Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd4ff0b04a1c29d8dab4049b6898f7bb9e043588457740fb3028145ddd806bda
+oid sha256:01c9a031d4b05ca791d5d2258eb2dfd30c78d58dc694bafda04a41c3bd8dc5d9
 size 267832560

run-0/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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-6414/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01c9a031d4b05ca791d5d2258eb2dfd30c78d58dc694bafda04a41c3bd8dc5d9
+size 267832560

run-0/checkpoint-6414/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc3b3750d25021ce3761f297443ab88cc8e87592c5f591e8a474ece27493e3cf
+size 535727290

run-0/checkpoint-6414/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f43152131e10c6c8143d67baee00885c80b1a35a86db3d8292e59d743842c36
+size 14308

run-0/checkpoint-6414/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:174de4719892ed29785c2ab8906215b0e8e51f0febfbfa446b5d4bc0f952249e
+size 1064

run-0/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-0/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-0/checkpoint-6414/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": 0.4870956322514055,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/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,
+      "learning_rate": 5.91742027348343e-06,
+      "loss": 0.5938,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.417131105958622e-06,
+      "loss": 0.5555,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.916841938433813e-06,
+      "loss": 0.5251,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.416552770909005e-06,
+      "loss": 0.5221,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6011144518852234,
+      "eval_matthews_correlation": 0.41217715910488273,
+      "eval_runtime": 0.7317,
+      "eval_samples_per_second": 1425.43,
+      "eval_steps_per_second": 90.2,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.9162636033841975e-06,
+      "loss": 0.4843,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 3.415974435859389e-06,
+      "loss": 0.4811,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2.915685268334581e-06,
+      "loss": 0.5,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.4153961008097733e-06,
+      "loss": 0.5042,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8069911599159241,
+      "eval_matthews_correlation": 0.4682662585067061,
+      "eval_runtime": 0.7303,
+      "eval_samples_per_second": 1428.269,
+      "eval_steps_per_second": 90.379,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.915106933284965e-06,
+      "loss": 0.4338,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.4148177657601572e-06,
+      "loss": 0.4198,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 9.145285982353492e-07,
+      "loss": 0.3733,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 4.142394307105411e-07,
+      "loss": 0.4857,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.864135205745697,
+      "eval_matthews_correlation": 0.4870956322514055,
+      "eval_runtime": 0.7392,
+      "eval_samples_per_second": 1410.893,
+      "eval_steps_per_second": 89.28,
+      "step": 6414
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6414,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 97604928799164.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.417709441008238e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 21
+  }
+}

run-0/checkpoint-6414/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4063d9de97922d812e03e8651332eb06da84b3626a2c3f00672854c323e1627
+size 4792

runs/Dec23_02-10-12_067bf7a71e5c/events.out.tfevents.1703298002.067bf7a71e5c.178.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e483cb293a402b8c6cc51f6127a4214cd7b90357783692d765f3199b21b5e84
-size 6274
+oid sha256:e61e2a6d996cf11d4cbf84768ede930ad88db25dd086201e83d597a2a7d330ad
+size 7591