Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f8faef3b23eaff2c363d74cc3e31d0922f626b504dff2127806023ff5ed2cc6
+oid sha256:cd401084e240b26599b364bc4cd915fa2d13a05d016ed53676e6612290d30b94
 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": "4.38.1",
+  "vocab_size": 30522
+}

run-9/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd401084e240b26599b364bc4cd915fa2d13a05d016ed53676e6612290d30b94
+size 267832560

run-9/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23ec0eba1afa1c9ad5d8c6507f13f68bc43659636f4386f25c764b65849497af
+size 535727290

run-9/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0559252c669e30e932c5f9838e7e4093c78bd1b93862edbe7e0544db8e869b58
+size 14308

run-9/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fd7eb391d0346dc71819493c3e416b20987c50fa1c515903d025cd10bbb63b8
+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 +1,49 @@
+{
+  "best_metric": 0.45247851615567836,
+  "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,
+      "grad_norm": 9.726993560791016,
+      "learning_rate": 9.269588012017996e-06,
+      "loss": 0.5455,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 10.481143951416016,
+      "learning_rate": 1.1240800928457676e-06,
+      "loss": 0.4971,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4961969256401062,
+      "eval_matthews_correlation": 0.45247851615567836,
+      "eval_runtime": 0.7351,
+      "eval_samples_per_second": 1418.76,
+      "eval_steps_per_second": 89.778,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1069,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 40086911616720.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.7415095931190226e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 8,
+    "seed": 13
+  }
+}

run-9/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51397c1d4836ad9bf577d2413143dcc9698b175bc18961bf74e3c4f9f3672fd0
+size 4984

runs/Feb25_19-05-35_a56a1d5f314a/events.out.tfevents.1708889449.a56a1d5f314a.1698.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0762179873e7fc15a26ee2ba6676a10e666d5f8a643f2732199ed6650a789638
+size 4877

runs/Feb25_19-05-35_a56a1d5f314a/events.out.tfevents.1708889469.a56a1d5f314a.1698.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df0d721e0f405495b84da6b3435bf993af3fa8a730dcc0283fca37ecbab94571
+size 4877

runs/Feb25_19-05-35_a56a1d5f314a/events.out.tfevents.1708889489.a56a1d5f314a.1698.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76476b639748a1dda5bb313272fd6a84d62ecac62b689da099978d5cbe0de1b8
+size 5721

runs/Feb25_19-05-35_a56a1d5f314a/events.out.tfevents.1708889587.a56a1d5f314a.1698.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce303a9714ef63cb5d7d4486e6bca9e65f3f92ec08dcc04ab43fefeb3c9c34f6
+size 5653

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d175295218833771d122d2b71c545d64b707b653f4659a8fe484f82a8b71d3a1
+oid sha256:51397c1d4836ad9bf577d2413143dcc9698b175bc18961bf74e3c4f9f3672fd0
 size 4984