Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f613ce1d7632ac94801dd53237c03ff199dfa8afc6e681b64e45cdf992008330
+oid sha256:a79c2da23f1a8aa2d33c0e916ecdcbdf7f935f0328add30b49499a6b07cbd728
 size 267832560

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

run-1/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a79c2da23f1a8aa2d33c0e916ecdcbdf7f935f0328add30b49499a6b07cbd728
+size 267832560

run-1/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426172c1f76f49abd6f80fa403a3900b253c2bad337d2282483bc4897b98cc56
+size 535727290

run-1/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e087b632fb3de78758cb9812f0802011a94c499cf019cab27d0fccec9a15d6f7
+size 14308

run-1/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aac35ab5f532b4778017e0dbaa9399fbb1a9fcf49d6c32e6f7f6c3ca5a44d29
+size 1064

run-1/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-1/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-1/checkpoint-4276/trainer_state.json

@@ -0,0 +1,110 @@
+{
+  "best_metric": 0.528465157424671,
+  "best_model_checkpoint": "andyWuTw/homework001-finetuned-cola/run-1/checkpoint-3207",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.2452452129344327e-05,
+      "loss": 0.5576,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.910338586212613e-05,
+      "loss": 0.5108,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.49123480916023254,
+      "eval_matthews_correlation": 0.4402129756759477,
+      "eval_runtime": 0.7657,
+      "eval_samples_per_second": 1362.107,
+      "eval_steps_per_second": 86.193,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.5754319594907933e-05,
+      "loss": 0.3607,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.2405253327689737e-05,
+      "loss": 0.3536,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5718550682067871,
+      "eval_matthews_correlation": 0.5015124872115657,
+      "eval_runtime": 0.728,
+      "eval_samples_per_second": 1432.68,
+      "eval_steps_per_second": 90.659,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.905618706047154e-05,
+      "loss": 0.254,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.5707120793253344e-05,
+      "loss": 0.2655,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.762388288974762,
+      "eval_matthews_correlation": 0.528465157424671,
+      "eval_runtime": 0.7265,
+      "eval_samples_per_second": 1435.582,
+      "eval_steps_per_second": 90.842,
+      "step": 3207
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 1.2358054526035147e-05,
+      "loss": 0.1973,
+      "step": 3500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 9.008988258816951e-06,
+      "loss": 0.1485,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.010642647743225,
+      "eval_matthews_correlation": 0.5132479296361289,
+      "eval_runtime": 0.7256,
+      "eval_samples_per_second": 1437.459,
+      "eval_steps_per_second": 90.961,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 150515046821328.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.5801518396562525e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 37
+  }
+}

run-1/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0cb55dad53927b5406db1fec190e847582487bb47dbf1f9d20c4d55a9c8beeb
+size 4792

runs/Dec23_02-16-37_5c7585257882/events.out.tfevents.1703298289.5c7585257882.414.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4065d55a8d0576a10d5bf76aa6037c545dbb1dfe1d7a3a8912e7db4ed05e348b
-size 6444
+oid sha256:19c3b1d41522ebf13d5250cb458789d452a5dce010200e51bf3056807902012a
+size 7093