Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e7e74868654b993ea9b59b117dcdd6c602d3ee692e09583dfc6dc14e7ba5e72
+oid sha256:2f3a65a7477a21db36dcbf2d5752d9bdbcc3bee0e40fe3004dc3616fdaaf9a08
 size 267832560

run-0/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": "4.39.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f3a65a7477a21db36dcbf2d5752d9bdbcc3bee0e40fe3004dc3616fdaaf9a08
+size 267832560

run-0/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a863ccaed9a575049fa22dccdaad62f914ab8b2e7ca03e3da953dc5c1f8961b
+size 535727290

run-0/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e4cad68f538e322f5ad28e53ea5dc75b8b122dffa1e894f8e631e297c02125d
+size 14244

run-0/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f46335807fb3c3b8dd52b3f8533958f3e75fa6c6f986434c51b5d13b44cdaac4
+size 1064

run-0/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-0/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-0/checkpoint-1069/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/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": 2.2928521633148193,
+      "learning_rate": 1.0665121638169595e-06,
+      "loss": 0.6218,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.819956302642822,
+      "learning_rate": 1.2933100053316384e-07,
+      "loss": 0.5768,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5835884809494019,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7311,
+      "eval_samples_per_second": 1426.684,
+      "eval_steps_per_second": 90.279,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1069,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 37738719995232.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.0036933271007554e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 8,
+    "seed": 19
+  }
+}

run-0/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:727176614698c5d84cb95b37956c558dcf7630b375c8982be4e01d2871afd993
+size 4984

runs/Mar23_02-09-13_2ed998b56e2c/events.out.tfevents.1711160662.2ed998b56e2c.195.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6747518e7fe6fca5a0ede58ed662b28970a683a35f3381d51cfb0b4aa0195da
+size 5703

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:254308fabb0f969e7a9ba51f77537cb9e571b6ba5e40b847f536496fbb3917f9
+oid sha256:727176614698c5d84cb95b37956c558dcf7630b375c8982be4e01d2871afd993
 size 4984