Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:208d98d18f31d4d6e3c526eaf2f08508b80a2d7dc0823a7f7b63afb7e4d7151b
+oid sha256:a5a8d31918a9cd61e849b810097cf12b86f9857a5ab886650b3c234d318a7fc9
 size 437958648

run-3/checkpoint-1432/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "google-bert/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-3/checkpoint-1432/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5a8d31918a9cd61e849b810097cf12b86f9857a5ab886650b3c234d318a7fc9
+size 437958648

run-3/checkpoint-1432/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb175015843149982292a2d48aab0976b4dbb644e4993bf658776224a0e614fc
+size 876038394

run-3/checkpoint-1432/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cac9b4f127c9b75915f8eb41d31db4c969fdc3ffcae8404b0ae7a6bd010aef17
+size 14244

run-3/checkpoint-1432/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07848629e42f2a0c657fa2469d8c86b7126f680359de356161eee4613414b446
+size 1064

run-3/checkpoint-1432/special_tokens_map.json

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

run-3/checkpoint-1432/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-1432/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.6427904367446899,
+  "best_model_checkpoint": "./results/run-3/checkpoint-1432",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1432,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7,
+      "grad_norm": 5.121725082397461,
+      "learning_rate": 3.900489629009753e-05,
+      "loss": 0.6715,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5194444444444444,
+      "eval_loss": 0.6856995224952698,
+      "eval_runtime": 10.3139,
+      "eval_samples_per_second": 92.593,
+      "eval_steps_per_second": 11.635,
+      "step": 716
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 5.500706672668457,
+      "learning_rate": 2.7170886493344643e-05,
+      "loss": 0.6179,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6847222222222221,
+      "eval_loss": 0.6427904367446899,
+      "eval_runtime": 10.3637,
+      "eval_samples_per_second": 92.149,
+      "eval_steps_per_second": 11.579,
+      "step": 1432
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2148,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1051917999329280.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.0838906086850423e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 1
+  }
+}

run-3/checkpoint-1432/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca3e355c8b980d50d5c37f844c116e1c836e9aa10d941320a18e584fc6bb174f
+size 4920

runs/Mar09_23-14-00_aa189cdd2d19/events.out.tfevents.1710027494.aa189cdd2d19.2368.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b679eab625617306b11caab0e504e939c013f719175b37290c1dcbcecd098836
-size 5096
+oid sha256:c8121b179c1443d3e48545df71bf2a5ccfadf0fd1ffb05536e026f9ab87070c2
+size 5841