Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc8900deb741c06fd2ef8ce50333046b90725a0ec464e0f1ebe44f3b10892c55
+oid sha256:8e86f473bce5bc106516c823de685d7f8a5f9fb1d929e8a68aabad4f7537dd01
 size 267832560

run-5/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": "4.37.2",
+  "vocab_size": 30522
+}

run-5/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e86f473bce5bc106516c823de685d7f8a5f9fb1d929e8a68aabad4f7537dd01
+size 267832560

run-5/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1551019922e1891052a1e8a13c5860c02a88b383e37d979e69baa30ef305e5ca
+size 535727290

run-5/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32a1bc6407a2d5b3e9fc976e0e4eac012833775e16a6e2d36ee64ba279cfa103
+size 14308

run-5/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c676628bc1e40a927e24d73a2bca1aa8a6ecf18f875f958a2dc08a3a5cc225bf
+size 1064

run-5/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-5/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-5/checkpoint-4276/trainer_state.json

@@ -0,0 +1,92 @@
+{
+  "best_metric": 0.4774039469283523,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/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,
+      "learning_rate": 1.0558259731736587e-05,
+      "loss": 0.5657,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.160185085055365e-06,
+      "loss": 0.543,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.762110438374143e-06,
+      "loss": 0.542,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 6.3640357916929215e-06,
+      "loss": 0.51,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.632324755191803,
+      "eval_matthews_correlation": 0.42751732583319796,
+      "eval_runtime": 0.7248,
+      "eval_samples_per_second": 1439.069,
+      "eval_steps_per_second": 91.063,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 4.9659611450117004e-06,
+      "loss": 0.4411,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 3.567886498330478e-06,
+      "loss": 0.444,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2.169811851649256e-06,
+      "loss": 0.4384,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 7.717372049680345e-07,
+      "loss": 0.4431,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8114245533943176,
+      "eval_matthews_correlation": 0.4774039469283523,
+      "eval_runtime": 0.7725,
+      "eval_samples_per_second": 1350.209,
+      "eval_steps_per_second": 85.44,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4276,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 65376283392168.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.195633437841781e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 4,
+    "seed": 17
+  }
+}

run-5/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73e39bf4dee25b10abf7d7506dfce380b8e74cbcd0a183464d4d3103ba37015d
+size 4792

runs/Feb07_07-45-57_5815a830ed1c/events.out.tfevents.1707293355.5815a830ed1c.392.7

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db0a91e0b9de295845af2d08cbf9c002bb362ced26cc901b8e530526c09f853c
-size 5630
+oid sha256:9d5ea2de575fc8db3b0eeb6aaf6f13a869aca574a95009a50de7d701e4a9eea1
+size 6633