Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a68461a17fd4260acf9ef0fa76418a9e4c92faffa45aa6228266734d0963c61
+oid sha256:9819857e5b94358c5b4c02429a2f6b84a0a0ba1167d39ec8803f97c328e8cb96
 size 267832560

run-1/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": "4.36.0",
+  "vocab_size": 30522
+}

run-1/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9819857e5b94358c5b4c02429a2f6b84a0a0ba1167d39ec8803f97c328e8cb96
+size 267832560

run-1/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a89f0116ebaae00ea14e0dc6a3de7398f809cd032b5e26a530027fc30430010
+size 535724410

run-1/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f7c5997f0d0a9b1184444452aaca0fb230c4e372594fbeff95b0d0a83f0b1eb
+size 13990

run-1/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19440e8b0cb3a1e5f9f5731e60296f94beff3a8ac9261f0fc64bec1bbd703d44
+size 1064

run-1/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-1/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-1/checkpoint-1069/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.3761493028688064,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola\\run-1\\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,
+      "learning_rate": 3.7377726667731875e-06,
+      "loss": 0.5753,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.5326241477565903e-07,
+      "loss": 0.5132,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5310395359992981,
+      "eval_matthews_correlation": 0.3761493028688064,
+      "eval_runtime": 6.3497,
+      "eval_samples_per_second": 164.259,
+      "eval_steps_per_second": 10.394,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1069,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 37616601612096.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.022282918770717e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 8,
+    "seed": 2
+  }
+}

run-1/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:251a6809d9e26b83d6d57987d9d22eeb36a4aa34b08775dd41cc8088a9ae250c
+size 4792

runs/Dec12_14-52-17_DESKTOP-UUVDD26/events.out.tfevents.1702383820.DESKTOP-UUVDD26.9476.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:001280eecd66055163d1d4d36954af69534db354a1b65605f310167fd4d9c296
+size 5337

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12cc95a7867972a8a3e5df6082d22b5af5d6d813216b363e3dca2eafb740bdec
+oid sha256:251a6809d9e26b83d6d57987d9d22eeb36a4aa34b08775dd41cc8088a9ae250c
 size 4792