Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31a955edfe625a2c61701e9aa2d6fe9f06a5d7de799725906805912f09e3985c
+oid sha256:a6dfd741045809a36650a05388fc4409cd52bec7602883947ecd4f586fe2e4d6
 size 437958648

run-2/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-2/checkpoint-8420/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6dfd741045809a36650a05388fc4409cd52bec7602883947ecd4f586fe2e4d6
+size 437958648

run-2/checkpoint-8420/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79154eab7acd991f5189f4c03affd8a86cb753718159bb0e702d2380eab4bd90
+size 876038394

run-2/checkpoint-8420/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:430e130028f3c75cf43415a66cdc5bb0d4d24df2016d581e4cd8fe07fce98d4e
+size 14308

run-2/checkpoint-8420/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73dbee26827383ca323b0513f3a93b7a88a2aec59db3f6c01233123469d29a35
+size 1064

run-2/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-2/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-2/checkpoint-8420/trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": 0.8371559633027523,
+  "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-2/checkpoint-8420",
+  "epoch": 4.0,
+  "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,
+      "eval_accuracy": 0.5745412844036697,
+      "eval_loss": 0.658979058265686,
+      "eval_runtime": 2.4031,
+      "eval_samples_per_second": 362.862,
+      "eval_steps_per_second": 22.887,
+      "step": 2105
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 11.47251033782959,
+      "learning_rate": 4.003340487387436e-07,
+      "loss": 0.6604,
+      "step": 4209
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7350917431192661,
+      "eval_loss": 0.5269513726234436,
+      "eval_runtime": 2.4016,
+      "eval_samples_per_second": 363.093,
+      "eval_steps_per_second": 22.901,
+      "step": 4210
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.819954128440367,
+      "eval_loss": 0.4339826703071594,
+      "eval_runtime": 2.4278,
+      "eval_samples_per_second": 359.172,
+      "eval_steps_per_second": 22.654,
+      "step": 6315
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 15.470611572265625,
+      "learning_rate": 1.9013728270659872e-10,
+      "loss": 0.5279,
+      "step": 8418
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8371559633027523,
+      "eval_loss": 0.4121007025241852,
+      "eval_runtime": 2.4148,
+      "eval_samples_per_second": 361.103,
+      "eval_steps_per_second": 22.776,
+      "step": 8420
+    }
+  ],
+  "logging_steps": 4209,
+  "max_steps": 8420,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 5552011212462480.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.004779601947806e-07,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 37,
+    "weight_decay": 0.24080188545658526
+  }
+}

run-2/checkpoint-8420/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab85adc03c06c516aa29acaf676259ddec6473900c9e4098cbbdb0d71ae75d15
+size 4984

runs/Mar06_18-14-36_e017d622c671/events.out.tfevents.1709755237.e017d622c671.539.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59b0a478f44c4b1b248d785a68f9b9d293f09723ef26ac5c4afcd3095c0db5ca
-size 5931
+oid sha256:b46bb7a15180ced685c0362f3814dca6f3f319ad6c2f95913c405daeeabf8a89
+size 6819