Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68d7b025cfe4c7609290a3a91491ccce0de450695fc5b01777659765de971b39
+oid sha256:0534ba13d038dcdc73e4927198cf8c3006b41a95848ae739c42811ebc06d7f6b
 size 267832560

run-5/checkpoint-216/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-5/checkpoint-216/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0534ba13d038dcdc73e4927198cf8c3006b41a95848ae739c42811ebc06d7f6b
+size 267832560

run-5/checkpoint-216/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a655672b833c6da8861cd5fffdd8850c2bb1e5a4171da1c99bad3f332be6d4a9
+size 535724410

run-5/checkpoint-216/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35ddb91000198c530ceb6f9aec8394774f978ef46880b6b01e5d2194ae5757d7
+size 13990

run-5/checkpoint-216/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb02bc20d72f1c8718a11eaecc09f6ba7740fe0217b48934b4bed5653e5de6dc
+size 1064

run-5/checkpoint-216/special_tokens_map.json

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

run-5/checkpoint-216/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-5/checkpoint-216/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.3215566034550075,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-162",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 216,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.575078010559082,
+      "eval_matthews_correlation": 0.06354272869611655,
+      "eval_runtime": 9.5691,
+      "eval_samples_per_second": 108.997,
+      "eval_steps_per_second": 6.897,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8100215196609497,
+      "eval_matthews_correlation": 0.24720569658796848,
+      "eval_runtime": 8.7353,
+      "eval_samples_per_second": 119.401,
+      "eval_steps_per_second": 7.556,
+      "step": 108
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.1307350397109985,
+      "eval_matthews_correlation": 0.3215566034550075,
+      "eval_runtime": 9.5213,
+      "eval_samples_per_second": 109.544,
+      "eval_steps_per_second": 6.932,
+      "step": 162
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.204452395439148,
+      "eval_matthews_correlation": 0.31355901616800796,
+      "eval_runtime": 9.7181,
+      "eval_samples_per_second": 107.325,
+      "eval_steps_per_second": 6.791,
+      "step": 216
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.264714442689283e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 3
+  }
+}

run-5/checkpoint-216/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72f05c17e403bd7c83492cd9bde59416cc3d083d7287b9aa74879ea431332404
+size 4984

runs/Mar06_18-56-30_6942db43b48a/events.out.tfevents.1709754047.6942db43b48a.1479.7

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d3848c836943d020c822135d109e167edb0c27a5649cfbbd8af0eb1f28cc08
-size 5534
+oid sha256:7b7cb8ba196ea680de33b08979949235a3cdc7b41de4f0084bc2fbef8c211322
+size 6223