Training in progress, epoch 1

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6314
-- Matthews Correlation: 0.5314
+- Loss: 0.8175
+- Matthews Correlation: 0.5370
 
 ## Model description
 
@@ -49,16 +49,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5228        | 1.0   | 535  | 0.4730          | 0.4430               |
-| 0.346         | 2.0   | 1070 | 0.5733          | 0.4414               |
-| 0.241         | 3.0   | 1605 | 0.6314          | 0.5314               |
-| 0.1678        | 4.0   | 2140 | 0.7194          | 0.5265               |
-| 0.1208        | 5.0   | 2675 | 0.8257          | 0.5268               |
+| 0.5266        | 1.0   | 535  | 0.4721          | 0.4559               |
+| 0.3562        | 2.0   | 1070 | 0.5916          | 0.4358               |
+| 0.2416        | 3.0   | 1605 | 0.6296          | 0.5182               |
+| 0.1692        | 4.0   | 2140 | 0.7156          | 0.5330               |
+| 0.1217        | 5.0   | 2675 | 0.8175          | 0.5370               |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu121
+- Transformers 4.36.2
+- Pytorch 2.1.2+cpu
 - Datasets 2.16.1
 - Tokenizers 0.15.0

config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.36.2",
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:852c4bfee02d729aabef162a6c6d78f381524477065a2cbd381954d1bfe04332
+oid sha256:e049a0bb30da1849282ec0d2d5030a6189c285cb614cefd272f6252ffac17172
 size 267832560

run-0/checkpoint-2138/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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e049a0bb30da1849282ec0d2d5030a6189c285cb614cefd272f6252ffac17172
+size 267832560

run-0/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28659f16d8875444a14085d9671fea888c072edb33ff884ea54315f97884bbc4
+size 535724410

run-0/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8c3387534496fab8b68adeb2f30252d96ae79aa9d5aebd9780ccc480b90db8b
+size 13990

run-0/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ec3347ce4d2019db9e253f437042b98d81e32609c1b9b62dba3b2fcda78205
+size 1064

run-0/checkpoint-2138/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-2138/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-2138/trainer_state.json

@@ -0,0 +1,59 @@
+{
+  "best_metric": 0.38219189241772933,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola\\run-0\\checkpoint-2138",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 3.6312236581084424e-06,
+      "loss": 0.6073,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.4530478161992938e-06,
+      "loss": 0.5532,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.274871974290146e-06,
+      "loss": 0.5355,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.0966961323809974e-06,
+      "loss": 0.525,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5965137481689453,
+      "eval_matthews_correlation": 0.38219189241772933,
+      "eval_runtime": 14.186,
+      "eval_samples_per_second": 73.523,
+      "eval_steps_per_second": 4.652,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 32817763115472.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.8093995000175905e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 2
+  }
+}

run-0/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:697b39335203f92964396c6ece9c8f6e3ba7258afd36451c7eead8f43e9818e4
+size 4792

runs/Jan13_22-34-04_DESKTOP-RFEED41/events.out.tfevents.1705163845.DESKTOP-RFEED41.28156.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:787b27e5032ced52bb718258b985b20ef954979aa271df549c9d9c541ea7fe1c
+size 5298

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19b6858c70ed136c051ffc9a1b41b90c1c19153a9114bdd5ede26af8b43d1dd2
-size 4664
+oid sha256:697b39335203f92964396c6ece9c8f6e3ba7258afd36451c7eead8f43e9818e4
+size 4792