Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e3139795994fe58ebae8dff0d22e397447333f436eaec59e29fafc3d1607517
+oid sha256:3fab52a70b75eb5cadd8dc48f012d53c4d0577ea3420700d34a72d52684a9318
 size 267832560

run-2/checkpoint-4452/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "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,
+  "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": "4.37.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-4452/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fab52a70b75eb5cadd8dc48f012d53c4d0577ea3420700d34a72d52684a9318
+size 267832560

run-2/checkpoint-4452/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b4602cb72417c56da9133380919e82eb04331db65eb3725dd5f720f1a2bca40
+size 535727290

run-2/checkpoint-4452/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03fa820cf89d2f9128eefb2f405d6cd938a0b0d63a0d45f115071f897928aad0
+size 14308

run-2/checkpoint-4452/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7ffed1c013f52a99737d049b38aaf8b21fba9ea191dc2c796ba417bfaeec59f
+size 1064

run-2/checkpoint-4452/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-4452/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-4452/trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_metric": 0.8483327357475797,
+  "best_model_checkpoint": "retrieval_model/run-2/checkpoint-4452",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 4452,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.4890233570154926e-05,
+      "loss": 0.3898,
+      "step": 500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.3006347743971357e-05,
+      "loss": 0.3149,
+      "step": 1000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.1122461917787789e-05,
+      "loss": 0.3024,
+      "step": 1500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.23857609160422e-06,
+      "loss": 0.2859,
+      "step": 2000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 7.354690265420652e-06,
+      "loss": 0.2714,
+      "step": 2500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.4708044392370836e-06,
+      "loss": 0.2745,
+      "step": 3000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.5869186130535147e-06,
+      "loss": 0.2546,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.7030327868699458e-06,
+      "loss": 0.2626,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.8483327357475797,
+      "eval_loss": 0.254926860332489,
+      "eval_runtime": 8.1114,
+      "eval_samples_per_second": 487.709,
+      "eval_steps_per_second": 7.644,
+      "step": 4452
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4452,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 4716133304194368.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6774119396338494e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 16,
+    "seed": 13
+  }
+}

run-2/checkpoint-4452/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e73c0297fe24998cdb1cf89fda7fdfe29f3cdf5c961b5c526e720a041ae28d30
+size 4664

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e54dc41d6ac230e0d0c0f42e6c374dbc1aeb8a58f555a507136f2227c8ba5626
+oid sha256:e73c0297fe24998cdb1cf89fda7fdfe29f3cdf5c961b5c526e720a041ae28d30
 size 4664