Training in progress, epoch 1

config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.37.2",
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:075b5f45169eb5075fff5b6a8087687c410e7612dca662eed0d618a5380fc64b
+oid sha256:369a9c12ed6162f9841ee96b21a47cdaa5921b66d8e72eb6a26c01451caf4359
 size 267832560

run-0/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-0/checkpoint-17805/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:369a9c12ed6162f9841ee96b21a47cdaa5921b66d8e72eb6a26c01451caf4359
+size 267832560

run-0/checkpoint-17805/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfed7ea52769de767c5cba56bf3bfd7d8e68fcf0f9ee00235e2f64b990db5f5e
+size 535727290

run-0/checkpoint-17805/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:339b0dc101fd05bc3723fb03fb143c9363b46545a39b7003439eaf76e202a0f7
+size 14244

run-0/checkpoint-17805/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3b82aa0acb28b81cbb3518f02663b03a3ed23d3c3ade0beb0cff851ceb9e25c
+size 1064

run-0/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-0/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-0/checkpoint-17805/trainer_state.json

@@ -0,0 +1,245 @@
+{
+  "best_metric": 0.8608981380065718,
+  "best_model_checkpoint": "retrieval_model/run-0/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": 1.7244730277546215e-05,
+      "loss": 0.4798,
+      "step": 500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6746471673745402e-05,
+      "loss": 0.4968,
+      "step": 1000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.6248213069944586e-05,
+      "loss": 0.4581,
+      "step": 1500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.574995446614377e-05,
+      "loss": 0.4369,
+      "step": 2000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.5251695862342956e-05,
+      "loss": 0.4057,
+      "step": 2500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.4753437258542141e-05,
+      "loss": 0.4399,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.4255178654741323e-05,
+      "loss": 0.4089,
+      "step": 3500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.3756920050940509e-05,
+      "loss": 0.3689,
+      "step": 4000
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.3258661447139695e-05,
+      "loss": 0.4282,
+      "step": 4500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.276040284333888e-05,
+      "loss": 0.3937,
+      "step": 5000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.2262144239538062e-05,
+      "loss": 0.3937,
+      "step": 5500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.1763885635737248e-05,
+      "loss": 0.4232,
+      "step": 6000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.1265627031936434e-05,
+      "loss": 0.3982,
+      "step": 6500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.0767368428135619e-05,
+      "loss": 0.3648,
+      "step": 7000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.0269109824334801e-05,
+      "loss": 0.3799,
+      "step": 7500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.770851220533987e-06,
+      "loss": 0.3843,
+      "step": 8000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.272592616733173e-06,
+      "loss": 0.3469,
+      "step": 8500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 8.774334012932356e-06,
+      "loss": 0.4015,
+      "step": 9000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 8.276075409131542e-06,
+      "loss": 0.3851,
+      "step": 9500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 7.777816805330726e-06,
+      "loss": 0.3675,
+      "step": 10000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.2795582015299115e-06,
+      "loss": 0.3621,
+      "step": 10500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.781299597729095e-06,
+      "loss": 0.3752,
+      "step": 11000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 6.283040993928281e-06,
+      "loss": 0.3616,
+      "step": 11500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.784782390127465e-06,
+      "loss": 0.3613,
+      "step": 12000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.2865237863266504e-06,
+      "loss": 0.3535,
+      "step": 12500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.788265182525834e-06,
+      "loss": 0.3479,
+      "step": 13000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.290006578725019e-06,
+      "loss": 0.3831,
+      "step": 13500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.791747974924204e-06,
+      "loss": 0.3841,
+      "step": 14000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.293489371123389e-06,
+      "loss": 0.3524,
+      "step": 14500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.7952307673225737e-06,
+      "loss": 0.3743,
+      "step": 15000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.2969721635217584e-06,
+      "loss": 0.3285,
+      "step": 15500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.798713559720943e-06,
+      "loss": 0.3474,
+      "step": 16000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.3004549559201277e-06,
+      "loss": 0.3736,
+      "step": 16500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 8.021963521193125e-07,
+      "loss": 0.3387,
+      "step": 17000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.039377483184973e-07,
+      "loss": 0.317,
+      "step": 17500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.8608981380065718,
+      "eval_loss": 0.3524799346923828,
+      "eval_runtime": 8.3155,
+      "eval_samples_per_second": 475.74,
+      "eval_steps_per_second": 7.456,
+      "step": 17805
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 17805,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 2755717224437664.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.774298888134703e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 4,
+    "seed": 18
+  }
+}

run-0/checkpoint-17805/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38803918182cee9f58463331c538b1704c52fb48b49366dff7f35059b08fbf3e
+size 4664

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccff9807a64ae3006a89c9a4725b85928db95cc0897bd922a74b715ed489b7c6
-size 4600
+oid sha256:38803918182cee9f58463331c538b1704c52fb48b49366dff7f35059b08fbf3e
+size 4664