Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:021e86c88dc67430e1e5c6d76dd0fc0c913c6aa802914511cccb0803a00af50c
+oid sha256:cd57296733da75721fe718a7dddbd6737599ab42a13403b449b9e16ea541eea4
 size 437958648

run-3/checkpoint-50514/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-3/checkpoint-50514/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd57296733da75721fe718a7dddbd6737599ab42a13403b449b9e16ea541eea4
+size 437958648

run-3/checkpoint-50514/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23d4a38a155d3fe710e0d343f05ec7cf43347a211c1366e1c1b580e3a20b00bc
+size 876038394

run-3/checkpoint-50514/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e02f251f1d76886b861c110af5f7305ac9e4335c38c052d85a2ed743810a884
+size 14244

run-3/checkpoint-50514/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a89317c6e09ae3241a028ca7bfeac5b7cb7df1496b8339fab1063f7b4501ea14
+size 1064

run-3/checkpoint-50514/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-50514/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-3/checkpoint-50514/trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": 0.9220183486238532,
+  "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-3/checkpoint-33676",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 50514,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "grad_norm": 295.93414306640625,
+      "learning_rate": 9.536827410046812e-06,
+      "loss": 0.6121,
+      "step": 4209
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.9155740141868591,
+      "learning_rate": 8.669955440089204e-06,
+      "loss": 0.573,
+      "step": 8418
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 162.3487091064453,
+      "learning_rate": 7.803083470131597e-06,
+      "loss": 0.5403,
+      "step": 12627
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.1670043170452118,
+      "learning_rate": 6.936211500173989e-06,
+      "loss": 0.4884,
+      "step": 16836
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9013761467889908,
+      "eval_loss": 0.4918152391910553,
+      "eval_runtime": 2.4623,
+      "eval_samples_per_second": 354.144,
+      "eval_steps_per_second": 22.337,
+      "step": 16838
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 33.91927719116211,
+      "learning_rate": 6.069339530216381e-06,
+      "loss": 0.4458,
+      "step": 21045
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 2.4961254596710205,
+      "learning_rate": 5.202467560258773e-06,
+      "loss": 0.4301,
+      "step": 25254
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.07560272514820099,
+      "learning_rate": 4.335595590301165e-06,
+      "loss": 0.4057,
+      "step": 29463
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6363665461540222,
+      "learning_rate": 3.4687236203435575e-06,
+      "loss": 0.3992,
+      "step": 33672
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9220183486238532,
+      "eval_loss": 0.4500230848789215,
+      "eval_runtime": 2.4396,
+      "eval_samples_per_second": 357.431,
+      "eval_steps_per_second": 22.544,
+      "step": 33676
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 41.03260040283203,
+      "learning_rate": 2.6018516503859495e-06,
+      "loss": 0.3631,
+      "step": 37881
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 62.73563766479492,
+      "learning_rate": 1.7349796804283415e-06,
+      "loss": 0.3686,
+      "step": 42090
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.011593305505812168,
+      "learning_rate": 8.681077104707335e-07,
+      "loss": 0.3506,
+      "step": 46299
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.15126778185367584,
+      "learning_rate": 1.2357405131255993e-09,
+      "loss": 0.3503,
+      "step": 50508
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9197247706422018,
+      "eval_loss": 0.5046377182006836,
+      "eval_runtime": 2.4337,
+      "eval_samples_per_second": 358.307,
+      "eval_steps_per_second": 22.6,
+      "step": 50514
+    }
+  ],
+  "logging_steps": 4209,
+  "max_steps": 50514,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2484012973657680.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.040369938000442e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 7,
+    "weight_decay": 0.2933024618852218
+  }
+}

run-3/checkpoint-50514/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9482bfd78493d3a93f61bdac0b3e0c266bc6feb1b9eeb8b0e705574041a082e
+size 4984

runs/Mar06_18-14-36_e017d622c671/events.out.tfevents.1709757360.e017d622c671.539.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45912ed147d899c4835d233c4595ca5865535280d2acf6623a5c8f35e5e21875
-size 7114
+oid sha256:fb627ec8782821ec389725a41a6b3f0ce349d86336cc731ecee749db44cb7b29
+size 8663