Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fce43ae65cd824625a3d3da0f62852b34630ba61166f7cdcfc4c9eb3afcf2ef
+oid sha256:25e2cf606b083f1c3f9ca6ef1dc8d64d999d160a70822da9f82e1c4f2df28db1
 size 267832560

run-0/checkpoint-8904/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-8904/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25e2cf606b083f1c3f9ca6ef1dc8d64d999d160a70822da9f82e1c4f2df28db1
+size 267832560

run-0/checkpoint-8904/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1119dbb15b3ba9064226613e21198aed660d4c9c9de74c9ed74083000ae855
+size 535727290

run-0/checkpoint-8904/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca1f00bd16373184df075867c1257c82b68a14bdad78cf684ef61656bf0b746e
+size 14308

run-0/checkpoint-8904/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44384d6cb5db7df8b2e4b228f72d4570646dcb4ba53aaaa7354f11d93b264e06
+size 1064

run-0/checkpoint-8904/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-8904/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-8904/trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": 0.8342602892102335,
+  "best_model_checkpoint": "retrieval_model/run-0/checkpoint-8904",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 8904,
+  "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
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.2451212130442076e-06,
+      "loss": 0.3137,
+      "step": 4500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.1748230415760387e-06,
+      "loss": 0.304,
+      "step": 5000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.1045248701078698e-06,
+      "loss": 0.2966,
+      "step": 5500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.034226698639701e-06,
+      "loss": 0.2903,
+      "step": 6000
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 9.639285271715318e-07,
+      "loss": 0.287,
+      "step": 6500
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.936303557033631e-07,
+      "loss": 0.2896,
+      "step": 7000
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.233321842351941e-07,
+      "loss": 0.2882,
+      "step": 7500
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.530340127670252e-07,
+      "loss": 0.2879,
+      "step": 8000
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.827358412988563e-07,
+      "loss": 0.2851,
+      "step": 8500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.8342602892102335,
+      "eval_loss": 0.2832660973072052,
+      "eval_runtime": 14.8465,
+      "eval_samples_per_second": 266.459,
+      "eval_steps_per_second": 8.352,
+      "step": 8904
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 13356,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.0058925370663536e+16,
+  "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-8904/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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acb8d50896f51a1aea8d89884c39b9663cd82b6ce9f5f83661bf5f31152b9e51
-size 5834
+oid sha256:aae16c69fd9d256683ff3e9cd7d681d556f4a05ae95e7c4858a925c36783aa2c
+size 7407