Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b22416acb57a20c87e73624357cf69b4784a4756ae3263dd6d5e6f0f9dc3628
+oid sha256:2e2137cd6dae0095fd7ade4b342667694adb6462949382ea7db824bc80b8cd04
 size 267832560

run-2/checkpoint-8552/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-2/checkpoint-8552/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e2137cd6dae0095fd7ade4b342667694adb6462949382ea7db824bc80b8cd04
+size 267832560

run-2/checkpoint-8552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f2366675a0093e7a55dbc20d5ea4d9e3f6fb2e5b082660c86272f2884d7a7e
+size 535727290

run-2/checkpoint-8552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e045e82e93d9055d857764b5860c82d59187eb9b8d62c054e239387a096e84d
+size 14308

run-2/checkpoint-8552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fe174ad3adc7449150104cf4c2032f2103fd559a8dc343a28115bb6c8abcd6c
+size 1064

run-2/checkpoint-8552/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-8552/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-8552/trainer_state.json

@@ -0,0 +1,164 @@
+{
+  "best_metric": 0.33508616900126137,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-8552",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 8552,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 5.6188127124741755e-05,
+      "loss": 0.6368,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.269904819250494e-05,
+      "loss": 0.6054,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.920996926026812e-05,
+      "loss": 0.6131,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.57208903280313e-05,
+      "loss": 0.5971,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6043549180030823,
+      "eval_matthews_correlation": 0.16979966395795365,
+      "eval_runtime": 0.8177,
+      "eval_samples_per_second": 1275.601,
+      "eval_steps_per_second": 80.719,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 4.2231811395794476e-05,
+      "loss": 0.5802,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 3.874273246355766e-05,
+      "loss": 0.5465,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 3.525365353132083e-05,
+      "loss": 0.575,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.1764574599084014e-05,
+      "loss": 0.56,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8283206820487976,
+      "eval_matthews_correlation": 0.3112801106717032,
+      "eval_runtime": 0.7366,
+      "eval_samples_per_second": 1416.049,
+      "eval_steps_per_second": 89.606,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 2.8275495666847193e-05,
+      "loss": 0.4468,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.4786416734610375e-05,
+      "loss": 0.4467,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 2.1297337802373553e-05,
+      "loss": 0.4318,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.7808258870136732e-05,
+      "loss": 0.4282,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.206721544265747,
+      "eval_matthews_correlation": 0.3321332844589781,
+      "eval_runtime": 0.7912,
+      "eval_samples_per_second": 1318.307,
+      "eval_steps_per_second": 83.421,
+      "step": 6414
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 1.4319179937899912e-05,
+      "loss": 0.3788,
+      "step": 6500
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 1.083010100566309e-05,
+      "loss": 0.2532,
+      "step": 7000
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 7.341022073426271e-06,
+      "loss": 0.2491,
+      "step": 7500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 3.85194314118945e-06,
+      "loss": 0.2683,
+      "step": 8000
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 3.6286420895262934e-07,
+      "loss": 0.2636,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.352795124053955,
+      "eval_matthews_correlation": 0.33508616900126137,
+      "eval_runtime": 0.7254,
+      "eval_samples_per_second": 1437.829,
+      "eval_steps_per_second": 90.984,
+      "step": 8552
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 138798926351136.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.967720605697858e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 37
+  }
+}

run-2/checkpoint-8552/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4cd2fef8507de0b6ec4fc6f0e972dd20ee83952ed9d6116f7f100b26d2a1eca
+size 4792

runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703298770.04248f4b0c3a.492.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c223c52fd94e287fce08c411c90961041b8eb2806c1644da7f58786c5202535
-size 7553
+oid sha256:9ddfeeda5471614321309151dfb7ef2a605f36580770155476e8a210ab8280a0
+size 8713