Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9be3d9f270ed98c53255781454631f8140be091dcbbc82d42aabd274b1764441
+oid sha256:c2b2aafcae729a306b3357ac97150c0b15496f661d290637b8bf1a56935baddc
 size 267835644

run-0/checkpoint-1640/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-1640/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2b2aafcae729a306b3357ac97150c0b15496f661d290637b8bf1a56935baddc
+size 267835644

run-0/checkpoint-1640/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6944f4537e9b34672d34be79b0cbfc7b4b72f0812ab17810c629fb0f438b876f
+size 535733434

run-0/checkpoint-1640/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7367775524162741c3193ee690ee07d620f33edf69a77229f967dfb22e22c965
+size 14308

run-0/checkpoint-1640/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a816ad6ccfb8559bc089e3dab6985f33067b86446c0c04f831c915b74a3faec9
+size 1064

run-0/checkpoint-1640/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-1640/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-1640/trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": 0.32205894589424133,
+  "best_model_checkpoint": "bert-finetuned-das/run-0/checkpoint-820",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1640,
+  "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
+    }
+  ],
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 126213669575640.0,
+  "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-1640/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:f0f06390e4b804b0194e5ab8ee8b2949f75508d53f458bf1d625519f25a85284
-size 5431
+oid sha256:fd0380d68bd62a744c4b1a463a74d5227b3b86d86f897eb82b1160f507639127
+size 6176