Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:097d83f7abfa7a086e971f1afb84acad12e5398bd9ed1ad294d5e26101fbdfaf
+oid sha256:01005cbb8e85152956ddb377cf179e3cd24dbe27e032cc71344529e0cc877c33
 size 437958648

run-2/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-2/checkpoint-421/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01005cbb8e85152956ddb377cf179e3cd24dbe27e032cc71344529e0cc877c33
+size 437958648

run-2/checkpoint-421/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b8195b23c9a8b26992b9058b668dfe1693a57f86dda70a85bd0dde16a683d5
+size 876038394

run-2/checkpoint-421/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6235a55a1406b399f73257619919ed5a90c608925c3f8dcf6bd713cf84e9a034
+size 14244

run-2/checkpoint-421/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4f91b170f6738fc1faadfae512b3d8af3072e91f29f865e4394d4507d79bc8d
+size 1064

run-2/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-2/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-2/checkpoint-421/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.8761467889908257,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-2/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": 0.8761467889908257,
+      "eval_loss": 0.3037863075733185,
+      "eval_runtime": 2.2668,
+      "eval_samples_per_second": 384.685,
+      "eval_steps_per_second": 24.263,
+      "step": 421
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2105,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.735962971422436e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 2
+  }
+}

run-2/checkpoint-421/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55dfbe476697181e66ebf5f3b6624f6c1c676b71c40c6125f531db2ed5ba1a72
+size 4920

runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709497917.90708aaa767a.21824.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:781cc6082e2c1d28081b76d85760483932c3583508940c692fa56ee99d2f4740
+size 5691

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a42951e65bb3aa1e125b1b27e2a27b66ec94bb48bc4ff40d24214557a0e4b15
+oid sha256:55dfbe476697181e66ebf5f3b6624f6c1c676b71c40c6125f531db2ed5ba1a72
 size 4920