Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27fa513ba81ff8294def91cdbe7efab084da8262d31de1a21d7e2b069b18cda1
+oid sha256:bf945a4cb72b7f07ea06c29c90ef2dc26fadb9cfd5008c8e15b5640f10cb4dff
 size 267832560

run-9/checkpoint-536/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": "4.44.0",
+  "vocab_size": 30522
+}

run-9/checkpoint-536/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76c0d5552b68ee82bf7cbef28ada26c3fa6ba0f33d9bc536337873d5da3bb765
+size 267832560

run-9/checkpoint-536/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0691a69af72a51165053aff3009103fadc9b7edd3a7caad59ff08568fb3c78d1
+size 535727290

run-9/checkpoint-536/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9e3aaf6b37b75264fbb2c562b3c32515689962db3ac97d7b0606726a5f7b4f
+size 14244

run-9/checkpoint-536/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09c2a1910b62342ff70cf7cd27e4afbb6726e91efbe82d37987e6eb7be5dc39a
+size 1064

run-9/checkpoint-536/special_tokens_map.json

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

run-9/checkpoint-536/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-9/checkpoint-536/trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": 0.44699732518353524,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-536",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 536,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5013087391853333,
+      "eval_matthews_correlation": 0.4182979471843555,
+      "eval_runtime": 0.7144,
+      "eval_samples_per_second": 1460.02,
+      "eval_steps_per_second": 92.389,
+      "step": 268
+    },
+    {
+      "epoch": 1.8656716417910446,
+      "grad_norm": 5.0521626472473145,
+      "learning_rate": 4.459085219377165e-06,
+      "loss": 0.4803,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5291440486907959,
+      "eval_matthews_correlation": 0.44699732518353524,
+      "eval_runtime": 0.8146,
+      "eval_samples_per_second": 1280.378,
+      "eval_steps_per_second": 81.021,
+      "step": 536
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 804,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 98314095087672.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1793106961773818e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 28
+  }
+}

run-9/checkpoint-536/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f19a56ef7d40281592b2e30bbf6caa0b549e649a11a8acc7147b89674c39f156
+size 5240

run-9/checkpoint-804/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": "4.44.0",
+  "vocab_size": 30522
+}

run-9/checkpoint-804/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3b2a832b8174e31d2d454efaae45867b350b38b2b49df22c11446d16ef34636
+size 267832560

run-9/checkpoint-804/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dcdef854847455bc6a38c1ba9b0a39015ca3c2a254c1e561fff35a9471affde
+size 535727290

run-9/checkpoint-804/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:409b9078199aaff19d2f454e6d0a0a6b622f5595cbc7effb5585b7100c2cc7d8
+size 14244

run-9/checkpoint-804/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f288e05d643ee55f63fcc5f8ef4114964eb3ddc33e041c8b08b86fb5fb71cbe
+size 1064

run-9/checkpoint-804/special_tokens_map.json

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

run-9/checkpoint-804/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-9/checkpoint-804/trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 0.46569143021903203,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-804",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 804,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5013087391853333,
+      "eval_matthews_correlation": 0.4182979471843555,
+      "eval_runtime": 0.7144,
+      "eval_samples_per_second": 1460.02,
+      "eval_steps_per_second": 92.389,
+      "step": 268
+    },
+    {
+      "epoch": 1.8656716417910446,
+      "grad_norm": 5.0521626472473145,
+      "learning_rate": 4.459085219377165e-06,
+      "loss": 0.4803,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5291440486907959,
+      "eval_matthews_correlation": 0.44699732518353524,
+      "eval_runtime": 0.8146,
+      "eval_samples_per_second": 1280.378,
+      "eval_steps_per_second": 81.021,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5174696445465088,
+      "eval_matthews_correlation": 0.46569143021903203,
+      "eval_runtime": 0.9044,
+      "eval_samples_per_second": 1153.241,
+      "eval_steps_per_second": 72.976,
+      "step": 804
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 804,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 98314095087672.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1793106961773818e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 28
+  }
+}

run-9/checkpoint-804/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f19a56ef7d40281592b2e30bbf6caa0b549e649a11a8acc7147b89674c39f156
+size 5240

runs/Aug17_02-11-34_b5f02c58e851/events.out.tfevents.1723865896.b5f02c58e851.301.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07f28dc2fc4ed9257843e787243ad221658b687dbcc916cff5e3ed377905dd2f
+size 7589

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f19a56ef7d40281592b2e30bbf6caa0b549e649a11a8acc7147b89674c39f156
+oid sha256:6fa913b6dd4193043ca75983cebb619f3f12421d16f3812039f1dd107acad34f
 size 5240