Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4e118c72b82e97ffb3c6a80958dea43b7b835428b78fe6da62efb35d54bace8
+oid sha256:478aaf865580be976c1bf3c5eec07bef3d438a36bf7d4df88d7e96127ddfc013
 size 267832560

run-4/checkpoint-2138/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "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": "4.42.4",
+  "vocab_size": 30522
+}

run-4/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8968b88443c643810b294e906a95cccc0b6e82be6d596170baa6100dda2e9779
+size 267832560

run-4/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d857aa9d7a098efa6b4159c7dfd06fe97efbd1e5517e059df3bb6acda6ce737
+size 535727290

run-4/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e482e252db8f2a452e6b9d9668677605f33af9fa4d7f2eefd41a816584ace9fc
+size 14244

run-4/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:187a69c5dc96cc9a0c45d5d4d607aa02bd604b003bf5c03f9f50c7770c832fcf
+size 1064

run-4/checkpoint-2138/special_tokens_map.json

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

run-4/checkpoint-2138/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]"
+}

run-4/checkpoint-2138/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": 0.4986084626480731,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-2138",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 13.482518196105957,
+      "learning_rate": 7.034296344775407e-06,
+      "loss": 0.5589,
+      "step": 500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 10.600051879882812,
+      "learning_rate": 6.308362769463187e-06,
+      "loss": 0.5047,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4949962794780731,
+      "eval_matthews_correlation": 0.4219587641967578,
+      "eval_runtime": 0.7754,
+      "eval_samples_per_second": 1345.165,
+      "eval_steps_per_second": 85.121,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 26.401622772216797,
+      "learning_rate": 5.5824291941509675e-06,
+      "loss": 0.3949,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 9.348161697387695,
+      "learning_rate": 4.856495618838748e-06,
+      "loss": 0.3944,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4984108507633209,
+      "eval_matthews_correlation": 0.4986084626480731,
+      "eval_runtime": 0.8094,
+      "eval_samples_per_second": 1288.531,
+      "eval_steps_per_second": 81.537,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 75534618301212.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.760229920087626e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 19
+  }
+}

run-4/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a2336d317662ba45154e97f4a0557ac333eaa4d23cc07df79bd5c651ca7afc
+size 5176

run-4/checkpoint-3207/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "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": "4.42.4",
+  "vocab_size": 30522
+}

run-4/checkpoint-3207/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478aaf865580be976c1bf3c5eec07bef3d438a36bf7d4df88d7e96127ddfc013
+size 267832560

run-4/checkpoint-3207/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66e2858ca1201b2ed226be1b288d195b90eedc842ea54f8682918b0597528491
+size 535727290

run-4/checkpoint-3207/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccaf101abf392c305d53135b94c266994f9fd6c86ea16587beeb86920df637f0
+size 14244

run-4/checkpoint-3207/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b75a735791edec8374bd83239b9ff890ed7d366964c6d9bca2da4204bcd51347
+size 1064

run-4/checkpoint-3207/special_tokens_map.json

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

run-4/checkpoint-3207/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]"
+}

run-4/checkpoint-3207/trainer_state.json

@@ -0,0 +1,107 @@
+{
+  "best_metric": 0.4986084626480731,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-2138",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3207,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 13.482518196105957,
+      "learning_rate": 7.034296344775407e-06,
+      "loss": 0.5589,
+      "step": 500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 10.600051879882812,
+      "learning_rate": 6.308362769463187e-06,
+      "loss": 0.5047,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4949962794780731,
+      "eval_matthews_correlation": 0.4219587641967578,
+      "eval_runtime": 0.7754,
+      "eval_samples_per_second": 1345.165,
+      "eval_steps_per_second": 85.121,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 26.401622772216797,
+      "learning_rate": 5.5824291941509675e-06,
+      "loss": 0.3949,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 9.348161697387695,
+      "learning_rate": 4.856495618838748e-06,
+      "loss": 0.3944,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4984108507633209,
+      "eval_matthews_correlation": 0.4986084626480731,
+      "eval_runtime": 0.8094,
+      "eval_samples_per_second": 1288.531,
+      "eval_steps_per_second": 81.537,
+      "step": 2138
+    },
+    {
+      "epoch": 2.3386342376052385,
+      "grad_norm": 2.740610122680664,
+      "learning_rate": 4.130562043526529e-06,
+      "loss": 0.3296,
+      "step": 2500
+    },
+    {
+      "epoch": 2.8063610851262863,
+      "grad_norm": 64.62920379638672,
+      "learning_rate": 3.4046284682143094e-06,
+      "loss": 0.3363,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6585824489593506,
+      "eval_matthews_correlation": 0.49323508482582806,
+      "eval_runtime": 0.8558,
+      "eval_samples_per_second": 1218.682,
+      "eval_steps_per_second": 77.117,
+      "step": 3207
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 112920436867212.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.760229920087626e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 19
+  }
+}

run-4/checkpoint-3207/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a2336d317662ba45154e97f4a0557ac333eaa4d23cc07df79bd5c651ca7afc
+size 5176

runs/Aug28_15-48-15_c15c80b486ff/events.out.tfevents.1724861871.c15c80b486ff.424.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb3f205068f503eed52fefb1139c14979d27845fcfdefc388291b034bee0762e
-size 6327
+oid sha256:d896fbea04994eac215415073c6696dd692275baba922947b89d854b539dc942
+size 8052