Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b60f5d2c0ab42107b330cf0bb13ccc15f664fa6dc3f068acb29f8e2d6243080
+oid sha256:570f33fd3437d19cc4711819c099674b6495be50237802d889d1b6f0dce5be1a
 size 267832560

run-9/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": "4.38.2",
+  "vocab_size": 30522
+}

run-9/checkpoint-535/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:570f33fd3437d19cc4711819c099674b6495be50237802d889d1b6f0dce5be1a
+size 267832560

run-9/checkpoint-535/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1065a37735b8ea9bebe0ec01933a3eae589af35ca0590bb06e244edec384ee06
+size 535727290

run-9/checkpoint-535/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd167220cd9f8dbbbfe17cb4b8c345df359bf6e802f005676825db707f99bd1a
+size 14308

run-9/checkpoint-535/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dd9dbf6166deed40f6ccdff9dce94c8a727672fd057857df89f24a345d202e6
+size 1064

run-9/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-9/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": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-9/checkpoint-535/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.4231731541032522,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/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": 0.93,
+      "grad_norm": 6.980520248413086,
+      "learning_rate": 7.782049038693399e-06,
+      "loss": 0.5402,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4980236887931824,
+      "eval_matthews_correlation": 0.4231731541032522,
+      "eval_runtime": 0.7267,
+      "eval_samples_per_second": 1435.197,
+      "eval_steps_per_second": 90.818,
+      "step": 535
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 144718821953964.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.571025829197629e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 8
+  }
+}

run-9/checkpoint-535/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c289996e2ed3e1b9aa468dfb4eacc49dd75a813d83501c87f1aa7287a09181e
+size 4984

runs/Mar16_01-46-29_6e5f088ca464/events.out.tfevents.1710555587.6e5f088ca464.226.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb6b147ef11735d2fe5d5ed12ebb303136dba3d22fb5e50a1fd351c649d4ac6
+size 4925

runs/Mar16_01-46-29_6e5f088ca464/events.out.tfevents.1710555612.6e5f088ca464.226.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2382f165f3a0a0d9f48785ceab13b33bb2fbc3c2c06f85c2b4c522e490720f44
+size 4925

runs/Mar16_01-46-29_6e5f088ca464/events.out.tfevents.1710555636.6e5f088ca464.226.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:965810f73ce21c2babc4d8c2496b8ee17124a1de54d4a0fd8946502b8e22c92b
+size 5680

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1c579802743ec5bde7ffe4a1b22c8900fae6cd071e374192c2957c3eec29367
+oid sha256:7c289996e2ed3e1b9aa468dfb4eacc49dd75a813d83501c87f1aa7287a09181e
 size 4984