Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:450231c4f60ce9bf4704efca28f3d213080726e6ea7fc3f1cf9e896900c6c78f
+oid sha256:3ece9257eae5f80e7eefc99c741b9b50c7f0f5258508f7b5a30317f034a7ccee
 size 267832560

run-6/checkpoint-268/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": "4.44.0",
+  "vocab_size": 30522
+}

run-6/checkpoint-268/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013c04aa340ef41c9374e7905e567557b71d93e104694d7bb9c8216ce5d74693
+size 267832560

run-6/checkpoint-268/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:566fec9aa93b473f70dd3d824a34d0d88d0c42ca5c75264e3ff4e27dcf1ef4fc
+size 535727290

run-6/checkpoint-268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e4d50d736a66a8af24800ffaff167e56b398ac8ed3a0915e799e4ba26ab902c
+size 14244

run-6/checkpoint-268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7086a641d21ec9508bd45a67bd7d87d14ff822e32be7c50619cc1c86d5be14b8
+size 1064

run-6/checkpoint-268/special_tokens_map.json

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

run-6/checkpoint-268/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-6/checkpoint-268/trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 268,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 500,
+  "max_steps": 268,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6346025152713588e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 32,
+    "seed": 25
+  }
+}

run-6/checkpoint-268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ca454c86eaaa647c649f9d93dea6a429ad8e94c8c6adca1348aae7c4fc5f0b
+size 5240

run-7/checkpoint-1069/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": "4.44.0",
+  "vocab_size": 30522
+}

run-7/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf945a4cb72b7f07ea06c29c90ef2dc26fadb9cfd5008c8e15b5640f10cb4dff
+size 267832560

run-7/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:535a306ba7c3590d9d23342f62e0e86236d9597abc9c85c2f15626ded1e7ea98
+size 535727290

run-7/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:991df4aa76f24d91526e7e51a90de580470ee9ff4e3f5336667f187c26f0e6c4
+size 14244

run-7/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75cdd5628239fee0b56334346304f649325520a5cd5a761550cce211c947a457
+size 1064

run-7/checkpoint-1069/special_tokens_map.json

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

run-7/checkpoint-1069/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-7/checkpoint-1069/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": 0.46472372045336796,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-1069",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1069,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 12.974456787109375,
+      "learning_rate": 1.1101348047567246e-05,
+      "loss": 0.5482,
+      "step": 500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 6.763242721557617,
+      "learning_rate": 9.955698094257931e-06,
+      "loss": 0.4949,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.47264614701271057,
+      "eval_matthews_correlation": 0.46472372045336796,
+      "eval_runtime": 0.7997,
+      "eval_samples_per_second": 1304.217,
+      "eval_steps_per_second": 82.53,
+      "step": 1069
+    }
+  ],
+  "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": 145295003393040.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.2246998000876558e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 6
+  }
+}

run-7/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa913b6dd4193043ca75983cebb619f3f12421d16f3812039f1dd107acad34f
+size 5240

run-7/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": "4.44.0",
+  "vocab_size": 30522
+}

run-7/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ece9257eae5f80e7eefc99c741b9b50c7f0f5258508f7b5a30317f034a7ccee
+size 267832560

run-7/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a47526de69f653d290a76d28b0a7c4af7352364bfa71aad91c5b854dfff01fff
+size 535727290

run-7/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90df934dd18ebd7d91cb8acb41efb58fb7d921aa4d2cfcc4238089f367f711f7
+size 14244

run-7/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a07338759d3c36bc9346a7dde55e24b372b8253ea7bb3a52166d4bb3c8c3bc7a
+size 1064

run-7/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-7/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-7/checkpoint-2138/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": 0.5238946707778435,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/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": 12.974456787109375,
+      "learning_rate": 1.1101348047567246e-05,
+      "loss": 0.5482,
+      "step": 500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 6.763242721557617,
+      "learning_rate": 9.955698094257931e-06,
+      "loss": 0.4949,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.47264614701271057,
+      "eval_matthews_correlation": 0.46472372045336796,
+      "eval_runtime": 0.7997,
+      "eval_samples_per_second": 1304.217,
+      "eval_steps_per_second": 82.53,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 21.93242835998535,
+      "learning_rate": 8.810048140948619e-06,
+      "loss": 0.3822,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 23.08902359008789,
+      "learning_rate": 7.664398187639304e-06,
+      "loss": 0.3651,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5118151903152466,
+      "eval_matthews_correlation": 0.5238946707778435,
+      "eval_runtime": 0.7256,
+      "eval_samples_per_second": 1437.525,
+      "eval_steps_per_second": 90.965,
+      "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": 182960762828856.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.2246998000876558e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 6
+  }
+}

run-7/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa913b6dd4193043ca75983cebb619f3f12421d16f3812039f1dd107acad34f
+size 5240

runs/Aug17_02-11-34_b5f02c58e851/events.out.tfevents.1723864031.b5f02c58e851.301.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:205f86dcece1c79246874c4238b329cbcd56b791c2fde0974a4a2412bb8cc178
+size 5233

runs/Aug17_02-11-34_b5f02c58e851/events.out.tfevents.1723864059.b5f02c58e851.301.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e79883f3175656d7cf17931867dfa4f0fcae30f462470ad878ec58cdf2995eb
+size 7924

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f681be37bd049bb3d40730ca6c5cecdc6d069e2b1201b01709d92cce9f6c36a
+oid sha256:6fa913b6dd4193043ca75983cebb619f3f12421d16f3812039f1dd107acad34f
 size 5240