Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a02e2c24c0fdd8f5083d2e6e2c4107ebfd081d977d7185b31c9052985c1a6c2
+oid sha256:5bae73aa675405034dd7d3cf5d75c4209490d3e4d1c6770cefd4fd0d162ce644
 size 267832560

run-1/checkpoint-5345/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": "4.36.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-5345/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bae73aa675405034dd7d3cf5d75c4209490d3e4d1c6770cefd4fd0d162ce644
+size 267832560

run-1/checkpoint-5345/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2f4512df8227c7268596c747eb4ef4743849009fdb7b615e36597a1f9941e50
+size 535727290

run-1/checkpoint-5345/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bfe567e87bf332c7040dab620d015c1e14d6f1adb044e988bdc1697a1045fdf
+size 14308

run-1/checkpoint-5345/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6be68280c6cad653ddf023f882c8a0dc1b160d738863d15daa046eb0adca48c4
+size 1064

run-1/checkpoint-5345/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-5345/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-5345/trainer_state.json

@@ -0,0 +1,131 @@
+{
+  "best_metric": 0.43624361512112764,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola-hw01/run-1/checkpoint-5345",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 5345,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.078291678610645e-06,
+      "loss": 0.6042,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8638136932019094e-06,
+      "loss": 0.5588,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5511462092399597,
+      "eval_matthews_correlation": 0.25695053268608636,
+      "eval_runtime": 0.7145,
+      "eval_samples_per_second": 1459.727,
+      "eval_steps_per_second": 92.37,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.6493357077931742e-06,
+      "loss": 0.507,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.4348577223844388e-06,
+      "loss": 0.4874,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5382365584373474,
+      "eval_matthews_correlation": 0.37605227228925864,
+      "eval_runtime": 0.8002,
+      "eval_samples_per_second": 1303.369,
+      "eval_steps_per_second": 82.476,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.2203797369757036e-06,
+      "loss": 0.4502,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.0059017515669684e-06,
+      "loss": 0.4544,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5281487107276917,
+      "eval_matthews_correlation": 0.4190778231127276,
+      "eval_runtime": 0.7566,
+      "eval_samples_per_second": 1378.583,
+      "eval_steps_per_second": 87.235,
+      "step": 3207
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 7.914237661582331e-07,
+      "loss": 0.4218,
+      "step": 3500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 5.769457807494979e-07,
+      "loss": 0.4095,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5424095392227173,
+      "eval_matthews_correlation": 0.43075140568698755,
+      "eval_runtime": 0.76,
+      "eval_samples_per_second": 1372.333,
+      "eval_steps_per_second": 86.84,
+      "step": 4276
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 3.6246779534076256e-07,
+      "loss": 0.4078,
+      "step": 4500
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 1.4798980993202734e-07,
+      "loss": 0.4003,
+      "step": 5000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5456374287605286,
+      "eval_matthews_correlation": 0.43624361512112764,
+      "eval_runtime": 0.7453,
+      "eval_samples_per_second": 1399.41,
+      "eval_steps_per_second": 88.553,
+      "step": 5345
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 188676524100552.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.29276966401938e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 13
+  }
+}

run-1/checkpoint-5345/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a69489651161291c5d60c71fe0449b5d4a343856d5bdde066b2e1b8ad0ce6c
+size 4792

runs/Dec23_02-10-25_786cd877caf6/events.out.tfevents.1703298068.786cd877caf6.1133.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29380047670d1eadfc9da8248449c39781dc22c9264d6e1346a31171766e9948
-size 7114
+oid sha256:971bc5818dcbf4badcfdb7ac499b46621583b76d24c6f470af75b764aa388ac3
+size 7960