Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cc62f265dbdd4dce4a4b6b25bb32be8f2ecef46b94f865d0870bcd119f670ef
+oid sha256:6f8d26d8a66510399de6491695e4b665308e1c7491987faa7235bcc54420c820
 size 267832560

run-1/checkpoint-1069/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-1/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f8d26d8a66510399de6491695e4b665308e1c7491987faa7235bcc54420c820
+size 267832560

run-1/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b15887597a7dbcaaa8bea533a3666a203e968ee857b6a13ff2184de3acaf18ed
+size 535727290

run-1/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b1508d4fc20b6ca93853a77a2f71e62b0450909ed12b516ec2fc689207803cf
+size 14244

run-1/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46299552a9aeaf9ca8965d870cd7f7827cf68056f10c87a37eefc01f5799e5cc
+size 1064

run-1/checkpoint-1069/special_tokens_map.json

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

run-1/checkpoint-1069/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-1/checkpoint-1069/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.4051130128677346,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-1069",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1069,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.972945030670128e-05,
+      "loss": 0.5666,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.0654526525656932e-05,
+      "loss": 0.5211,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5038339495658875,
+      "eval_matthews_correlation": 0.4051130128677346,
+      "eval_runtime": 0.7912,
+      "eval_samples_per_second": 1318.257,
+      "eval_steps_per_second": 83.418,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 37877396803200.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.8804374087745627e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 18
+  }
+}

run-1/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:909fa524061d6512cdc9000093fba071240645db37ca2a337df7a8b6661c2561
+size 4792

runs/Dec22_07-12-50_84c4b1f8dc6c/events.out.tfevents.1703229756.84c4b1f8dc6c.518.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41bf3f31d93b1c295224953698794183324f47fa3682b2274ba75b099531ed91
+size 5147

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04cdafb2f3028d92aeb215c4f9ee1fa4b2ece61c011af271e09c318dcf8f36fa
+oid sha256:909fa524061d6512cdc9000093fba071240645db37ca2a337df7a8b6661c2561
 size 4792