Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4a282987b7c167804ecb765f0169699166d69ff57c88cc7d47b3df20df7c158
+oid sha256:249b1157edef1e2de15752e74e4e2344d094183b59595c8a1149623c80263e9e
 size 267835644

run-0/checkpoint-3280/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Not-Applicable",
+    "1": "Closed",
+    "2": "Open"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Closed": 1,
+    "Not-Applicable": 0,
+    "Open": 2
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-3280/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:249b1157edef1e2de15752e74e4e2344d094183b59595c8a1149623c80263e9e
+size 267835644

run-0/checkpoint-3280/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbe50db84baaad212f5fab5f652c3ffae4473e85c0b16f000acb7e9f59cc57a6
+size 535733434

run-0/checkpoint-3280/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca0ffe8661d2be56aeb6195841aa2af73df40b5dee5fbde19cbfad8303707e28
+size 14308

run-0/checkpoint-3280/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdafda64fcabe6196e923f5a08b3110775f8eebb60c3b7d818e2ea268d9dc77b
+size 1064

run-0/checkpoint-3280/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-3280/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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-3280/trainer_state.json

@@ -0,0 +1,116 @@
+{
+  "best_metric": 0.32205894589424133,
+  "best_model_checkpoint": "bert-finetuned-das/run-0/checkpoint-820",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 3280,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6097560975609756,
+      "grad_norm": 6.909906387329102,
+      "learning_rate": 1.2707321441211695e-05,
+      "loss": 0.482,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8989037758830695,
+      "eval_loss": 0.32205894589424133,
+      "eval_runtime": 2.1237,
+      "eval_samples_per_second": 386.598,
+      "eval_steps_per_second": 24.486,
+      "step": 820
+    },
+    {
+      "epoch": 1.2195121951219512,
+      "grad_norm": 11.560399055480957,
+      "learning_rate": 1.0421831973367864e-05,
+      "loss": 0.3702,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8292682926829267,
+      "grad_norm": 14.808815002441406,
+      "learning_rate": 8.136342505524035e-06,
+      "loss": 0.305,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9110840438489647,
+      "eval_loss": 0.32592716813087463,
+      "eval_runtime": 2.0954,
+      "eval_samples_per_second": 391.814,
+      "eval_steps_per_second": 24.816,
+      "step": 1640
+    },
+    {
+      "epoch": 2.4390243902439024,
+      "grad_norm": 0.16634021699428558,
+      "learning_rate": 5.8508530376802055e-06,
+      "loss": 0.2068,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9086479902557856,
+      "eval_loss": 0.3789357542991638,
+      "eval_runtime": 2.0963,
+      "eval_samples_per_second": 391.652,
+      "eval_steps_per_second": 24.806,
+      "step": 2460
+    },
+    {
+      "epoch": 3.048780487804878,
+      "grad_norm": 0.1265229731798172,
+      "learning_rate": 3.565363569836375e-06,
+      "loss": 0.2238,
+      "step": 2500
+    },
+    {
+      "epoch": 3.658536585365854,
+      "grad_norm": 0.020687824115157127,
+      "learning_rate": 1.279874101992545e-06,
+      "loss": 0.1217,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.904993909866017,
+      "eval_loss": 0.43472909927368164,
+      "eval_runtime": 2.1089,
+      "eval_samples_per_second": 389.295,
+      "eval_steps_per_second": 24.657,
+      "step": 3280
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 252408710591136.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.4992810909055526e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 20
+  }
+}

run-0/checkpoint-3280/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b0f5d683ba7842a9befa31fbd56c9c9d4eb9148c126c4076136fed0b561b05d
+size 5112

runs/Jul17_22-58-25_10dbc3c42dd8/events.out.tfevents.1721257299.10dbc3c42dd8.34.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e76f20246532275c503b1cb5fcfda6b9607f4463f7021a67c9490fb71510f8f6
-size 6921
+oid sha256:b8826ef2925ed06e60b844b8d918a3ac8a1f4a0f7da7944a6f7d0c2c1cef7c6b
+size 7809