Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d65ea46da3ca47cefe8a2cfbf43b46848a5b1fb2abf441bba7be1bd6ffc4aaaf
+oid sha256:7ab0e4b0ed38643fb83b8bb8ab9ba2c04c04a9cd009e9bfa4385a0dfd9b33b27
 size 267832560

run-1/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": "4.40.0",
+  "vocab_size": 30522
+}

run-1/checkpoint-535/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab0e4b0ed38643fb83b8bb8ab9ba2c04c04a9cd009e9bfa4385a0dfd9b33b27
+size 267832560

run-1/checkpoint-535/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54012c7318d9313eeb4a6bd349db9a07e87ef4c96c971819d2eb81ce52e994f5
+size 535724410

run-1/checkpoint-535/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a16a911bfad796caa2cc14884e0ffa417dbd68fb750729872f0da2e692f38d1
+size 14054

run-1/checkpoint-535/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ea125037157b9855d8b3056a7349c7a6896c196053166c53c5a1996476b339
+size 1064

run-1/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-1/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": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-535/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.46458665505165037,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/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": 0.9345794392523364,
+      "grad_norm": 5.241539001464844,
+      "learning_rate": 2.0642859465572347e-05,
+      "loss": 0.5172,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4695243239402771,
+      "eval_matthews_correlation": 0.46458665505165037,
+      "eval_runtime": 34.1313,
+      "eval_samples_per_second": 30.558,
+      "eval_steps_per_second": 1.934,
+      "step": 535
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 43027066925952.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.693641418068587e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 20
+  }
+}

run-1/checkpoint-535/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd22865ae20aa547bc48d25549f90f12defd8e920333d535e7df0f311b74e33
+size 5048

runs/Apr23_01-32-54_2e24b0ee9d48/events.out.tfevents.1713846388.2e24b0ee9d48.45752.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48923b117dc033c30aa494316d075b7447036366eebf4c54af083e6671754602
+size 5196

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef3851731c9251ecf7b27e7c164fec575b150a35fa273ebb279f85322b83ff1b
+oid sha256:5cd22865ae20aa547bc48d25549f90f12defd8e920333d535e7df0f311b74e33
 size 5048