Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad6f9d4ac3c9f752fff20182a38f207952142299b5715678edf2d3e8f5cd6273
+oid sha256:e291c47e7d9d5a05d2c7760597db9b7aa7570086ca78ef91651159ece4e1b91c
 size 267832560

run-4/checkpoint-4276/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": "4.36.0",
+  "vocab_size": 30522
+}

run-4/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e291c47e7d9d5a05d2c7760597db9b7aa7570086ca78ef91651159ece4e1b91c
+size 267832560

run-4/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:739ca7bb21ad72daea8061dafe301ade702f38fe5720c1eb9868ee4f9a98673e
+size 535724410

run-4/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1419ae4dcc8ff4ee69bcd4528df393071c1e42f3853e0633e694de255d7ad221
+size 13990

run-4/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3bec17659bceda576c0839dc8cec4d6140f3769499ba48c90405c52fb58160c
+size 1064

run-4/checkpoint-4276/special_tokens_map.json

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

run-4/checkpoint-4276/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-4/checkpoint-4276/trainer_state.json

@@ -0,0 +1,92 @@
+{
+  "best_metric": 0.47375271850377065,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola\\run-4\\checkpoint-4276",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 6.042296562538321e-06,
+      "loss": 0.606,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.242204327032718e-06,
+      "loss": 0.5464,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.442112091527114e-06,
+      "loss": 0.5152,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.642019856021509e-06,
+      "loss": 0.5153,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5116811394691467,
+      "eval_matthews_correlation": 0.46741180953359257,
+      "eval_runtime": 5.9325,
+      "eval_samples_per_second": 175.81,
+      "eval_steps_per_second": 11.125,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 2.8419276205159054e-06,
+      "loss": 0.4465,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.041835385010301e-06,
+      "loss": 0.4589,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.2417431495046974e-06,
+      "loss": 0.527,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 4.4165091399909343e-07,
+      "loss": 0.5133,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7559528946876526,
+      "eval_matthews_correlation": 0.47375271850377065,
+      "eval_runtime": 5.972,
+      "eval_samples_per_second": 174.648,
+      "eval_steps_per_second": 11.052,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4276,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 65223117962472.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.842388798043926e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 4,
+    "seed": 11
+  }
+}

run-4/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:286ee074d165e0e383ffaa7595ee0c7093832221ee96e7ed3f9a6dcd9c5b653b
+size 4792

runs/Dec12_14-52-17_DESKTOP-UUVDD26/events.out.tfevents.1702385782.DESKTOP-UUVDD26.9476.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35a951cccc2ee597f97d10b668650d1acda5f8cf2f8da9545f87042a671c1a9d
-size 5298
+oid sha256:e1c6e5b195bfc22632c5fc5dbedb84598655120f2b30b13bcd3378802ef15190
+size 6615