Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d04b93d9e24d7d905b8a7942556d3e47936cc03d1e123cfd363fbc95781fffb
+oid sha256:6f0b11a066b5b85812fc06a84ae4968da5eacdbd054d62f07b18f68dc3bc0151
 size 267832560

run-9/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": "4.36.2",
+  "vocab_size": 30522
+}

run-9/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f0b11a066b5b85812fc06a84ae4968da5eacdbd054d62f07b18f68dc3bc0151
+size 267832560

run-9/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9547971cf0a30effaf5c58b66ff3b798e291f392d244473c91d27a5e83c62aed
+size 535727290

run-9/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c182ca6ae22418584e7aa6949cbeff2730f31b3581b751c3b24c1536848c2b84
+size 14308

run-9/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c2b6966ee2b5722c7d5cc4228d64babca1127cfde86c4d941dae9a55e7aa858
+size 1064

run-9/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-9/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-9/checkpoint-1069/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.4691032179514943,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/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": 0.47,
+      "learning_rate": 1.942054911488753e-05,
+      "loss": 0.5525,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5833451014612775e-05,
+      "loss": 0.4922,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4696793258190155,
+      "eval_matthews_correlation": 0.4691032179514943,
+      "eval_runtime": 0.7564,
+      "eval_samples_per_second": 1378.966,
+      "eval_steps_per_second": 87.26,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3207,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 96605213899932.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.3007647215162288e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 14
+  }
+}

run-9/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca0d14927e03b866cc3e1bf18d0c09980fa2cb73785088015390dc1d85c1cbc
+size 4792

runs/Dec23_01-55-51_48296f50e732/events.out.tfevents.1703298848.48296f50e732.508.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303ae5fe1d1e34f85eab49cebbf4024fc6925146ab55c600039a7e75cd8121f1
+size 4837

runs/Dec23_01-55-51_48296f50e732/events.out.tfevents.1703298878.48296f50e732.508.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:262d0b19b357e9f9091be5b955f6fd9a33b4d4580ddd79e8d2ed3d14e5689d1e
+size 4680

runs/Dec23_01-55-51_48296f50e732/events.out.tfevents.1703298900.48296f50e732.508.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c2b46a21ef7a6aa044a5a25cdda8b056ad3f31648416f6cdeb722296163f1c2
+size 4839

runs/Dec23_01-55-51_48296f50e732/events.out.tfevents.1703298931.48296f50e732.508.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cf6621369e9f9489598e6987761474eb7bf1d5109da4bc4db4f69b8f33294f8
+size 4681

runs/Dec23_01-55-51_48296f50e732/events.out.tfevents.1703298952.48296f50e732.508.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d482aaf6c80aab8d29bb2ddc527fa8b8e82210695f8ccca74b13b541e5e0ab77
+size 5801

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ac1bf1a268ec975a9893d08fff7fe9454bf7cf07eeccb26ed7bf0dc25e351a
+oid sha256:dca0d14927e03b866cc3e1bf18d0c09980fa2cb73785088015390dc1d85c1cbc
 size 4792