Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7f3b30207cb33bfbca6b89499a12df75b8f84f2ac5d99587ca172ccea837344
+oid sha256:894d1b0c0da326d4f8cda11cc4ca29592366fce3736ec56ffbc39c1397e63d03
 size 437958648

run-4/checkpoint-12630/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.4,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.4,
+  "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-12630/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:894d1b0c0da326d4f8cda11cc4ca29592366fce3736ec56ffbc39c1397e63d03
+size 437958648

run-4/checkpoint-12630/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d9a03a11d17a5d0fd9e0998237a75a7e8157d0c76486d44aa53a5201cbca54e
+size 876038394

run-4/checkpoint-12630/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e27ae77c7c17d1e01a615dbcaf5f0b2bfd6b743d2f3ea2e92189e56abcbd301
+size 14244

run-4/checkpoint-12630/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34cb0a7bbf1704ae8a6f3f996baa7ce7a8b068f9a26c7e5249faf0ac49d4fc0c
+size 1064

run-4/checkpoint-12630/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-12630/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-12630/trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_metric": 0.9139908256880734,
+  "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-4/checkpoint-8420",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 12630,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 20.266050338745117,
+      "learning_rate": 2.0417873766363758e-05,
+      "loss": 0.3739,
+      "step": 4209
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9059633027522935,
+      "eval_loss": 0.28132590651512146,
+      "eval_runtime": 2.4226,
+      "eval_samples_per_second": 359.943,
+      "eval_steps_per_second": 22.703,
+      "step": 4210
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 31.52709197998047,
+      "learning_rate": 1.531492081329535e-05,
+      "loss": 0.2461,
+      "step": 8418
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9139908256880734,
+      "eval_loss": 0.35249146819114685,
+      "eval_runtime": 2.4264,
+      "eval_samples_per_second": 359.387,
+      "eval_steps_per_second": 22.668,
+      "step": 8420
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.8592076301574707,
+      "learning_rate": 1.0211967860226942e-05,
+      "loss": 0.2063,
+      "step": 12627
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.908256880733945,
+      "eval_loss": 0.38172876834869385,
+      "eval_runtime": 2.4147,
+      "eval_samples_per_second": 361.12,
+      "eval_steps_per_second": 22.777,
+      "step": 12630
+    }
+  ],
+  "logging_steps": 4209,
+  "max_steps": 21050,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 3654833531125800.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.5520826719432166e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 27,
+    "weight_decay": 0.30671272708017133
+  }
+}

run-4/checkpoint-12630/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79639f8dc59c3749bc4f8e0b04d77757fcb59a728c0f0abcf338eda4dfd20a1a
+size 4984

runs/Mar06_18-14-36_e017d622c671/events.out.tfevents.1709761277.e017d622c671.539.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a96d0f45fd70dafb15445b35f495627a1ff0c5bfce771ca1323c2a10cd413897
-size 5820
+oid sha256:b7bdd43f5597661bab4955e74967f69027b679995c07a6c7754de068a95e77b0
+size 6354