Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da2395699d68956e79a93b889d16f2bdfe5a282152c0c0c46c6dc4a9cc283eb5
+oid sha256:d831d84203b749fee322a238e2b51c26274efac8e623beac8c7e20f6ccd628e8
 size 267832560

run-4/checkpoint-535/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": "4.35.2",
+  "vocab_size": 30522
+}

run-4/checkpoint-535/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d831d84203b749fee322a238e2b51c26274efac8e623beac8c7e20f6ccd628e8
+size 267832560

run-4/checkpoint-535/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27187d7913d7f4badeddc5049b21334c0d880997f7a6c884485c686b5eceaee0
+size 535727290

run-4/checkpoint-535/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fb5a93d038824f0b97429e5931755b807dfb1cb997edb698fdac3d9f175a1c6
+size 14308

run-4/checkpoint-535/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59e1f4823a8d56e9a18b16a337e783f644a00e97ae0464a171284c8f94bf9aed
+size 1064

run-4/checkpoint-535/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-535/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-535/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 0.42602448983421265,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-535",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 535,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.177733965790665e-05,
+      "loss": 0.5312,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5129074454307556,
+      "eval_matthews_correlation": 0.42602448983421265,
+      "eval_runtime": 0.5399,
+      "eval_samples_per_second": 1932.01,
+      "eval_steps_per_second": 122.256,
+      "step": 535
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1605,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 42749713310016.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.615622638094134e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 31
+  }
+}

run-4/checkpoint-535/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e0711ff1c5b62a69433b342e2e24f1332b672cefd16a4a41c0a137742f7cecf
+size 4664

runs/Jan08_03-19-08_fe6f5592002e/events.out.tfevents.1704685456.fe6f5592002e.4919.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11614e7fdbcba67f9a5c5a4b79556c4ff5e6733372b0cf9c08e474f4935f258a
+size 5174

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d9652ca70b9356bfe903224a7f680aae42d19a272404f4ab3eb2f1f5240a517
+oid sha256:9e0711ff1c5b62a69433b342e2e24f1332b672cefd16a4a41c0a137742f7cecf
 size 4664