Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:369a9c12ed6162f9841ee96b21a47cdaa5921b66d8e72eb6a26c01451caf4359
+oid sha256:8e3139795994fe58ebae8dff0d22e397447333f436eaec59e29fafc3d1607517
 size 267832560

run-1/checkpoint-17805/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-1/checkpoint-17805/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e3139795994fe58ebae8dff0d22e397447333f436eaec59e29fafc3d1607517
+size 267832560

run-1/checkpoint-17805/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0186f85a5fbc59de363888f3ac264fb7a53542e7ccaf2e4dffef3ec33e9d7d8
+size 535727290

run-1/checkpoint-17805/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2922e74a595e0d222270a7bd4805435cd54d2fabccf6a31f7665d89c31fc9d6b
+size 14244

run-1/checkpoint-17805/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d00818d944a68f6f867764041c69327f1dd4399641fcf3f2aa0f0d00c7b0dafa
+size 1064

run-1/checkpoint-17805/special_tokens_map.json

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

run-1/checkpoint-17805/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-1/checkpoint-17805/trainer_state.json

@@ -0,0 +1,245 @@
+{
+  "best_metric": 0.8397058823529412,
+  "best_model_checkpoint": "retrieval_model/run-1/checkpoint-17805",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 17805,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.996054434429772e-06,
+      "loss": 0.4883,
+      "step": 500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 5.822808134677396e-06,
+      "loss": 0.461,
+      "step": 1000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 5.649561834925018e-06,
+      "loss": 0.4252,
+      "step": 1500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 5.476315535172641e-06,
+      "loss": 0.4726,
+      "step": 2000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 5.3030692354202634e-06,
+      "loss": 0.4414,
+      "step": 2500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 5.129822935667887e-06,
+      "loss": 0.4246,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.956576635915509e-06,
+      "loss": 0.4483,
+      "step": 3500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.783330336163132e-06,
+      "loss": 0.4054,
+      "step": 4000
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.610084036410755e-06,
+      "loss": 0.424,
+      "step": 4500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.4368377366583785e-06,
+      "loss": 0.4262,
+      "step": 5000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.263591436906001e-06,
+      "loss": 0.3839,
+      "step": 5500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.090345137153624e-06,
+      "loss": 0.4169,
+      "step": 6000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.917098837401247e-06,
+      "loss": 0.4181,
+      "step": 6500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.74385253764887e-06,
+      "loss": 0.4383,
+      "step": 7000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.5706062378964923e-06,
+      "loss": 0.4181,
+      "step": 7500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.3973599381441155e-06,
+      "loss": 0.4204,
+      "step": 8000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 3.2241136383917382e-06,
+      "loss": 0.3985,
+      "step": 8500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 3.050867338639361e-06,
+      "loss": 0.3914,
+      "step": 9000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.877621038886984e-06,
+      "loss": 0.4033,
+      "step": 9500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.704374739134607e-06,
+      "loss": 0.3896,
+      "step": 10000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.5311284393822297e-06,
+      "loss": 0.3972,
+      "step": 10500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.3578821396298524e-06,
+      "loss": 0.3872,
+      "step": 11000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.1846358398774756e-06,
+      "loss": 0.3979,
+      "step": 11500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.0113895401250984e-06,
+      "loss": 0.4093,
+      "step": 12000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.8381432403727214e-06,
+      "loss": 0.4108,
+      "step": 12500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.6648969406203441e-06,
+      "loss": 0.4237,
+      "step": 13000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.4916506408679669e-06,
+      "loss": 0.3668,
+      "step": 13500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.3184043411155898e-06,
+      "loss": 0.3956,
+      "step": 14000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.1451580413632128e-06,
+      "loss": 0.4561,
+      "step": 14500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 9.719117416108356e-07,
+      "loss": 0.3957,
+      "step": 15000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 7.986654418584585e-07,
+      "loss": 0.4191,
+      "step": 15500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.254191421060814e-07,
+      "loss": 0.3459,
+      "step": 16000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.521728423537043e-07,
+      "loss": 0.3571,
+      "step": 16500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.7892654260132714e-07,
+      "loss": 0.3998,
+      "step": 17000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0568024284895004e-07,
+      "loss": 0.3398,
+      "step": 17500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.8397058823529412,
+      "eval_loss": 0.42075324058532715,
+      "eval_runtime": 8.1438,
+      "eval_samples_per_second": 485.771,
+      "eval_steps_per_second": 7.613,
+      "step": 17805
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 17805,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 2756639321720496.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.169300734182149e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 4,
+    "seed": 2
+  }
+}

run-1/checkpoint-17805/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e54dc41d6ac230e0d0c0f42e6c374dbc1aeb8a58f555a507136f2227c8ba5626
+size 4664

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38803918182cee9f58463331c538b1704c52fb48b49366dff7f35059b08fbf3e
+oid sha256:e54dc41d6ac230e0d0c0f42e6c374dbc1aeb8a58f555a507136f2227c8ba5626
 size 4664