Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41163830d68c0c71e3d9e102767b6e13952332322e1a89db2f939c410a4d7099
+oid sha256:8740e6818af4f7b3de81524dc8912b49bce0877f182ba27f482d246dcec98beb
 size 267832560

run-2/checkpoint-2138/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-2/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b23a968971b19293287438eef60ae5c1918ec542ff71380aae31cd91c873538f
+size 267832560

run-2/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de823e79a240af7a023f39e071d2ee53375f471e37d82ffc8ad524d0210c963
+size 535727290

run-2/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11edc7ed6e233cf8ded4a33dfcfe8204ae40733acbe38c974b94308bacdc2d6d
+size 14308

run-2/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4faa4bda620d03b6edc8353e8edb3a8710818368d5ef4d63d2cae7608666363
+size 1064

run-2/checkpoint-2138/special_tokens_map.json

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

run-2/checkpoint-2138/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-2/checkpoint-2138/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.48409375114357234,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-2138",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.944660653119031e-06,
+      "loss": 0.5558,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 5.157496901381872e-06,
+      "loss": 0.5053,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4907635748386383,
+      "eval_matthews_correlation": 0.42854888313294803,
+      "eval_runtime": 0.8054,
+      "eval_samples_per_second": 1295.012,
+      "eval_steps_per_second": 81.947,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.370333149644712e-06,
+      "loss": 0.4286,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.5831693979075514e-06,
+      "loss": 0.3992,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5015696883201599,
+      "eval_matthews_correlation": 0.48409375114357234,
+      "eval_runtime": 0.8234,
+      "eval_samples_per_second": 1266.73,
+      "eval_steps_per_second": 80.157,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4276,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 75782994673692.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.7318244048561916e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 14
+  }
+}

run-2/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:618b6f744377ad587ba25f1af0a1c4f702e5743116ab1fe52e9ecc52d00dc59b
+size 4664

run-2/checkpoint-3207/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-2/checkpoint-3207/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8740e6818af4f7b3de81524dc8912b49bce0877f182ba27f482d246dcec98beb
+size 267832560

run-2/checkpoint-3207/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4efa8ea3c7821d8b408a50eb9b5470337da6687a6c6a4b21eb5ad40438a8c50
+size 535727290

run-2/checkpoint-3207/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aaf7eb043c95159ae29e4bfd6d67345e53d80ca4223e192916a55fe580f321f
+size 14308

run-2/checkpoint-3207/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a5539767651d99d2c48fe63d4f87370b950e47b28505930e9b4bccd1f87334d
+size 1064

run-2/checkpoint-3207/special_tokens_map.json

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

run-2/checkpoint-3207/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-2/checkpoint-3207/trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_metric": 0.49329306040311344,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-3207",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3207,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.944660653119031e-06,
+      "loss": 0.5558,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 5.157496901381872e-06,
+      "loss": 0.5053,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4907635748386383,
+      "eval_matthews_correlation": 0.42854888313294803,
+      "eval_runtime": 0.8054,
+      "eval_samples_per_second": 1295.012,
+      "eval_steps_per_second": 81.947,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.370333149644712e-06,
+      "loss": 0.4286,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.5831693979075514e-06,
+      "loss": 0.3992,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5015696883201599,
+      "eval_matthews_correlation": 0.48409375114357234,
+      "eval_runtime": 0.8234,
+      "eval_samples_per_second": 1266.73,
+      "eval_steps_per_second": 80.157,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.796005646170392e-06,
+      "loss": 0.3434,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 2.008841894433232e-06,
+      "loss": 0.3371,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5880187749862671,
+      "eval_matthews_correlation": 0.49329306040311344,
+      "eval_runtime": 0.9037,
+      "eval_samples_per_second": 1154.15,
+      "eval_steps_per_second": 73.033,
+      "step": 3207
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4276,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 113339571995772.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.7318244048561916e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 14
+  }
+}

run-2/checkpoint-3207/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:618b6f744377ad587ba25f1af0a1c4f702e5743116ab1fe52e9ecc52d00dc59b
+size 4664

runs/Nov17_02-59-16_faa202bf7ecf/events.out.tfevents.1700190963.faa202bf7ecf.336.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fd08b330f08079d72111a35fc732085984e5ace7d0a6a09684d502b89dff346
-size 5535
+oid sha256:5145488b68906a41089a67a6837c837d7496307c7f919c116f307dbfc3f6b751
+size 7187