Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d0421dc47b926c2840c228ee01c46404b91fd24388c0d321c2513a6583b59ea
+oid sha256:191f7133f3692ae307d6f068e87f6a9a05228b4352cd68b838cb729c0be9e2e4
 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": "4.40.0",
+  "vocab_size": 30522
+}

run-3/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:191f7133f3692ae307d6f068e87f6a9a05228b4352cd68b838cb729c0be9e2e4
+size 267832560

run-3/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2cf8fc2e7e9824d5909f6a6dff56eb87004ed7889bfd223535eaf1ba59225ae
+size 535724410

run-3/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1a3a374a73b7ed3da59c7bacd91a9963723cf0c787f00fe41756fc6accffa4c
+size 13990

run-3/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a42ac55088e0a4e619ceb5473cd972a810fea7f6d6e3eeeea365cfc2443ff55
+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": 1000000000000000019884624838656,
+  "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 +1,63 @@
+{
+  "best_metric": 0.3296754174940789,
+  "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": 0.23386342376052385,
+      "grad_norm": 3.277184009552002,
+      "learning_rate": 4.2343189505455224e-05,
+      "loss": 0.6317,
+      "step": 500
+    },
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 3.041562795639038,
+      "learning_rate": 2.9417917983643493e-05,
+      "loss": 0.6069,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7015902712815716,
+      "grad_norm": 5.285711765289307,
+      "learning_rate": 1.6492646461831766e-05,
+      "loss": 0.5833,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 13.721405982971191,
+      "learning_rate": 3.5673749400200375e-06,
+      "loss": 0.5335,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.611344575881958,
+      "eval_matthews_correlation": 0.3296754174940789,
+      "eval_runtime": 29.4461,
+      "eval_samples_per_second": 35.421,
+      "eval_steps_per_second": 2.241,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 32604573395760.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.5268461027266954e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 4,
+    "seed": 6
+  }
+}

run-3/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4d1c4b4499c80b69bfed6edd85fe0239996007591da728d83a9275f50ffa4f2
+size 5048

runs/Apr23_13-58-51_309eb7d6022b/events.out.tfevents.1713895855.309eb7d6022b.9612.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8331c6dda86070413b76f0d1e5d7d3838e0e4dadbfa4f3d46a1c6ea30efd28c
+size 6182

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52a3b2e1ec5a1c8f67e0f69b146b5cfc61a90f4dd76ed7c7f6e062bc7284397e
+oid sha256:a4d1c4b4499c80b69bfed6edd85fe0239996007591da728d83a9275f50ffa4f2
 size 5048