_loss": 0.2763120234012604,
+      "eval_runtime": 2.3197,
+      "eval_samples_per_second": 375.903,
+      "eval_steps_per_second": 23.709,
+      "step": 422
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 7.35267448425293,
+      "learning_rate": 1.4004341381907418e-05,
+      "loss": 0.2085,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9071100917431193,
+      "eval_loss": 0.39031100273132324,
+      "eval_runtime": 2.3726,
+      "eval_samples_per_second": 367.532,
+      "eval_steps_per_second": 23.181,
+      "step": 633
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 633,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 519273306636840.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.665224131389019e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 10
+  }
+}

run-0/checkpoint-633/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:680d0afe4db5f1404c33bdba3d7f7d0610baba4265733865b13f9ea27d8c6125
+size 4920

runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709497243.90708aaa767a.21824.18

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c93d2055202f0bee200388bb3437595708e32c4cc565b30e72de7745355f7425
+size 11016

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ade228fc6bd95046697574a73a36f3413a1273363ebbb392ad60a58f2443b9d
+oid sha256:680d0afe4db5f1404c33bdba3d7f7d0610baba4265733865b13f9ea27d8c6125
 size 4920