Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a77e5fb2e0250b5d9087fe7c74192cc9a073b185e0c83d8b03b647c28858645
+oid sha256:f08052c2e29c23e1132588d6b0140b92030594318aadea8c5eaf269e9e91e35e
 size 437958648

run-0/checkpoint-842/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "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-0/checkpoint-842/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f08052c2e29c23e1132588d6b0140b92030594318aadea8c5eaf269e9e91e35e
+size 437958648

run-0/checkpoint-842/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4019edec2a3953444c24da0a6cb02ae938f3eaa84c3c765083855aed39c0fb48
+size 876038394

run-0/checkpoint-842/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbef7fdec46a34ed3dc47114ae13abd964fe7daf9004f4c4a7c35dfcc4146ef2
+size 14308

run-0/checkpoint-842/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed0ae41870ca182e263458d4466803cfa6c4ead1532a921733a159e9489da14e
+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 +1,42 @@
+{
+  "best_metric": 0.8646788990825688,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-0/checkpoint-842",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 842,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.59,
+      "grad_norm": 14.076563835144043,
+      "learning_rate": 2.1488708627178514e-06,
+      "loss": 0.4976,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8646788990825688,
+      "eval_loss": 0.33198288083076477,
+      "eval_runtime": 2.248,
+      "eval_samples_per_second": 387.892,
+      "eval_steps_per_second": 24.466,
+      "step": 842
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4210,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 60244209456960.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.438476100280904e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 29
+  }
+}

run-0/checkpoint-842/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97abbdcb1d4ff26ff452c134035ac092df99b9eac097f1e25dcf4b4c26f6558b
+size 4920

runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709487744.90708aaa767a.21824.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13cd6684689623b1fa8528dcd30c65990d146724f38427bd5518e0838649b264
-size 15186
+oid sha256:bbd78385c46367264ded30b902e2c29fc1156f7bc612ea42a81ac29d362b2e22
+size 15546

runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709490615.90708aaa767a.21824.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68f9cb9b3f81e1c9fe1d38fe68f2d4ffafd3831143e12770dc7676b2a199c98e
+size 417

runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709491671.90708aaa767a.21824.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d8868ab2fa3492d5321aa8ac8c2535c15c6def4a282d7b7b729e27e24c74f1b
+size 5157

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95576265752f75be71c0b6dc46e57e0200305cf27a310bbe5ca820b3e53cdee4
+oid sha256:97abbdcb1d4ff26ff452c134035ac092df99b9eac097f1e25dcf4b4c26f6558b
 size 4920