Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7b3e40006dfbbb0b013a50f60402e18c0cad89d65192248d8cad2ca1181dc96
+oid sha256:e155afcdacda71cb5dd7910fc2d76cd060540068b1e8b06aaee9bb5d13c3e0f8
 size 267835644

run-2/checkpoint-820/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-2/checkpoint-820/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e155afcdacda71cb5dd7910fc2d76cd060540068b1e8b06aaee9bb5d13c3e0f8
+size 267835644

run-2/checkpoint-820/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f005acfd3fce21975a4c540208743e9f3214e47c8e3d2acdb7bf24d75ba7b3
+size 535733434

run-2/checkpoint-820/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1413cab1eb2fda657c624e979f84406b7cce7c72a1d30fed57c0f54fa00d206e
+size 14308

run-2/checkpoint-820/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bee53137a06ca607991271c63ead52a3039e7213660364fee434e561ef149ee
+size 1064

run-2/checkpoint-820/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-820/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-2/checkpoint-820/trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": 0.2669081389904022,
+  "best_model_checkpoint": "bert-finetuned-das/run-2/checkpoint-820",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 820,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8903775883069428,
+      "eval_loss": 0.3384491503238678,
+      "eval_runtime": 2.0928,
+      "eval_samples_per_second": 392.288,
+      "eval_steps_per_second": 24.847,
+      "step": 410
+    },
+    {
+      "epoch": 1.2195121951219512,
+      "grad_norm": 1.6518828868865967,
+      "learning_rate": 5.3856111022740605e-06,
+      "loss": 0.4169,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9086479902557856,
+      "eval_loss": 0.2669081389904022,
+      "eval_runtime": 2.1495,
+      "eval_samples_per_second": 381.941,
+      "eval_steps_per_second": 24.191,
+      "step": 820
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1230,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 113814292959792.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.074385829859034e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 37
+  }
+}

run-2/checkpoint-820/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a90bb106ccdd2ccf2a4824c59376533afb88bd2957ad800a06ac02b31f5d622
+size 5112

runs/Jul17_22-58-25_10dbc3c42dd8/events.out.tfevents.1721257663.10dbc3c42dd8.34.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57c0bb020c2e35596511d5f0306aefda27eca87a721aee348d9317fd4a26ff8e
-size 5414
+oid sha256:2ae2b75e4d86a3d6a775af6307f762f148d8ea6680629d821f71aeed4e728458
+size 5948