Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35741f9e902b5be55147f3057ff5f19dc876a8ee71e37a455fbfaf2902dc5d35
+oid sha256:904fdbaae30c130b440bd0202b33546417b7ecd72fd7f4e5a5545a7ffe8811a7
 size 437958648

run-4/checkpoint-421/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-4/checkpoint-421/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:904fdbaae30c130b440bd0202b33546417b7ecd72fd7f4e5a5545a7ffe8811a7
+size 437958648

run-4/checkpoint-421/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d737f3ecf18bd40012f1f6ed6fa7bebc0cb44d5e4ebde680c9ad628e68877997
+size 876038394

run-4/checkpoint-421/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab3ab8549c2095201e483feec140ee7795c47512d16dbb6359d3a36be29f1800
+size 14244

run-4/checkpoint-421/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb75b0a6bdfecb8e6375ce9343c5205e8ada8c306d991e61da7bad9e8236616
+size 1064

run-4/checkpoint-421/special_tokens_map.json

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

run-4/checkpoint-421/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-4/checkpoint-421/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.911697247706422,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-4/checkpoint-421",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 421,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.911697247706422,
+      "eval_loss": 0.22564278542995453,
+      "eval_runtime": 2.3507,
+      "eval_samples_per_second": 370.952,
+      "eval_steps_per_second": 23.397,
+      "step": 421
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1684,
+  "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": 1.9332308987714115e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 7
+  }
+}

run-4/checkpoint-421/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ddfa9214cc4a8744b1acb7c736584356b64328d1bba7daa8c13355771e08a2
+size 4920

runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709493006.90708aaa767a.21824.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b39165a1826bde653c99663fd3cb0f008f96fe8f98fc80fbc22d7c7f1f0e367
+size 5158

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cce3c6e72492bb7c1a4c484b82ee3bdab0e12eac30e90df01d84b713c962136
+oid sha256:98ddfa9214cc4a8744b1acb7c736584356b64328d1bba7daa8c13355771e08a2
 size 4920