Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aafb79774351b6b6f3b4a82cf6c01be8b263ea56acf5a545028bf58c6c18e92
+oid sha256:e281f51f0d781b3c16873fbef66975f9d37ea6612757eb447c8bbd5db94f59f1
 size 267832560

run-3/checkpoint-17806/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-3/checkpoint-17806/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e281f51f0d781b3c16873fbef66975f9d37ea6612757eb447c8bbd5db94f59f1
+size 267832560

run-3/checkpoint-17806/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:477ee413a27e46b5e420ab20ddfcd9ce153c3bf3183c840d8eb68675b64eb23a
+size 535727290

run-3/checkpoint-17806/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8245e038011173a9581a4fd00ef34c756895d497edd68cda54b5e445190cb6f1
+size 14244

run-3/checkpoint-17806/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f8919a62f442f225e4208c5165b2b57aec5eb638114faa7ca2fe3392d4e1f62
+size 1064

run-3/checkpoint-17806/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-17806/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-3/checkpoint-17806/trainer_state.json

@@ -0,0 +1,254 @@
+{
+  "best_metric": 0.8438514244500541,
+  "best_model_checkpoint": "retrieval_model/run-3/checkpoint-17806",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 17806,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06,
+      "learning_rate": 3.4704519236458057e-06,
+      "loss": 0.4686,
+      "step": 500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.4210321821949366e-06,
+      "loss": 0.3929,
+      "step": 1000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.3716124407440683e-06,
+      "loss": 0.3526,
+      "step": 1500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 3.3221926992931996e-06,
+      "loss": 0.3448,
+      "step": 2000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 3.272772957842331e-06,
+      "loss": 0.3648,
+      "step": 2500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.223353216391462e-06,
+      "loss": 0.3417,
+      "step": 3000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.173933474940593e-06,
+      "loss": 0.3259,
+      "step": 3500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.124513733489725e-06,
+      "loss": 0.3513,
+      "step": 4000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 3.0750939920388557e-06,
+      "loss": 0.3343,
+      "step": 4500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 3.025674250587987e-06,
+      "loss": 0.3465,
+      "step": 5000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.9762545091371184e-06,
+      "loss": 0.3218,
+      "step": 5500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.9268347676862497e-06,
+      "loss": 0.3134,
+      "step": 6000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2.877415026235381e-06,
+      "loss": 0.3115,
+      "step": 6500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.8279952847845123e-06,
+      "loss": 0.3143,
+      "step": 7000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.7785755433336436e-06,
+      "loss": 0.3086,
+      "step": 7500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.7291558018827745e-06,
+      "loss": 0.3295,
+      "step": 8000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.679736060431906e-06,
+      "loss": 0.3056,
+      "step": 8500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.8321005917159763,
+      "eval_loss": 0.32298120856285095,
+      "eval_runtime": 8.1227,
+      "eval_samples_per_second": 487.029,
+      "eval_steps_per_second": 7.633,
+      "step": 8903
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.630316318981037e-06,
+      "loss": 0.318,
+      "step": 9000
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.580896577530169e-06,
+      "loss": 0.2982,
+      "step": 9500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.5314768360792997e-06,
+      "loss": 0.2874,
+      "step": 10000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 2.482057094628431e-06,
+      "loss": 0.2856,
+      "step": 10500
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 2.4326373531775623e-06,
+      "loss": 0.3088,
+      "step": 11000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 2.3832176117266936e-06,
+      "loss": 0.2887,
+      "step": 11500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2.333797870275825e-06,
+      "loss": 0.2844,
+      "step": 12000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.2843781288249563e-06,
+      "loss": 0.2884,
+      "step": 12500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 2.2349583873740876e-06,
+      "loss": 0.2838,
+      "step": 13000
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.1855386459232185e-06,
+      "loss": 0.2988,
+      "step": 13500
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.1361189044723498e-06,
+      "loss": 0.2881,
+      "step": 14000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 2.0866991630214815e-06,
+      "loss": 0.2822,
+      "step": 14500
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 2.0372794215706124e-06,
+      "loss": 0.2904,
+      "step": 15000
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 1.9878596801197437e-06,
+      "loss": 0.289,
+      "step": 15500
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.938439938668875e-06,
+      "loss": 0.3042,
+      "step": 16000
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.889020197218006e-06,
+      "loss": 0.286,
+      "step": 16500
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.8396004557671378e-06,
+      "loss": 0.2667,
+      "step": 17000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.790180714316269e-06,
+      "loss": 0.3005,
+      "step": 17500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.8438514244500541,
+      "eval_loss": 0.33582502603530884,
+      "eval_runtime": 8.1185,
+      "eval_samples_per_second": 487.283,
+      "eval_steps_per_second": 7.637,
+      "step": 17806
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 35612,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 7767932240503800.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.5198716650966744e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 35
+  }
+}

run-3/checkpoint-17806/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b03d5f520310321e5fcebd5cc86c2f3104bcd99312aa4df858df6b5d1cd412b2
+size 4664