Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a02434c65736d0a8fcec4a8cb7e73842f4f322531971a14d1bd7374a916d5716
+oid sha256:aca276b3a4b8c7e7cef998620d0f17620ec3d47601c1f8af36947609f269c625
 size 267832560

run-2/checkpoint-28/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": "4.38.1",
+  "vocab_size": 30522
+}

run-2/checkpoint-28/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ef86be4b5b724d481c59930823cfdbed5a969f442d5b9d1e2b2296110c5ea35
+size 267832560

run-2/checkpoint-28/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bfba6f33bad60f824c0de9d5a7528aaf2e41cb4b70f6e13637aff215c07cf02
+size 535727290

run-2/checkpoint-28/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1482ff7d867e95230bcf08276f0feafcfcd22bd2d57489974af2ee40af69273d
+size 14244

run-2/checkpoint-28/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2291ed785eae639dfbb8366b7a4a295b6713b746f4041579d4d817a2f6aafdae
+size 1064

run-2/checkpoint-28/special_tokens_map.json

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

run-2/checkpoint-28/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-2/checkpoint-28/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-14",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 28,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6130949854850769,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8143,
+      "eval_samples_per_second": 1280.789,
+      "eval_steps_per_second": 81.047,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5834124088287354,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7766,
+      "eval_samples_per_second": 1343.102,
+      "eval_steps_per_second": 84.99,
+      "step": 28
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 56,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.734214749417639e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "seed": 19
+  }
+}

run-2/checkpoint-28/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29cb90bd1c8e46e5757d6712e23ef509a5498348487b496f7195b93b5b09254f
+size 4984

run-2/checkpoint-42/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": "4.38.1",
+  "vocab_size": 30522
+}

run-2/checkpoint-42/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6bb49e37d3645160e304dd9ed40efc26383947acc9a8a00b3677328594be8a
+size 267832560

run-2/checkpoint-42/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2124724d256f9d19ec99b7c99f98babe70abcd4db9061f4b576fc5e5dcfd8545
+size 535727290

run-2/checkpoint-42/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5abc52a4130c42e33a96c83eaee571adb8101f155c351a3716656999d5d3c06a
+size 14244

run-2/checkpoint-42/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f69e76f576214ab76eba53dfba3602b3b6710c9f34df7c742742ce1bf5476535
+size 1064

run-2/checkpoint-42/special_tokens_map.json

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

run-2/checkpoint-42/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-2/checkpoint-42/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.1077683109552469,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-42",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 42,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6130949854850769,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8143,
+      "eval_samples_per_second": 1280.789,
+      "eval_steps_per_second": 81.047,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5834124088287354,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7766,
+      "eval_samples_per_second": 1343.102,
+      "eval_steps_per_second": 84.99,
+      "step": 28
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5700901746749878,
+      "eval_matthews_correlation": 0.1077683109552469,
+      "eval_runtime": 0.757,
+      "eval_samples_per_second": 1377.871,
+      "eval_steps_per_second": 87.19,
+      "step": 42
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 56,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.734214749417639e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "seed": 19
+  }
+}

run-2/checkpoint-42/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29cb90bd1c8e46e5757d6712e23ef509a5498348487b496f7195b93b5b09254f
+size 4984

run-2/checkpoint-56/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": "4.38.1",
+  "vocab_size": 30522
+}

run-2/checkpoint-56/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:300dfd172836da805b4b4419e24287ae095aac3e0ce6d2b55ed586ac2a9c9567
+size 267832560

run-2/checkpoint-56/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a6a07fc94af83e7d70cffdb6890ad00f414d262031b71540b897f9e7ea952d
+size 535727290

run-2/checkpoint-56/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9373b63c15530f5ce87b21b804bf3fe2f3a8ce3aa9e4e84dc90de015499222cd
+size 14244

run-2/checkpoint-56/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5515a2243b266a87393cb8d7e211d1a288de2412729cf8017416db2098a2010f
+size 1064

