Training in progress, step 471

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8e20a83c706d8f243fdd5451cc21222c4326c89dcf45c565700fbf0e2b83391
+oid sha256:e4cc33b8d0b52dcf2a12f056d1fcef90253d2526a82e2e0ad9738277ef4b90bd
 size 265470032

run-0/checkpoint-471/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-0/checkpoint-471/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4cc33b8d0b52dcf2a12f056d1fcef90253d2526a82e2e0ad9738277ef4b90bd
+size 265470032

run-0/checkpoint-471/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd3a6abbfdcdd30dd87ca3433116a9bebb1c8b092a15ca749eb650137914d6f1
+size 531000890

run-0/checkpoint-471/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebf75655742e6964c7cc52079464486f9ea521640d6557a2919ae32a21e6889a
+size 14244

run-0/checkpoint-471/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:026e0f853e5a0df846bb5ef1a604f68614805d64a78033ac55f7493f43746b39
+size 1064

run-0/checkpoint-471/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-471/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-0/checkpoint-471/trainer_state.json

@@ -0,0 +1,107 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 471,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6369426751592356,
+      "grad_norm": 11.424042701721191,
+      "learning_rate": 2.617862969670073e-05,
+      "loss": 3.8796,
+      "step": 100
+    },
+    {
+      "epoch": 0.6369426751592356,
+      "eval_loss": 2.8795037269592285,
+      "eval_runtime": 3.5583,
+      "eval_samples_per_second": 140.515,
+      "eval_steps_per_second": 4.496,
+      "step": 100
+    },
+    {
+      "epoch": 1.2738853503184713,
+      "grad_norm": 13.521265029907227,
+      "learning_rate": 1.9122395277104845e-05,
+      "loss": 2.306,
+      "step": 200
+    },
+    {
+      "epoch": 1.2738853503184713,
+      "eval_loss": 1.97040593624115,
+      "eval_runtime": 3.6094,
+      "eval_samples_per_second": 138.528,
+      "eval_steps_per_second": 4.433,
+      "step": 200
+    },
+    {
+      "epoch": 1.910828025477707,
+      "grad_norm": 16.13125228881836,
+      "learning_rate": 1.206616085750896e-05,
+      "loss": 1.6392,
+      "step": 300
+    },
+    {
+      "epoch": 1.910828025477707,
+      "eval_loss": 1.7181620597839355,
+      "eval_runtime": 3.5951,
+      "eval_samples_per_second": 139.079,
+      "eval_steps_per_second": 4.451,
+      "step": 300
+    },
+    {
+      "epoch": 2.5477707006369426,
+      "grad_norm": 11.650218963623047,
+      "learning_rate": 5.009926437913077e-06,
+      "loss": 1.2706,
+      "step": 400
+    },
+    {
+      "epoch": 2.5477707006369426,
+      "eval_loss": 1.7209367752075195,
+      "eval_runtime": 3.5763,
+      "eval_samples_per_second": 139.808,
+      "eval_steps_per_second": 4.474,
+      "step": 400
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 471,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1249566248706048.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.323486411629661e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 28
+  }
+}

run-0/checkpoint-471/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402b2439b600ffbf748e5b356349c52da746deb8c130785c86fd777ae8904832
+size 5176

runs/Nov18_09-36-44_aa151f0a91fc/events.out.tfevents.1731922605.aa151f0a91fc.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94e08238a25aba514d294e65d73d1dc8a27aae777058a98a3b1f5bb8c7f03595
+size 7144

special_tokens_map.json

@@ -1,37 +1,7 @@
 {
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -45,18 +45,11 @@
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "max_length": 384,
   "model_max_length": 512,
-  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "[SEP]",
-  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "DistilBertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "only_second",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bb34187f447a16d45e04af5f8b4429bdc7160f82f0bad3553fb192984222ad1
-size 5240
+oid sha256:402b2439b600ffbf748e5b356349c52da746deb8c130785c86fd777ae8904832
+size 5176