Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f355ff596fc9a81f9d48fca17727279c1b8e426ea17d864e94ad0fad9e40bae7
+oid sha256:4662f4e8dc27c8b2567b4f06b9dbafd4f1b814ede8a5f6f32991cd0b16885e0e
 size 267832560

run-3/checkpoint-108/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": "4.38.1",
+  "vocab_size": 30522
+}

run-3/checkpoint-108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b50cf92e15427cb5acded6800ce4d2860b54d7da9b03bb0c2ba4c2994775180a
+size 267832560

run-3/checkpoint-108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c0a9e13a7fea4467c951156668a0317e7760301147a6beff32f0d9b4ff98717
+size 535727290

run-3/checkpoint-108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00e7e60447fe6b0b398d23f91b0df5696220d68e25fe4da0911193612264b803
+size 14244

run-3/checkpoint-108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86e7323a38bbdac6a3c6b0caf8dd3486670af3378fb8f117be694180e2e637a5
+size 1064

run-3/checkpoint-108/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-108/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-108/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-54",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 108,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.604997992515564,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.892,
+      "eval_samples_per_second": 1169.223,
+      "eval_steps_per_second": 73.987,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.591522753238678,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7773,
+      "eval_samples_per_second": 1341.91,
+      "eval_steps_per_second": 84.915,
+      "step": 108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.793684226638268e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 28
+  }
+}

run-3/checkpoint-108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30b316a20f512911d47be6738bfd2ac40f20563dc31b2024eb75a8ec5063b977
+size 4984

run-4/checkpoint-27/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:452d9ed5c0693a004691e67d1911da2f6d537364410446882d40da14ca1013e6
+oid sha256:4662f4e8dc27c8b2567b4f06b9dbafd4f1b814ede8a5f6f32991cd0b16885e0e
 size 267832560

run-4/checkpoint-27/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:233b32821c04e7d257ced441ce372d319cb37cf8b4e08fbd506338394534c98d
+oid sha256:7461432f8c5c7e3ac83d8eccc633ea013a4051568d2370cc7410ec7a77fcc6b4
 size 535727290

run-4/checkpoint-27/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22f40887a9aa64436f373c2378e34877cfef171d5714e7005f6563bf4cdadc6d
-size 14308
+oid sha256:82f521cf7e0b4cecdee8f34e844c1c53c70cbd348a9c73b185cbecee5d66c082
+size 14244

run-4/checkpoint-27/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98bf207cfd1ec6f6d8b697af5d991998619464355e7bd6e2c5860b6b61e2129b
+oid sha256:1f6cf700c91f931dcb2328a6f2b6bec4de3ce4c0bb5113ea14bbc6eb99282a9c
 size 1064

run-4/checkpoint-27/trainer_state.json

@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6120168566703796,
+      "eval_loss": 0.6172463297843933,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.7721,
-      "eval_samples_per_second": 1350.817,
-      "eval_steps_per_second": 85.478,
+      "eval_runtime": 0.7437,
+      "eval_samples_per_second": 1402.475,
+      "eval_steps_per_second": 88.747,
       "step": 27
     }
   ],
   "logging_steps": 500,
-  "max_steps": 27,
+  "max_steps": 108,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 3.2325188353509425e-05,
-    "num_train_epochs": 1,
+    "learning_rate": 6.784461117596466e-06,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 32,
-    "seed": 21
+    "seed": 15
   }
 }

run-4/checkpoint-27/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ee9986d9b661a8f174bb45702ca19392adb431444c463e3ab467cc87e880e2b
+oid sha256:443eb1867eb54327e419f78e290432cb32b5c391fff06995ea104f10aaafb654
 size 4984

runs/Feb27_14-43-24_1abfc43efc69/events.out.tfevents.1709045827.1abfc43efc69.155.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05c15de59161d5a10d7334d22b99075d02a712d58c2afb75ad7156cfc791c24
+size 6206

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30b316a20f512911d47be6738bfd2ac40f20563dc31b2024eb75a8ec5063b977
+oid sha256:443eb1867eb54327e419f78e290432cb32b5c391fff06995ea104f10aaafb654
 size 4984