Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a029dfc9b81886295b7f77e6c83ac9b27e34ee6fe15f9d53604a01a31ca78c5e
+oid sha256:b6f629c2db0cf6a2a1ceafca0ab21cb85fc9c5d8e585f947034e752a6b9bd6f2
 size 437958648

run-8/checkpoint-842/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.3,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.3,
+  "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-8/checkpoint-842/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:496815a200cae3c486debd2df2d07f9f10f36ca851977e4f7c1966db0b5c281b
+size 437958648

run-8/checkpoint-842/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58d8743d34dd5d4f86483814a71a1da8f6983fa7bbafd6dd3bb92c100fae4c3
+size 876038394

run-8/checkpoint-842/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f667b5b5643fdb8f833da42b416840f5b9b87f293ca457ccc35b82cf514d97
+size 14180

run-8/checkpoint-842/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c225241ac5065b358fd6497cb27a2ff47161c477985b63fac966ee91d184153
+size 1064

run-8/checkpoint-842/special_tokens_map.json

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

run-8/checkpoint-842/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-8/checkpoint-842/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.8876146788990825,
+  "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-8/checkpoint-421",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 842,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8876146788990825,
+      "eval_loss": 0.2878369987010956,
+      "eval_runtime": 2.3568,
+      "eval_samples_per_second": 369.996,
+      "eval_steps_per_second": 23.337,
+      "step": 421
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8864678899082569,
+      "eval_loss": 0.2797411382198334,
+      "eval_runtime": 2.3688,
+      "eval_samples_per_second": 368.112,
+      "eval_steps_per_second": 23.218,
+      "step": 842
+    }
+  ],
+  "logging_steps": 4209,
+  "max_steps": 842,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3007555473187744e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 10,
+    "weight_decay": 0.3516798909755618
+  }
+}

run-8/checkpoint-842/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7654b2f5b661ba7a7284e6ce0550ef7fb0f9a4e6dcc315f58196aa8be0b4267
+size 4984

runs/Mar05_15-08-53_9d72474d753b/events.out.tfevents.1709653896.9d72474d753b.33271.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b79146a75e9494ce951c19f86faf505c0e45e65ff152b537074936db9ee756
+size 5073

runs/Mar05_15-08-53_9d72474d753b/events.out.tfevents.1709654407.9d72474d753b.33271.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0cea03d920c965aa923ef08fdeb9ac2989f357804293c0d86d474c31cf96bf0
+size 5072

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7654b2f5b661ba7a7284e6ce0550ef7fb0f9a4e6dcc315f58196aa8be0b4267
+oid sha256:29ae5b378da67d6d3b8366dbe235ab8607f31fbbf97b177d40ac47d54da34fd0
 size 4984