Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73e48ab6eeeda9e01734d42bec36d4e088c82b1d12d97525c24182671eefda1f
+oid sha256:9fce43ae65cd824625a3d3da0f62852b34630ba61166f7cdcfc4c9eb3afcf2ef
 size 267832560

run-0/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": "4.35.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-4452/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fce43ae65cd824625a3d3da0f62852b34630ba61166f7cdcfc4c9eb3afcf2ef
+size 267832560

run-0/checkpoint-4452/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f9d61221d9e2b58ff7b8591abcd64e2ec147b05e6408dbfcce601025cbf555
+size 535727290

run-0/checkpoint-4452/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883dea6117854fd62ff1156836e2eca22a56c829ddf7fc0b087f69b0db045ae9
+size 14308

run-0/checkpoint-4452/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7be15ed6165cc57c1621138d8e4b79197113ae6ba3cc9f16f050f21d5e5355e
+size 1064

run-0/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-0/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-0/checkpoint-4452/trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": 0.8266480641785839,
+  "best_model_checkpoint": "retrieval_model/run-0/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": 1.8075065847895588e-06,
+      "loss": 0.4825,
+      "step": 500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.73720841332139e-06,
+      "loss": 0.3777,
+      "step": 1000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.666910241853221e-06,
+      "loss": 0.3516,
+      "step": 1500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.5966120703850521e-06,
+      "loss": 0.3194,
+      "step": 2000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.5263138989168832e-06,
+      "loss": 0.3394,
+      "step": 2500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.4560157274487143e-06,
+      "loss": 0.3201,
+      "step": 3000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.3857175559805454e-06,
+      "loss": 0.3128,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.3154193845123765e-06,
+      "loss": 0.3316,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.8266480641785839,
+      "eval_loss": 0.306449294090271,
+      "eval_runtime": 15.3165,
+      "eval_samples_per_second": 258.283,
+      "eval_steps_per_second": 8.096,
+      "step": 4452
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 13356,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 4721514792264768.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.8778047562577277e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 37
+  }
+}

run-0/checkpoint-4452/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5521eb92746940d9565af4306b63f1239e8192971887da1871b30da6a3051d
+size 4600

runs/Feb05_22-24-00_760f8e25befd/events.out.tfevents.1707171842.760f8e25befd.956.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acb8d50896f51a1aea8d89884c39b9663cd82b6ce9f5f83661bf5f31152b9e51
+size 5834

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c3bbe83a16e4d0795b3103b6f74c9cc86efb22cb921fb0cbc559c28763ac610
+oid sha256:8a5521eb92746940d9565af4306b63f1239e8192971887da1871b30da6a3051d
 size 4600