Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b428807a2e5da9ebee7ca15e468f1f1ec4ecbe9303e4fe21671433032a0ebbc5
+oid sha256:63fd40fcc4b77eb4b55acf1bd4799363cb903ca730c1246e3fa7e5717a50839f
 size 437958648

run-0/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-0/checkpoint-842/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63fd40fcc4b77eb4b55acf1bd4799363cb903ca730c1246e3fa7e5717a50839f
+size 437958648

run-0/checkpoint-842/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e01a2404057cdcb5ddf47786af17d0fd8566fb7e66c72e8c785df6c135d2e0aa
+size 876038394

run-0/checkpoint-842/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:505ff0daefb21a6c8c2324f62a92aad54c4bd1f2e84dbebb3c66afe6327a77a4
+size 14244

run-0/checkpoint-842/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0517da48a31c274eff5736bf0d10d4e0c2c1e8a7bfb08bf1cfb24b4d20c9e8b
+size 1064

run-0/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-0/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-0/checkpoint-842/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.7717889908256881,
+  "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-0/checkpoint-842",
+  "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": 0.5871559633027523,
+      "eval_loss": 0.6697461009025574,
+      "eval_runtime": 2.3652,
+      "eval_samples_per_second": 368.681,
+      "eval_steps_per_second": 23.254,
+      "step": 421
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7717889908256881,
+      "eval_loss": 0.6226800084114075,
+      "eval_runtime": 2.335,
+      "eval_samples_per_second": 373.447,
+      "eval_steps_per_second": 23.555,
+      "step": 842
+    }
+  ],
+  "logging_steps": 4209,
+  "max_steps": 1263,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3048303331369337e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 6,
+    "weight_decay": 0.3377283287391723
+  }
+}

run-0/checkpoint-842/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44dc25bba6431ca36f2d7d667943561f905d13814eb88802e61a1b3a6032a237
+size 4984

runs/Mar05_15-08-53_9d72474d753b/events.out.tfevents.1709651760.9d72474d753b.33271.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ecded596c4f3d643c2cc5326c7c02af83d343d45d0251f9255bc817c79b89e4
-size 5073
+oid sha256:4be774d90b3134b8719ee1899a366e80e1bb6097572a248131dadc64448c75f6
+size 5396