Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d06c385e1a84e2a270f11e7dc4bf44f69a4565004eb7a1df5ec287026f4de1
+oid sha256:cb02cd90731f9a42920c5193dfd51446a2461ba40a8482cbe55e3dea1b535e21
 size 267832560

run-3/checkpoint-4276/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": "4.38.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb02cd90731f9a42920c5193dfd51446a2461ba40a8482cbe55e3dea1b535e21
+size 267832560

run-3/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8df89a6e62e704a896790dba214f2b58f13d806298edcceccdda1cb5712d485
+size 535727290

run-3/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93774b3571050b1d9cd6fac463058780297d650078a769c6540ec42aa37e5d79
+size 14180

run-3/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63eddf5ba8e534b318e9601bb10e82c9f53a6d1ec228d39e22ac3c151ac30cd0
+size 1064

run-3/checkpoint-4276/special_tokens_map.json

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

run-3/checkpoint-4276/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-3/checkpoint-4276/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.5422278243727644,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-4276",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 11.004450798034668,
+      "learning_rate": 2.0214687462514598e-05,
+      "loss": 0.598,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 15.662084579467773,
+      "learning_rate": 1.8959428678205447e-05,
+      "loss": 0.5617,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 28.870677947998047,
+      "learning_rate": 1.7704169893896296e-05,
+      "loss": 0.5375,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 64.57504272460938,
+      "learning_rate": 1.6448911109587142e-05,
+      "loss": 0.5691,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5517680048942566,
+      "eval_matthews_correlation": 0.4384136507504086,
+      "eval_runtime": 0.737,
+      "eval_samples_per_second": 1415.216,
+      "eval_steps_per_second": 89.553,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 25.73099708557129,
+      "learning_rate": 1.5193652325277987e-05,
+      "loss": 0.4513,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 63.40884017944336,
+      "learning_rate": 1.3938393540968835e-05,
+      "loss": 0.442,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.524051308631897,
+      "learning_rate": 1.268313475665968e-05,
+      "loss": 0.4237,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 135.24822998046875,
+      "learning_rate": 1.1427875972350528e-05,
+      "loss": 0.4295,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7380757331848145,
+      "eval_matthews_correlation": 0.5422278243727644,
+      "eval_runtime": 0.7356,
+      "eval_samples_per_second": 1417.881,
+      "eval_steps_per_second": 89.722,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 65295043620336.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.1469946246823753e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 10
+  }
+}

run-3/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5794c39e5f32d9d04daa3a15f6f00d81e0613156566c68faaedd5643205dda11
+size 4984

runs/Mar03_19-18-26_abc5bcbabcce/events.out.tfevents.1709494143.abc5bcbabcce.1176.32

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bef60206c6309027c562d6836a66fa7352e0aeb3aeaaa91f2ca5bf45a7d87dfa
-size 6354
+oid sha256:4ef10902572a9e8bc58061d93b444a9fd7699d9e05e51bd5a1d3bc1c9021b925
+size 7744