Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29022bff9b21dc6fdd4ed82c59bdc34d306e4d0355f8a49346ba76403a372b28
+oid sha256:c37c6734f7c0e231522951b77690479dfc44ca12e5238e6008296ef5497f5249
 size 267832560

run-3/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-3/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c37c6734f7c0e231522951b77690479dfc44ca12e5238e6008296ef5497f5249
+size 267832560

run-3/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e09677f458f793c8f08a8acfa694b9f84cddf5ef35d78743021c8c7b1c3d4c9
+size 535727290

run-3/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a22d1498697868d4fd51fedc2d243dfeb0c202fd49e378d2e958096437df1b02
+size 14244

run-3/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ddc50dabbb34446bd76cd51e86002ef2d9496982b8744d9ef9ed9c98866dfab
+size 1064

run-3/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-3/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-3/checkpoint-2138/trainer_state.json

@@ -0,0 +1,59 @@
+{
+  "best_metric": 0.4471137769925502,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/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": 2.2593712965969752e-05,
+      "loss": 0.6136,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.068352417953335e-05,
+      "loss": 0.5687,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.877333539309695e-05,
+      "loss": 0.5475,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.686314660666055e-05,
+      "loss": 0.5604,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5529224276542664,
+      "eval_matthews_correlation": 0.4471137769925502,
+      "eval_runtime": 0.7648,
+      "eval_samples_per_second": 1363.699,
+      "eval_steps_per_second": 86.293,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6414,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 32633550639216.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.4503901752406154e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 11
+  }
+}

run-3/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d08bfc3d7f49a884fc330f138c816e06fded64aa61c9f76b393d7e45663a9d61
+size 4792

runs/Dec23_02-21-58_39bac3413ec0/events.out.tfevents.1703299109.39bac3413ec0.1762.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8321fb716e676c8275accfe2dcaa253c85566df8f4a536a173d87d6c5a166618
+size 5628

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:919ebdb29df2c4dfd588105d7307257de4b882cebbc2d385c8ded06fba2a3ea0
+oid sha256:d08bfc3d7f49a884fc330f138c816e06fded64aa61c9f76b393d7e45663a9d61
 size 4792