Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fa0198d1d8cb8b95f8e378ff78e1fe169ae40ea2fa6c2d7da9bf5ef5385aa48
+oid sha256:61e796889a69a7eaf0ead60a93fac728cc39da1171085a5f9c7f542ed37454c5
 size 267832560

run-7/checkpoint-214/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-7/checkpoint-214/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61e796889a69a7eaf0ead60a93fac728cc39da1171085a5f9c7f542ed37454c5
+size 267832560

run-7/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89276cdc4962b7678959911b389532fbe10dd37bf3d4644b7d779c03ee9f968c
+size 535727290

run-7/checkpoint-214/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cec6f73cb52d24443a174a02cdf80165fdfa43697bf4bf4d96cb9fa57cd42ba2
+size 14308

run-7/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e82272ae298fab1fde74b59282fbee675a7a2502a317d37e9de4ba980f3a3fd
+size 1064

run-7/checkpoint-214/special_tokens_map.json

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

run-7/checkpoint-214/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-7/checkpoint-214/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-214",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 214,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6352456212043762,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7521,
+      "eval_samples_per_second": 1386.822,
+      "eval_steps_per_second": 87.757,
+      "step": 214
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 856,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1428406195594783e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 32
+  }
+}

run-7/checkpoint-214/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d193ed91fad8ec59b2a381b19b8036af181988e7ec363fbcd9b2ad694486250a
+size 4984

runs/Feb27_13-14-59_9ced9ff90bdb/events.out.tfevents.1709040248.9ced9ff90bdb.370.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e3d005ea1b6d0d7e8ae570a11b49bf22cfb8783d1c825111f42f8f2d47f9a65
+size 4870

runs/Feb27_13-14-59_9ced9ff90bdb/events.out.tfevents.1709040253.9ced9ff90bdb.370.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbfe9fd8a2205872e0af5580b05088d3c1f5e14de67fd983c93d3d163479327a
+size 5212

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4505165cc7e056cd3ccf3b568f54a9c94651de4452d938bcb49a1cf62c2af6cd
+oid sha256:d193ed91fad8ec59b2a381b19b8036af181988e7ec363fbcd9b2ad694486250a
 size 4984