Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5790e5a8c5c22f07393ee4bdba2f5a53f0b7883c9875bbfeaa6055475923cc
+oid sha256:0dbd76b53649a2e698dd2acdb87ce73fd734705433351eab27f1c382d596a715
 size 437958648

run-1/checkpoint-8420/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-1/checkpoint-8420/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dbd76b53649a2e698dd2acdb87ce73fd734705433351eab27f1c382d596a715
+size 437958648

run-1/checkpoint-8420/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30ea7f8f9c234e9323a7883ae2684d383e5ce93769daf8ca606983f45363ab73
+size 876038394

run-1/checkpoint-8420/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d57846f7ff8bde06bb25651ac6e490fb15e15ce5b28e8dbf1a7a106bbc9a61b6
+size 14308

run-1/checkpoint-8420/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:374960b96d89c3bafa1c2990238bd08b3605284ab52b64d65b2dba0fc105dc2f
+size 1064

run-1/checkpoint-8420/special_tokens_map.json

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

run-1/checkpoint-8420/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-1/checkpoint-8420/trainer_state.json

@@ -0,0 +1,59 @@
+{
+  "best_metric": 0.8555045871559633,
+  "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-1/checkpoint-8420",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 8420,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 19.184335708618164,
+      "learning_rate": 6.400602545895411e-07,
+      "loss": 0.684,
+      "step": 4209
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8211009174311926,
+      "eval_loss": 0.5808640718460083,
+      "eval_runtime": 2.4176,
+      "eval_samples_per_second": 360.683,
+      "eval_steps_per_second": 22.749,
+      "step": 4210
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 19.448436737060547,
+      "learning_rate": 3.039944215576068e-10,
+      "loss": 0.5704,
+      "step": 8418
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8555045871559633,
+      "eval_loss": 0.4303591251373291,
+      "eval_runtime": 2.4304,
+      "eval_samples_per_second": 358.783,
+      "eval_steps_per_second": 22.63,
+      "step": 8420
+    }
+  ],
+  "logging_steps": 4209,
+  "max_steps": 8420,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 2437637080706580.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.2798165147575246e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 24,
+    "weight_decay": 0.022271875197444224
+  }
+}

run-1/checkpoint-8420/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1319ddc45a70cf6c8258282d58f5ce2a722664ee561e40f594d0b44a8d8c1fb6
+size 4984

runs/Mar06_18-14-36_e017d622c671/events.out.tfevents.1709754030.e017d622c671.539.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbdbe802d64c52543d1cd10ced0b781f29e90b0bfeb855911e29b6b96274ca3e
-size 5287
+oid sha256:8d9a3778fafd6abde4d810cf0371210dd5d9b2ab21c892a02fbe5f8666447659
+size 6175