Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ccdf837c8ebda4caa44681d02bb2d6ae6b721c17415e8e1a9bdb75243aad05a
+oid sha256:945826e2756aee187ff6d9bdd54154b39351f77603e0170a083bc3c49be4ee68
 size 267832560

run-1/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": "4.35.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-536/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d98edead287397dbc85e9965e55e0e9a63f182e2ec349fac928973b841db896
+size 267832560

run-1/checkpoint-536/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af1eb72f05bdc789e62e12a02f45666b68ffc9a9e3b265cf587c59eb4f859615
+size 535727290

run-1/checkpoint-536/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ebe287cfea3dfa72a8b1b6f7c5dca99ab99027833636d010a42c39c8d98519
+size 14244

run-1/checkpoint-536/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:131ccd977f9f8b655127b0bfc9d5858f739a5117dd5605449b2124dee8f1f1b2
+size 1064

run-1/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-1/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-1/checkpoint-536/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": 0.4810794261012942,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/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": 0.4801884889602661,
+      "eval_matthews_correlation": 0.4522326299878879,
+      "eval_runtime": 0.6893,
+      "eval_samples_per_second": 1513.095,
+      "eval_steps_per_second": 95.747,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0329146614031314e-05,
+      "loss": 0.4583,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5012368559837341,
+      "eval_matthews_correlation": 0.4810794261012942,
+      "eval_runtime": 1.1504,
+      "eval_samples_per_second": 906.647,
+      "eval_steps_per_second": 57.372,
+      "step": 536
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 95441467104708.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6477448170002332e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 34
+  }
+}

run-1/checkpoint-536/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1aa22f290642ee01c58508f6341455213d65d2b747968e31a42fb22e7b7ee22
+size 4664

run-1/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": "4.35.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-804/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945826e2756aee187ff6d9bdd54154b39351f77603e0170a083bc3c49be4ee68
+size 267832560

run-1/checkpoint-804/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ea911767fd5bd81c9ae263da864a0ce433894f85b467a23058011a3b4b7e2cb
+size 535727290

run-1/checkpoint-804/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0420cf3993252b233c288946920f1af18011a1b61e0f617168a7cf0d3fe2092b
+size 14244

run-1/checkpoint-804/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475f434ce1db47dc716bfd6101d5f9cecc5edefc32602d23d923f0f0f46628c3
+size 1064

run-1/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-1/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-1/checkpoint-804/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 0.5202123212283704,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/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": 0.4801884889602661,
+      "eval_matthews_correlation": 0.4522326299878879,
+      "eval_runtime": 0.6893,
+      "eval_samples_per_second": 1513.095,
+      "eval_steps_per_second": 95.747,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0329146614031314e-05,
+      "loss": 0.4583,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5012368559837341,
+      "eval_matthews_correlation": 0.4810794261012942,
+      "eval_runtime": 1.1504,
+      "eval_samples_per_second": 906.647,
+      "eval_steps_per_second": 57.372,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5001268982887268,
+      "eval_matthews_correlation": 0.5202123212283704,
+      "eval_runtime": 0.6949,
+      "eval_samples_per_second": 1500.847,
+      "eval_steps_per_second": 94.972,
+      "step": 804
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 95441467104708.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6477448170002332e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 34
+  }
+}

run-1/checkpoint-804/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1aa22f290642ee01c58508f6341455213d65d2b747968e31a42fb22e7b7ee22
+size 4664

runs/Nov17_02-59-16_faa202bf7ecf/events.out.tfevents.1700190791.faa202bf7ecf.336.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:586c12483e48bad4a440d435b94ef3a52f619b1f58ce90254b7f938ca25ad039
-size 4730
+oid sha256:35e399a88ef4c553045eb8630f18d6c703f6cb218ffb533ba62117b487f30c51
+size 6581