Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45f742ed752eb86c7e1931d926b9e98ddf169ab5fd0d1aa2422cd958471b1b96
+oid sha256:e699d91b423f2e72fa75a5741d4f342a35afd9a1e9b8127c151f109f32edb498
 size 437958648

run-0/checkpoint-67352/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-0/checkpoint-67352/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e699d91b423f2e72fa75a5741d4f342a35afd9a1e9b8127c151f109f32edb498
+size 437958648

run-0/checkpoint-67352/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b91a1bddd91afb7b3286db3b08989c6927901b5e4f93932b9202355eedef30f
+size 876038394

run-0/checkpoint-67352/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c7bfee0f9a95a9e8164bdf1b90de63c49ca3d1b2af140071e5981410fd8c2e
+size 14244

run-0/checkpoint-67352/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb8a2220ed5efddb63245525b40bcc0dfe6a5c2147d5d1c7685f23890af2c60c
+size 1064

run-0/checkpoint-67352/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-67352/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-67352/trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.8841743119266054,
+  "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-0/checkpoint-50514",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 67352,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "grad_norm": 19.703554153442383,
+      "learning_rate": 6.973163454116781e-07,
+      "loss": 0.7045,
+      "step": 4209
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 33.55769729614258,
+      "learning_rate": 6.508344788890587e-07,
+      "loss": 0.6701,
+      "step": 8418
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 121.4453353881836,
+      "learning_rate": 6.043526123664394e-07,
+      "loss": 0.566,
+      "step": 12627
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 72.47432708740234,
+      "learning_rate": 5.578707458438201e-07,
+      "loss": 0.5309,
+      "step": 16836
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8715596330275229,
+      "eval_loss": 0.3419412672519684,
+      "eval_runtime": 2.4269,
+      "eval_samples_per_second": 359.309,
+      "eval_steps_per_second": 22.663,
+      "step": 16838
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 169.0806884765625,
+      "learning_rate": 5.113888793212007e-07,
+      "loss": 0.5455,
+      "step": 21045
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 26.04638671875,
+      "learning_rate": 4.649070127985814e-07,
+      "loss": 0.5548,
+      "step": 25254
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 17.553491592407227,
+      "learning_rate": 4.18425146275962e-07,
+      "loss": 0.5681,
+      "step": 29463
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.3310186862945557,
+      "learning_rate": 3.7194327975334265e-07,
+      "loss": 0.6066,
+      "step": 33672
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8784403669724771,
+      "eval_loss": 0.3679516315460205,
+      "eval_runtime": 2.4422,
+      "eval_samples_per_second": 357.051,
+      "eval_steps_per_second": 22.52,
+      "step": 33676
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 60.65003967285156,
+      "learning_rate": 3.2546141323072335e-07,
+      "loss": 0.5873,
+      "step": 37881
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 179.75804138183594,
+      "learning_rate": 2.78979546708104e-07,
+      "loss": 0.6103,
+      "step": 42090
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.3105064332485199,
+      "learning_rate": 2.3249768018548465e-07,
+      "loss": 0.6097,
+      "step": 46299
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 22.6956844329834,
+      "learning_rate": 1.8601581366286533e-07,
+      "loss": 0.5877,
+      "step": 50508
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8841743119266054,
+      "eval_loss": 0.40006375312805176,
+      "eval_runtime": 2.4426,
+      "eval_samples_per_second": 357.004,
+      "eval_steps_per_second": 22.517,
+      "step": 50514
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 72.1812973022461,
+      "learning_rate": 1.39533947140246e-07,
+      "loss": 0.5876,
+      "step": 54717
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 173.94847106933594,
+      "learning_rate": 9.305208061762665e-08,
+      "loss": 0.6035,
+      "step": 58926
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 258.52398681640625,
+      "learning_rate": 4.657021409500731e-08,
+      "loss": 0.5893,
+      "step": 63135
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 36.017032623291016,
+      "learning_rate": 8.834757238796738e-11,
+      "loss": 0.5887,
+      "step": 67344
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8841743119266054,
+      "eval_loss": 0.40259793400764465,
+      "eval_runtime": 2.4205,
+      "eval_samples_per_second": 360.264,
+      "eval_steps_per_second": 22.723,
+      "step": 67352
+    }
+  ],
+  "logging_steps": 4209,
+  "max_steps": 67352,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 3312611867528700.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.437982119342974e-07,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 7,
+    "weight_decay": 0.46186751115854463
+  }
+}

run-0/checkpoint-67352/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2cdb1762dc540953c33889b0130bacb81cb55cd749bc8f619467321c5f1919
+size 4984

runs/Mar06_18-14-36_e017d622c671/events.out.tfevents.1709748990.e017d622c671.539.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf4b9739dedba9c5a809e07f50fbc00f5db5e076b10b12e882fd21b41272b396
-size 8304
+oid sha256:a2bff6532478e600ebca94cbbe0fc7b75678908143caa77a9937e122ca05a06d
+size 9853