Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34e903f2ddddbb3ea29f07347937996826dd466a343733e40a5133407822dc23
+oid sha256:5f87e5de965aacfc03e62911d782a5a797f6acd6b46e24bcbee37c7c69b4cd82
 size 267832560

run-0/checkpoint-535/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": "4.48.3",
+  "vocab_size": 30522
+}

run-0/checkpoint-535/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f87e5de965aacfc03e62911d782a5a797f6acd6b46e24bcbee37c7c69b4cd82
+size 267832560

run-0/checkpoint-535/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9dc066cf5552d47fb50a073088140793d0ddd38e3c84f918195ae145ee0dfbc
+size 535727290

run-0/checkpoint-535/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ffb3f60df81b69d11b676e27e5d2b594801fe8b95b6f48470b8cbbcd625ea52
+size 14308

run-0/checkpoint-535/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e688bdd997e2216f29fb7abf2014eb8dc567c728f530bec835cd1535a2b90bc5
+size 1064

run-0/checkpoint-535/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-535/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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-535/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.22205460292245263,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-535",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 535,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9345794392523364,
+      "grad_norm": 4.322480201721191,
+      "learning_rate": 3.996235251374436e-07,
+      "loss": 0.5728,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.548197865486145,
+      "eval_matthews_correlation": 0.22205460292245263,
+      "eval_runtime": 0.8306,
+      "eval_samples_per_second": 1255.698,
+      "eval_steps_per_second": 79.459,
+      "step": 535
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 535,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 42861482677632.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.108531027100924e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 16,
+    "seed": 26
+  }
+}

run-0/checkpoint-535/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c53328c8b7b16986b40eadb885a9ea389d679affb4b315b92d72fef5535ca53
+size 5432

runs/Mar20_11-54-05_c50c1849b8cd/events.out.tfevents.1742472052.c50c1849b8cd.231.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ccf76fcb77cdc0f4a48c4076a246a218703a19328b6a57ab83469da21af0eb
+size 5936

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c00ae8335afbb7d6711692ca706c5271b58d5baa721269698a2f08169e2f2364
+oid sha256:9c53328c8b7b16986b40eadb885a9ea389d679affb4b315b92d72fef5535ca53
 size 5432