Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b55b5e8e8a38e17bc666024003be50e364e2f36fd801be78509cfd662f2baf6c
+oid sha256:d65cbd11871bb7ca54d237b7fec0939208b70a3f06d3a2a7fbef47405a2af448
 size 267832560

run-0/checkpoint-8552/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-8552/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc0e7b5c6f3909aacdeddba078435a5ba1d09004efc21dd028526189c9e3d9b
+size 267832560

run-0/checkpoint-8552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:708ee95c9d9fbd5b92724bd6d3a855dd74607c6c7e93c0f3681c4f4fa0b4e02a
+size 535727290

run-0/checkpoint-8552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9e74c55368a10b021a874152ad01506b2c0e3e7f3cf082249b344f45a1de047
+size 14308

run-0/checkpoint-8552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f94af1ecd2e70287b566579399862e47dd3b591ac84864d46ed0568f3d845a5
+size 1064

run-0/checkpoint-8552/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-8552/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-8552/trainer_state.json

@@ -0,0 +1,164 @@
+{
+  "best_metric": 0.502884728860933,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-8552",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 8552,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 5.147700386643525e-06,
+      "loss": 0.5941,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.828046860398895e-06,
+      "loss": 0.5599,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.5083933341542655e-06,
+      "loss": 0.5441,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.188739807909635e-06,
+      "loss": 0.5171,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.59578937292099,
+      "eval_matthews_correlation": 0.4396965574668407,
+      "eval_runtime": 0.776,
+      "eval_samples_per_second": 1344.121,
+      "eval_steps_per_second": 85.055,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.869086281665004e-06,
+      "loss": 0.4915,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 3.549432755420374e-06,
+      "loss": 0.4792,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 3.2297792291757436e-06,
+      "loss": 0.4855,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.9101257029311134e-06,
+      "loss": 0.4638,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7263815402984619,
+      "eval_matthews_correlation": 0.4867950830885312,
+      "eval_runtime": 0.7416,
+      "eval_samples_per_second": 1406.389,
+      "eval_steps_per_second": 88.995,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 2.5904721766864832e-06,
+      "loss": 0.4408,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.2708186504418535e-06,
+      "loss": 0.4401,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.951165124197223e-06,
+      "loss": 0.4285,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.6315115979525925e-06,
+      "loss": 0.426,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8495753407478333,
+      "eval_matthews_correlation": 0.4863630663948402,
+      "eval_runtime": 0.749,
+      "eval_samples_per_second": 1392.573,
+      "eval_steps_per_second": 88.121,
+      "step": 6414
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 1.3118580717079626e-06,
+      "loss": 0.4376,
+      "step": 6500
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 9.922045454633322e-07,
+      "loss": 0.3443,
+      "step": 7000
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 6.72551019218702e-07,
+      "loss": 0.3567,
+      "step": 7500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 3.528974929740718e-07,
+      "loss": 0.3956,
+      "step": 8000
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 3.3243966729441546e-08,
+      "loss": 0.3431,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.9010036587715149,
+      "eval_matthews_correlation": 0.502884728860933,
+      "eval_runtime": 0.7405,
+      "eval_samples_per_second": 1408.431,
+      "eval_steps_per_second": 89.124,
+      "step": 8552
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 138637999159800.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.467353912888156e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 14
+  }
+}

run-0/checkpoint-8552/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77241119206029366def929b35474bd91e3cb2ee1487eac76e2a3198cad6dc98
+size 4792

run-1/checkpoint-134/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-1/checkpoint-134/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d65cbd11871bb7ca54d237b7fec0939208b70a3f06d3a2a7fbef47405a2af448
+size 267832560

run-1/checkpoint-134/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bec765267b5360112fdc3e503dd48c059b7bdba66e6590d579eb447586acff1
+size 535727290

run-1/checkpoint-134/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b229645b40fbde71bfefe569bc58bee6d1d10d8f74232c3f3372fca937d6d3
+size 14244

run-1/checkpoint-134/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd40ff87d63c351d1a438ac820f4e6918f2faca4fada38b0c01e78048aeec9b4
+size 1064

run-1/checkpoint-134/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-134/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-134/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.4578426154336062,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-134",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 134,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.48087000846862793,
+      "eval_matthews_correlation": 0.4578426154336062,
+      "eval_runtime": 0.7998,
+      "eval_samples_per_second": 1304.033,
+      "eval_steps_per_second": 82.518,
+      "step": 134
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 402,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.8486749150890306e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64,
+    "seed": 35
+  }
+}

run-1/checkpoint-134/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:906491b427edaeea68361f9ccbc1145bee8cb30436f3ab81a18f207971d0a2dc
+size 4792

runs/Dec23_02-13-09_9bda7ec8aa80/events.out.tfevents.1703299325.9bda7ec8aa80.207.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:239167a85ce255d75f3ca880da9430177152050fb7ba5a943ea9a9fd4a3cc43d
-size 7395
+oid sha256:a7208744284a6fe3db29718e5b90f6e9b6b4182ee230dad4af7cae03578ad3b0
+size 8712

runs/Dec23_02-13-09_9bda7ec8aa80/events.out.tfevents.1703299754.9bda7ec8aa80.207.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfee4b187c155a0422ccce7dd07c1515c1084f9f7fa7ede0412037f87bcc6cd3
+size 5021

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77241119206029366def929b35474bd91e3cb2ee1487eac76e2a3198cad6dc98
+oid sha256:906491b427edaeea68361f9ccbc1145bee8cb30436f3ab81a18f207971d0a2dc
 size 4792