Training in progress, step 200

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7067dddc82824bd08360f27db4a9e691d0b8c8f31e5c39f230e146cdef033f65
+oid sha256:92ae91f19d7a0bddff9952990025d76845e6143230199342593690c6446e00e1
 size 265470032

run-4/checkpoint-200/config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForQuestionAnswering"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "vocab_size": 30522
+}

run-4/checkpoint-200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ae91f19d7a0bddff9952990025d76845e6143230199342593690c6446e00e1
+size 265470032

run-4/checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3764ff66171d844bb2902bf8800416f5bc349561f81a4916f0efdde145c74bb1
+size 531000890

run-4/checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f53d01aded511556ba263ceb94071ea8bb4840b05e274e836a18db6ec1fe3e7
+size 14244

run-4/checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6330d27c20797705017d995b8dc77e96dbcb7e30e9aa9231891c909bca656e86
+size 1064

run-4/checkpoint-200/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-200/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": false,
+  "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-4/checkpoint-200/trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": 1.7362614870071411,
+  "best_model_checkpoint": "qa_finetuning/run-4/checkpoint-200",
+  "epoch": 5.0,
+  "eval_steps": 100,
+  "global_step": 200,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.5,
+      "grad_norm": 7.338883876800537,
+      "learning_rate": 1.8677116057865877e-05,
+      "loss": 3.2617,
+      "step": 100
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 1.8736786842346191,
+      "eval_runtime": 3.6445,
+      "eval_samples_per_second": 137.192,
+      "eval_steps_per_second": 4.39,
+      "step": 100
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 30.04753303527832,
+      "learning_rate": 0.0,
+      "loss": 1.439,
+      "step": 200
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.7362614870071411,
+      "eval_runtime": 3.6733,
+      "eval_samples_per_second": 136.118,
+      "eval_steps_per_second": 4.356,
+      "step": 200
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2449745625600000.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.7354232115731755e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 9
+  }
+}

run-4/checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0d3817e4d4917be54a57c0ab3bc2de429712457e9df748914ff6168e15c57f0
+size 5176

runs/Nov18_10-11-09_aa151f0a91fc/events.out.tfevents.1731926196.aa151f0a91fc.1516.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:781f291f5769a79a76aca765593b1b14120a88d15a32396612d612111d3def75
+size 6141

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a37f5b8dfa12292086ae10710a829db6ed3942399f7b20f71f43f3abb90d0284
+oid sha256:b0d3817e4d4917be54a57c0ab3bc2de429712457e9df748914ff6168e15c57f0
 size 5176