run-2/checkpoint-56/special_tokens_map.json

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

run-2/checkpoint-56/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-2/checkpoint-56/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.2047253529986547,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-56",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 56,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6130949854850769,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.8143,
+      "eval_samples_per_second": 1280.789,
+      "eval_steps_per_second": 81.047,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5834124088287354,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7766,
+      "eval_samples_per_second": 1343.102,
+      "eval_steps_per_second": 84.99,
+      "step": 28
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5700901746749878,
+      "eval_matthews_correlation": 0.1077683109552469,
+      "eval_runtime": 0.757,
+      "eval_samples_per_second": 1377.871,
+      "eval_steps_per_second": 87.19,
+      "step": 42
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5696095824241638,
+      "eval_matthews_correlation": 0.2047253529986547,
+      "eval_runtime": 0.7553,
+      "eval_samples_per_second": 1380.933,
+      "eval_steps_per_second": 87.384,
+      "step": 56
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 56,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.734214749417639e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "seed": 19
+  }
+}

run-2/checkpoint-56/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29cb90bd1c8e46e5757d6712e23ef509a5498348487b496f7195b93b5b09254f
+size 4984

run-3/checkpoint-54/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53b33baef0bea3902415cbe62ff3428010bfd76b7efaf578366db2e39d4c63fe
+oid sha256:aca276b3a4b8c7e7cef998620d0f17620ec3d47601c1f8af36947609f269c625
 size 267832560

run-3/checkpoint-54/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ba4ee5be72cb4143caa2897f77410566fac806e168f6570dc7c4d66e9714a49
+oid sha256:6401775af83abf126a160d2cfc9e0e2303a11944ad92d959d8004d1fa618c33d
 size 535727290

run-3/checkpoint-54/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:369d7b80e9e7cb856d382ef6a50ec190c9ca9a8950f95fb694f8f1fdbb7c9fee
+oid sha256:156dca70f156dd4e17a1e78e5ba6c0e3ab4d562ab9db28a63fdbcdc968ddbcf4
 size 14244

run-3/checkpoint-54/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a4d5fbaa446412f6bcebdfe4c617fc227241fb97546e88f3710b5383a973030
+oid sha256:09742c40c0b0fc632f552b168c574d3599cb4037e9a7ec27c91a0871f9cd5d45
 size 1064

run-3/checkpoint-54/trainer_state.json

@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6117144227027893,
+      "eval_loss": 0.5995345115661621,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.7419,
-      "eval_samples_per_second": 1405.842,
-      "eval_steps_per_second": 88.96,
+      "eval_runtime": 0.783,
+      "eval_samples_per_second": 1331.991,
+      "eval_steps_per_second": 84.287,
       "step": 54
     }
   ],
   "logging_steps": 500,
-  "max_steps": 108,
+  "max_steps": 54,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 1,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 5.958113215910997e-06,
-    "num_train_epochs": 2,
+    "learning_rate": 4.7309844765404436e-05,
+    "num_train_epochs": 1,
     "per_device_train_batch_size": 16,
-    "seed": 27
+    "seed": 34
   }
 }

run-3/checkpoint-54/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eea09312c033855fe12d8be695636b10f5eef7899140e17c043550da69ed873
+oid sha256:9d804e24fd3fc8f787c7ef6343fa1d0a212d37f7b1d74ed48cff69d4655e8f4d
 size 4984

runs/Feb28_19-52-39_5620ed9b2fff/events.out.tfevents.1709151080.5620ed9b2fff.209.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12310dbe68123a3b4be1c11605d7aac756c468d2fe6975721b6426b04d3dcf80
+size 5220

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29cb90bd1c8e46e5757d6712e23ef509a5498348487b496f7195b93b5b09254f
+oid sha256:9d804e24fd3fc8f787c7ef6343fa1d0a212d37f7b1d74ed48cff69d4655e8f4d
 size 4984