Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eab2f1862b02176ffde3eec6507bb84c6f9762c42530fcfaa2dd7877f4f9a51
+oid sha256:82678ebe8af8189e1da2ce84e198a2a9348046c4721b43b1097b9905720b99e6
 size 267832560

run-2/checkpoint-2140/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-2/checkpoint-2140/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82678ebe8af8189e1da2ce84e198a2a9348046c4721b43b1097b9905720b99e6
+size 267832560

run-2/checkpoint-2140/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ac30c144d0b577fe6ad970c8f1d38a85ae4789f64cb4c09d037bf4ad84ffbe
+size 535724410

run-2/checkpoint-2140/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9758a81e4cced6578a6e9299b7b5833438d5e52df5e76fc19a0d89f1058d1ae9
+size 13990

run-2/checkpoint-2140/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df01e86fe7930972d6588f62fc823d117de2ee70dd62b4f944a4bf0529873b5c
+size 1064

run-2/checkpoint-2140/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-2140/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-2/checkpoint-2140/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 0.5141951979542654,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola\\run-2\\checkpoint-1605",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2140,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 7.330426643717586e-06,
+      "loss": 0.5309,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4970090985298157,
+      "eval_matthews_correlation": 0.43624361512112764,
+      "eval_runtime": 6.9324,
+      "eval_samples_per_second": 150.453,
+      "eval_steps_per_second": 9.521,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 5.095540471852468e-06,
+      "loss": 0.4001,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5170313715934753,
+      "eval_matthews_correlation": 0.4414558823469975,
+      "eval_runtime": 6.257,
+      "eval_samples_per_second": 166.694,
+      "eval_steps_per_second": 10.548,
+      "step": 1070
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.8606542999873506e-06,
+      "loss": 0.3288,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.512870192527771,
+      "eval_matthews_correlation": 0.5141951979542654,
+      "eval_runtime": 6.366,
+      "eval_samples_per_second": 163.839,
+      "eval_steps_per_second": 10.368,
+      "step": 1605
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 6.257681281222329e-07,
+      "loss": 0.2647,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5683671236038208,
+      "eval_matthews_correlation": 0.4982331824617808,
+      "eval_runtime": 6.6371,
+      "eval_samples_per_second": 157.146,
+      "eval_steps_per_second": 9.944,
+      "step": 2140
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 171385647695124.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.565312815582705e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 23
+  }
+}

run-2/checkpoint-2140/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6beaf658b5b4cd433d32b468fc202bb7f1bbb1f978347e8cf413c4bb5083790d
+size 4792

runs/Dec12_14-52-17_DESKTOP-UUVDD26/events.out.tfevents.1702384338.DESKTOP-UUVDD26.9476.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a8ebdf42f914bb50c4ef7195e6cbb62aa3b9c1c4a6706fdef76eea1cefee85d
-size 5812
+oid sha256:8f1acc4ce21242563e81c49efacb482095083ebf280158732fd9daec2e3b55ee
+size 6658