Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200ee35d297dc8b8e8eb2bd2d9e52426cc400de72560cdb131044b6b73e0b864
+oid sha256:82700449774cce96b693a4c87b08b083e8233ce9ed54d6290f43569a35f749cb
 size 267832560

run-2/checkpoint-4276/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-2/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82700449774cce96b693a4c87b08b083e8233ce9ed54d6290f43569a35f749cb
+size 267832560

run-2/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bce1a13ed5e5a9657c164269557ab8f6f4ea1599abc75fcb8fcc299bb0a197f
+size 535724410

run-2/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8b0fa003be807b362116e9efa03eaa0f9017687da7cec521d6f081fab78dc51
+size 14054

run-2/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac410544bd488aa6c43a13a36f312e27787ff675b026b57d89734f105d4a281c
+size 1064

run-2/checkpoint-4276/special_tokens_map.json

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

run-2/checkpoint-4276/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-2/checkpoint-4276/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.24283245427340167,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-4276",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 3.03009033203125,
+      "learning_rate": 6.435826529339398e-05,
+      "loss": 0.6104,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 3.0893821716308594,
+      "learning_rate": 6.120035237418916e-05,
+      "loss": 0.599,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.689079284667969,
+      "learning_rate": 5.804243945498436e-05,
+      "loss": 0.6233,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.1753005981445312,
+      "learning_rate": 5.488452653577955e-05,
+      "loss": 0.6504,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6044347286224365,
+      "eval_matthews_correlation": 0.16393153624590007,
+      "eval_runtime": 30.5852,
+      "eval_samples_per_second": 34.102,
+      "eval_steps_per_second": 2.158,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 21.40749740600586,
+      "learning_rate": 5.1726613616574746e-05,
+      "loss": 0.5778,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 2.966848850250244,
+      "learning_rate": 4.856870069736993e-05,
+      "loss": 0.5597,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.6385752558708191,
+      "learning_rate": 4.541078777816513e-05,
+      "loss": 0.5879,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 5.519526481628418,
+      "learning_rate": 4.225287485896032e-05,
+      "loss": 0.5867,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6037802696228027,
+      "eval_matthews_correlation": 0.24283245427340167,
+      "eval_runtime": 35.8964,
+      "eval_samples_per_second": 29.056,
+      "eval_steps_per_second": 1.839,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 65355585361128.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.751617821259878e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 13
+  }
+}

run-2/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5c5c7be0f50a61c6e9e22c6c96912df518c2bf9ae78538097c92c4dbd3fca91
+size 4984

runs/Apr22_15-37-01_8b9197ee03bb/events.out.tfevents.1713811054.8b9197ee03bb.4753.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea949f6907a44c92797ee361daf3d5bc3dde3572d3b546c4ec76c9d8cc963bd2
-size 5720
+oid sha256:6fd9b2b1ea1210dbde970c7c3ea79ea4c928dae9e62a3b915d9f1d62972da5b2
+size 6899