Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50d5be2b06d0dd7daad8eea903a8cd5fe8ed8e054e1e9876149ced132cc3fe66
+oid sha256:4b60f5d2c0ab42107b330cf0bb13ccc15f664fa6dc3f068acb29f8e2d6243080
 size 267832560

run-6/checkpoint-6414/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-6/checkpoint-6414/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b60f5d2c0ab42107b330cf0bb13ccc15f664fa6dc3f068acb29f8e2d6243080
+size 267832560

run-6/checkpoint-6414/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd296223feb667789366a3e7014341395271193e5ccc0ff419825224129797d2
+size 535727290

run-6/checkpoint-6414/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c179957f0ec81a94ca288583bbb51e046d15b3e8ef952992b6155b8fc5a8757c
+size 14244

run-6/checkpoint-6414/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac28941ef16aadb857f272a4d8652f192ba3f4d4a718ff2ef072588b595804dd
+size 1064

run-6/checkpoint-6414/special_tokens_map.json

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

run-6/checkpoint-6414/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-6/checkpoint-6414/trainer_state.json

@@ -0,0 +1,137 @@
+{
+  "best_metric": 0.5245014079698576,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-6414",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6414,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 17.90995979309082,
+      "learning_rate": 1.8573493164868257e-05,
+      "loss": 0.6076,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 25.591594696044922,
+      "learning_rate": 1.700319445292471e-05,
+      "loss": 0.5721,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 17.508258819580078,
+      "learning_rate": 1.5432895740981165e-05,
+      "loss": 0.5514,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 47.17720031738281,
+      "learning_rate": 1.3862597029037618e-05,
+      "loss": 0.5529,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4856245219707489,
+      "eval_matthews_correlation": 0.47921629302778096,
+      "eval_runtime": 0.8291,
+      "eval_samples_per_second": 1258.047,
+      "eval_steps_per_second": 79.608,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.4112852215766907,
+      "learning_rate": 1.2292298317094074e-05,
+      "loss": 0.4362,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 34.63631057739258,
+      "learning_rate": 1.0721999605150526e-05,
+      "loss": 0.435,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.18024270236492157,
+      "learning_rate": 9.151700893206982e-06,
+      "loss": 0.4341,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.2709442675113678,
+      "learning_rate": 7.581402181263437e-06,
+      "loss": 0.4354,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7808897495269775,
+      "eval_matthews_correlation": 0.4758828120362657,
+      "eval_runtime": 0.7521,
+      "eval_samples_per_second": 1386.711,
+      "eval_steps_per_second": 87.75,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 68.71192169189453,
+      "learning_rate": 6.011103469319891e-06,
+      "loss": 0.3867,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.26191192865371704,
+      "learning_rate": 4.440804757376346e-06,
+      "loss": 0.2848,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.26115551590919495,
+      "learning_rate": 2.8705060454328013e-06,
+      "loss": 0.2901,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 0.08103559166193008,
+      "learning_rate": 1.3002073334892556e-06,
+      "loss": 0.281,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9468569755554199,
+      "eval_matthews_correlation": 0.5245014079698576,
+      "eval_runtime": 0.7366,
+      "eval_samples_per_second": 1415.874,
+      "eval_steps_per_second": 89.595,
+      "step": 6414
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6414,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 149328014741184.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.01437918768118e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 9
+  }
+}

run-6/checkpoint-6414/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c579802743ec5bde7ffe4a1b22c8900fae6cd071e374192c2957c3eec29367
+size 4984

runs/Mar16_01-46-29_6e5f088ca464/events.out.tfevents.1710555138.6e5f088ca464.226.8

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb806ec7dd4520dcc7a2a23439a02606f88eb50f8198c837ad3e9cee52f6bf73
-size 7788
+oid sha256:dcc909bb8cdfb39bc73a33575436d826280eb53e19eeb6e941fc513484f4383e
+size 8477