Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fcc3078778018654e2d37dc852896d3f7aa614916fede5b44302569095d055f
+oid sha256:cb7c176eac5dc5a2c35c28b2d3cd62510d871dd5fcfd98c9141c58170e5addf7
 size 267832560

run-0/checkpoint-535/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": "4.35.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-535/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb7c176eac5dc5a2c35c28b2d3cd62510d871dd5fcfd98c9141c58170e5addf7
+size 267832560

run-0/checkpoint-535/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56453b5a619c9ccb6d518ca017c3cc843bb60b15f8df40edee2455815b116ccb
+size 535724410

run-0/checkpoint-535/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a1ed7b9f426d46e61952f5d5041116eb1b0f8546be42ba235d3ee8b5b31d74
+size 14054

run-0/checkpoint-535/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1dc0e17f7e272a78b6af66ce2bb33383cab4836d40792934c1b2787bb5d6aea
+size 1064

run-0/checkpoint-535/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-535/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-0/checkpoint-535/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-535",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 535,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 9.212400120037402e-07,
+      "loss": 0.6099,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.594454824924469,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 36.4602,
+      "eval_samples_per_second": 28.607,
+      "eval_steps_per_second": 1.81,
+      "step": 535
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1605,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 54041524143888.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3380906961683286e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 14
+  }
+}

run-0/checkpoint-535/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:423290cba7635e78e720e265a2f901ed8603d916cf30d17897498298f0982346
+size 4664

runs/Dec27_12-01-37_e619de3c5f04/events.out.tfevents.1703678719.e619de3c5f04.301.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a791ccb90ccaa99a2acdffd61d17d41875098c7de0433b201e247555bf0da6cb
+size 37496

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1754e9b07586701e7998b97a5364fa655ad1819c13e54629225b2c9384dd4415
+oid sha256:423290cba7635e78e720e265a2f901ed8603d916cf30d17897498298f0982346
 size 4664