Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ffa66191c7997d3b86686b7ca7b22f03e0efaca9054f5f289afd54a52fe80c5
+oid sha256:31e8e66a6fdbe2714a08ba1683f1f2ddf589b760aa4848941d634763bfe8536c
 size 437958648

run-4/checkpoint-21050/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-4/checkpoint-21050/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31e8e66a6fdbe2714a08ba1683f1f2ddf589b760aa4848941d634763bfe8536c
+size 437958648

run-4/checkpoint-21050/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56eae9ed4aa86bf4c83af7c55ba189cd92c9597457f746a4e5c9873152c97cca
+size 876038394

run-4/checkpoint-21050/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e094541ff5efdafdc4b0f0948dbb524dde74692c560bafd45ec4677675110419
+size 14244

run-4/checkpoint-21050/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc614c72fa401b7fbe980f7fb8cce3a3cfe7fe79e2ae5e7e4c8d3d71d8f4324c
+size 1064

run-4/checkpoint-21050/special_tokens_map.json

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

run-4/checkpoint-21050/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-4/checkpoint-21050/trainer_state.json

@@ -0,0 +1,107 @@
+{
+  "best_metric": 0.9139908256880734,
+  "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-4/checkpoint-8420",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 21050,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 20.266050338745117,
+      "learning_rate": 2.0417873766363758e-05,
+      "loss": 0.3739,
+      "step": 4209
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9059633027522935,
+      "eval_loss": 0.28132590651512146,
+      "eval_runtime": 2.4226,
+      "eval_samples_per_second": 359.943,
+      "eval_steps_per_second": 22.703,
+      "step": 4210
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 31.52709197998047,
+      "learning_rate": 1.531492081329535e-05,
+      "loss": 0.2461,
+      "step": 8418
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9139908256880734,
+      "eval_loss": 0.35249146819114685,
+      "eval_runtime": 2.4264,
+      "eval_samples_per_second": 359.387,
+      "eval_steps_per_second": 22.668,
+      "step": 8420
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.8592076301574707,
+      "learning_rate": 1.0211967860226942e-05,
+      "loss": 0.2063,
+      "step": 12627
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.908256880733945,
+      "eval_loss": 0.38172876834869385,
+      "eval_runtime": 2.4147,
+      "eval_samples_per_second": 361.12,
+      "eval_steps_per_second": 22.777,
+      "step": 12630
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 19.267065048217773,
+      "learning_rate": 5.109014907158535e-06,
+      "loss": 0.1789,
+      "step": 16836
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9139908256880734,
+      "eval_loss": 0.4979610741138458,
+      "eval_runtime": 2.4158,
+      "eval_samples_per_second": 360.958,
+      "eval_steps_per_second": 22.767,
+      "step": 16840
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.8149940967559814,
+      "learning_rate": 6.061954090126405e-09,
+      "loss": 0.1621,
+      "step": 21045
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9139908256880734,
+      "eval_loss": 0.46082746982574463,
+      "eval_runtime": 2.4166,
+      "eval_samples_per_second": 360.832,
+      "eval_steps_per_second": 22.759,
+      "step": 21050
+    }
+  ],
+  "logging_steps": 4209,
+  "max_steps": 21050,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 6093988125399720.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.5520826719432166e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 27,
+    "weight_decay": 0.30671272708017133
+  }
+}

run-4/checkpoint-21050/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79639f8dc59c3749bc4f8e0b04d77757fcb59a728c0f0abcf338eda4dfd20a1a
+size 4984

runs/Mar06_18-14-36_e017d622c671/events.out.tfevents.1709761277.e017d622c671.539.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e48d4cac9ed777eaff7ae095a7024abe71d524d1356f0d7caa52040c6b395fb2
-size 6898
+oid sha256:49f51cd2d077926e7b7d3f9858a1311506b98d5d2bdb1fd46a8f49f66bff52bf
+size 7802