Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:928dcf00535efbf95f39352222d917d8416d315f9dd9e01c737a8dfbccd664d7
+oid sha256:aacb937a2e844d5a55f60844ce1cb173ad39949ddccb0cddbbc62c5b9fc8eba8
 size 267832560

run-1/checkpoint-642/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-1/checkpoint-642/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aacb937a2e844d5a55f60844ce1cb173ad39949ddccb0cddbbc62c5b9fc8eba8
+size 267832560

run-1/checkpoint-642/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8793d8b1317578e2cf710862b72b3357d7bfd7245c85f7256ac6c4995d04ea9
+size 535724410

run-1/checkpoint-642/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f775e29fe75d4dbb753221bbcc71e9ab687aa63e323123ef6775c451b530065e
+size 13990

run-1/checkpoint-642/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13b2b56e23550a4eb32f88d2098800c2568d2acfd8da5565eac3043e2b19b423
+size 1064

run-1/checkpoint-642/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-642/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-642/trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_metric": 0.31403563513642563,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-642",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 642,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5608745217323303,
+      "eval_matthews_correlation": 0.24840160003533945,
+      "eval_runtime": 9.2451,
+      "eval_samples_per_second": 112.816,
+      "eval_steps_per_second": 7.139,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.0266742706298828,
+      "eval_matthews_correlation": 0.3036582497219888,
+      "eval_runtime": 9.8473,
+      "eval_samples_per_second": 105.917,
+      "eval_steps_per_second": 6.702,
+      "step": 428
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 6.674153804779053,
+      "learning_rate": 7.64701112872254e-06,
+      "loss": 0.4638,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.230393409729004,
+      "eval_matthews_correlation": 0.31403563513642563,
+      "eval_runtime": 8.8435,
+      "eval_samples_per_second": 117.94,
+      "eval_steps_per_second": 7.463,
+      "step": 642
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 642,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 8381150218872.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.4573106652393455e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 34
+  }
+}

run-1/checkpoint-642/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88810bb43620f039cd2ce7bddf99dc02b110c21bc4146650633e1cff2129aa10
+size 4984

runs/Mar06_18-56-30_6942db43b48a/events.out.tfevents.1709753366.6942db43b48a.1479.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60a28fed285bdb7b6f059dd4b1d9cfb22b4566a483f29f1c4390642dba92fcb4
-size 5212
+oid sha256:7aa65b5e9d8a972531f178da05e378350321b91959ce9a4db582da2c6122aacb
+size 6112