Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ebb6202a7d1a41113d412e87f742996ca5b6bbc31971a25cbaf58b338f216bb
+oid sha256:a81e4ba8809e9bd7b5bd99cddf31750c4aabbca9ceb665f51c098e1fc7110237
 size 267832560

run-6/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": "4.36.2",
+  "vocab_size": 30522
+}

run-6/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:802daef4341ccc277fb77b32667a17eb120e444bb73689eeea090a3a0723ccc9
+size 267832560

run-6/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d45acb27e4baea16b8752df6bd379f2afbf8ceb9fb8889834f3f00a2768973
+size 535727290

run-6/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13acbd68197c6d3b2ae24d61f8e4f8733d0afa1257405f0763e9849788504e75
+size 14244

run-6/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c9e582ce8735ae35d615b64994ff06112f58b9e53821029df05f477fb53881
+size 1064

run-6/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-6/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-6/checkpoint-4276/trainer_state.json

@@ -0,0 +1,110 @@
+{
+  "best_metric": 0.5294539646667358,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-3207",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.743168095162701e-05,
+      "loss": 0.5546,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5632745868899764e-05,
+      "loss": 0.5141,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4699566662311554,
+      "eval_matthews_correlation": 0.46417453765870365,
+      "eval_runtime": 0.8233,
+      "eval_samples_per_second": 1266.776,
+      "eval_steps_per_second": 80.16,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.3833810786172519e-05,
+      "loss": 0.3839,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.2034875703445273e-05,
+      "loss": 0.3641,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.49815642833709717,
+      "eval_matthews_correlation": 0.5003634450667074,
+      "eval_runtime": 0.8279,
+      "eval_samples_per_second": 1259.884,
+      "eval_steps_per_second": 79.724,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.0235940620718027e-05,
+      "loss": 0.2949,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 8.437005537990782e-06,
+      "loss": 0.2606,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6836941838264465,
+      "eval_matthews_correlation": 0.5294539646667358,
+      "eval_runtime": 0.7645,
+      "eval_samples_per_second": 1364.231,
+      "eval_steps_per_second": 86.327,
+      "step": 3207
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 6.638070455263536e-06,
+      "loss": 0.2286,
+      "step": 3500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 4.839135372536291e-06,
+      "loss": 0.1944,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.9617471098899841,
+      "eval_matthews_correlation": 0.5166483393052006,
+      "eval_runtime": 0.8112,
+      "eval_samples_per_second": 1285.75,
+      "eval_steps_per_second": 81.361,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 262614030581640.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.9230616034354256e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 35
+  }
+}

run-6/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb866ee69ed04e267f5df72a73bb2a0b19d6fca8000858da0328c340dd11d9b2
+size 4792

run-6/checkpoint-5345/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-6/checkpoint-5345/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b618647fb3a499347c2ba76237d04a8522117ab6ee9ac4dd2ec76f15a9d67ee
+size 267832560

run-6/checkpoint-5345/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22f9bbf19d407c568a0b677905d69a4c90b946f70065b3a9e98a00c37fc1b190
+size 535727290

run-6/checkpoint-5345/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323a1e98cc2ec1ba2868d4c4363bae8a435b3a1dcc756a1d87098a6bc826052b
+size 14244

run-6/checkpoint-5345/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dffca9dae16fa9462a8350ae4be14b6641404053ab91d58fec93367483a6a4a0
+size 1064

run-6/checkpoint-5345/special_tokens_map.json

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

run-6/checkpoint-5345/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-6/checkpoint-5345/trainer_state.json

@@ -0,0 +1,131 @@
+{
+  "best_metric": 0.5294539646667358,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-3207",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 5345,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.743168095162701e-05,
+      "loss": 0.5546,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5632745868899764e-05,
+      "loss": 0.5141,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4699566662311554,
+      "eval_matthews_correlation": 0.46417453765870365,
+      "eval_runtime": 0.8233,
+      "eval_samples_per_second": 1266.776,
+      "eval_steps_per_second": 80.16,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.3833810786172519e-05,
+      "loss": 0.3839,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.2034875703445273e-05,
+      "loss": 0.3641,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.49815642833709717,
+      "eval_matthews_correlation": 0.5003634450667074,
+      "eval_runtime": 0.8279,
+      "eval_samples_per_second": 1259.884,
+      "eval_steps_per_second": 79.724,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.0235940620718027e-05,
+      "loss": 0.2949,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 8.437005537990782e-06,
+      "loss": 0.2606,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6836941838264465,
+      "eval_matthews_correlation": 0.5294539646667358,
+      "eval_runtime": 0.7645,
+      "eval_samples_per_second": 1364.231,
+      "eval_steps_per_second": 86.327,
+      "step": 3207
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 6.638070455263536e-06,
+      "loss": 0.2286,
+      "step": 3500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 4.839135372536291e-06,
+      "loss": 0.1944,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.9617471098899841,
+      "eval_matthews_correlation": 0.5166483393052006,
+      "eval_runtime": 0.8112,
+      "eval_samples_per_second": 1285.75,
+      "eval_steps_per_second": 81.361,
+      "step": 4276
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 3.040200289809045e-06,
+      "loss": 0.1725,
+      "step": 4500
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 1.2412652070817996e-06,
+      "loss": 0.1299,
+      "step": 5000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.0240098237991333,
+      "eval_matthews_correlation": 0.5144566045467207,
+      "eval_runtime": 1.3861,
+      "eval_samples_per_second": 752.466,
+      "eval_steps_per_second": 47.615,
+      "step": 5345
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 299858326360404.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.9230616034354256e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 35
+  }
+}

run-6/checkpoint-5345/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb866ee69ed04e267f5df72a73bb2a0b19d6fca8000858da0328c340dd11d9b2
+size 4792

runs/Dec23_02-13-49_7a63bfb314a5/events.out.tfevents.1703300848.7a63bfb314a5.153.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6978a5117808c4db05de6a42380dbafeaa1d08891c3332cf3db5e4635137114
+size 5342

runs/Dec23_02-13-49_7a63bfb314a5/events.out.tfevents.1703300948.7a63bfb314a5.153.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0566e5021db47f04b48dd3c87d76d33249f2c1314908905c2f9753351dc03037
+size 6210

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb866ee69ed04e267f5df72a73bb2a0b19d6fca8000858da0328c340dd11d9b2
+oid sha256:b3a7e9b4de1ac105a36953dacc17dd677066ac952d8ffed336a5c863fcb54ea8
 size 4792