Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4a449f5ba8d475db833357bb2a8e66d95f049863cfcf9a02e6b387a5e18218e
+oid sha256:fd8b5a5907d61f119e37cb48d5085a194789fe19c47f09c0950ee7254b10c53b
 size 267832560

run-0/checkpoint-3207/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": "4.35.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-3207/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd8b5a5907d61f119e37cb48d5085a194789fe19c47f09c0950ee7254b10c53b
+size 267832560

run-0/checkpoint-3207/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:517170c57b9be3696da3dd842a49bd5336ec92bc76d685ea7ccaefdb308aa19b
+size 535727290

run-0/checkpoint-3207/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86d21d26c9cb146bee42e59ef53f8aa2fcf92189b222d0f5ca339b6dbf1f9b6
+size 14244

run-0/checkpoint-3207/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c6ff343cdc8c697c60c82591ed7de93723747ee6e3240097235400049bd0d1f
+size 1064

run-0/checkpoint-3207/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-3207/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-3207/trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_metric": 0.166651669293941,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-3207",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3207,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.447053301406701e-07,
+      "loss": 0.6327,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 7.702122880016472e-07,
+      "loss": 0.5907,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5891121625900269,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6963,
+      "eval_samples_per_second": 1497.889,
+      "eval_steps_per_second": 94.785,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 5.957192458626242e-07,
+      "loss": 0.5573,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 4.2122620372360136e-07,
+      "loss": 0.5487,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.55595862865448,
+      "eval_matthews_correlation": 0.12300105566407585,
+      "eval_runtime": 0.7049,
+      "eval_samples_per_second": 1479.688,
+      "eval_steps_per_second": 93.633,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.4673316158457843e-07,
+      "loss": 0.5211,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 7.22401194455555e-08,
+      "loss": 0.5205,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.55258709192276,
+      "eval_matthews_correlation": 0.166651669293941,
+      "eval_runtime": 1.1749,
+      "eval_samples_per_second": 887.771,
+      "eval_steps_per_second": 56.177,
+      "step": 3207
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3207,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 113236081840572.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.119198372279693e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 19
+  }
+}

run-0/checkpoint-3207/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2697eed6b7ac5cb3358c6f6a74efea40e321a5f5e6bfffafbe5f4a6b261625ae
+size 4664

runs/Nov17_02-59-16_faa202bf7ecf/events.out.tfevents.1700190571.faa202bf7ecf.336.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f155c18af0285c152c956fef7fe5073933f922b89dae2fd493a2d49a35e2ad8
-size 5534
+oid sha256:787b836378ef56ce91021ff4a2258c6211ff40bbb27d1faf420e55be521c94db
+size 6537