Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa36847c4a846d86fcc41acc57631d6a768fdb9c50f83720e9273fe30df0be70
+oid sha256:f5c1c05442affdf3b39fba5107e6fd5278e730a1d99401a107b04ca29b5908b8
 size 267832560

run-3/checkpoint-28/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": "4.38.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-28/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4915d94c75b7910d101b59936db74a6ac7e0a40b9d06397a558c714175ecc6c6
+size 267832560

run-3/checkpoint-28/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52ed2ee9516d178e7232100f3feb065a36a181a9a2aa270815156e78377b4cc2
+size 535727290

run-3/checkpoint-28/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5197778b13fdd3d29d0d2bd5a3963b7496971abf30b91e7dc44d73ee41788c0
+size 14308

run-3/checkpoint-28/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdc855975f84b24bb3a06f4e3f85e10c44cb1c2a8dca33e3d623b3bbe8faea25
+size 1064

run-3/checkpoint-28/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-28/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-28/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-14",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 28,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6361618041992188,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7041,
+      "eval_samples_per_second": 1481.307,
+      "eval_steps_per_second": 93.736,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6270348429679871,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7614,
+      "eval_samples_per_second": 1369.848,
+      "eval_steps_per_second": 86.683,
+      "step": 28
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 28,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.334022097714822e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 64,
+    "seed": 26
+  }
+}

run-3/checkpoint-28/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd6254a4bc0329126eea9d9960e7f3eccfaad75afcb4434d09492043fb5191f9
+size 4984

runs/Mar08_15-33-58_7fccc33f1b3d/events.out.tfevents.1709913093.7fccc33f1b3d.260.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa8f2e29c7630f77801d7e3ddd6efaf9c1a302be19baf33479839db06beb6c01
+size 5219

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd6254a4bc0329126eea9d9960e7f3eccfaad75afcb4434d09492043fb5191f9
+oid sha256:60650c8b709c56b5edcee76063497a3ac16b5d2ecf42250082212586a5bd8442
 size 4984