Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9b9c8894a3469b664a47846d0d70f719b96d021a40ff13f3bbf15673d92db82
+oid sha256:15609c8679ccf25b5c03992c8824881d4931e827f19e8d21deb9c5b48a6183f1
 size 267832560

run-0/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": "4.38.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef9c6ba68937c85e0da4b5422affce4df94cdc9feaccd1468cb1097044f2e8fe
+size 267832560

run-0/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc744a1aacfde8d4a435d15fe751ab0646eac6317dd997cd2908c207a8b2613
+size 535727290

run-0/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c08ffc4bc74de2a976ef45ef8ed28b3438038181283effcb14cc51da3bdaa32
+size 14308

run-0/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1bfe5bd8e3163a0f6eef672ade767d6e5d171279133d99a55c7159a4138f667
+size 1064

run-0/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-0/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-0/checkpoint-2138/trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": 0.472806497515492,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-2138",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 3.7270963191986084,
+      "learning_rate": 1.0277702544991746e-05,
+      "loss": 0.5849,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 16.02177619934082,
+      "learning_rate": 9.408772671387439e-06,
+      "loss": 0.5575,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 15.67810344696045,
+      "learning_rate": 8.539842797783132e-06,
+      "loss": 0.5369,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 19.78717041015625,
+      "learning_rate": 7.670912924178823e-06,
+      "loss": 0.5402,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5537068843841553,
+      "eval_matthews_correlation": 0.472806497515492,
+      "eval_runtime": 0.7082,
+      "eval_samples_per_second": 1472.658,
+      "eval_steps_per_second": 93.188,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6414,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 32638725146976.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1146632418596053e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 14
+  }
+}

run-0/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd26d53ea6a56bf97ca32b87d1591bb17f3cfbb5b6e17b15ddad3a69357752cf
+size 4984

run-0/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": "4.38.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5f99152a17e8907c7aa1040f92c65ae7965b7abc6177896c9a85c95b0737fc9
+size 267832560

run-0/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ce8296034e4662882339c35d97c389d03358189df0d673e66d4395ce36ccf7d
+size 535727290

run-0/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e3d35fc1a32d61ab5374f5710b03082046bff05cd67346d60c9d01369555e5f
+size 14308

run-0/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe128d965d16e52faa7abd30706db04f400795189536c5a783279bfffe10f4d
+size 1064

run-0/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-0/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-0/checkpoint-4276/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.4863630663948402,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-4276",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 3.7270963191986084,
+      "learning_rate": 1.0277702544991746e-05,
+      "loss": 0.5849,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 16.02177619934082,
+      "learning_rate": 9.408772671387439e-06,
+      "loss": 0.5575,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 15.67810344696045,
+      "learning_rate": 8.539842797783132e-06,
+      "loss": 0.5369,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 19.78717041015625,
+      "learning_rate": 7.670912924178823e-06,
+      "loss": 0.5402,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5537068843841553,
+      "eval_matthews_correlation": 0.472806497515492,
+      "eval_runtime": 0.7082,
+      "eval_samples_per_second": 1472.658,
+      "eval_steps_per_second": 93.188,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 10.657214164733887,
+      "learning_rate": 6.801983050574517e-06,
+      "loss": 0.4772,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.260273933410645,
+      "learning_rate": 5.933053176970209e-06,
+      "loss": 0.4307,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.3461722433567047,
+      "learning_rate": 5.064123303365902e-06,
+      "loss": 0.4898,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 9.188729286193848,
+      "learning_rate": 4.195193429761595e-06,
+      "loss": 0.4323,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8039517402648926,
+      "eval_matthews_correlation": 0.4863630663948402,
+      "eval_runtime": 0.7133,
+      "eval_samples_per_second": 1462.131,
+      "eval_steps_per_second": 92.522,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6414,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 65242522366572.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1146632418596053e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 14
+  }
+}

run-0/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd26d53ea6a56bf97ca32b87d1591bb17f3cfbb5b6e17b15ddad3a69357752cf
+size 4984

run-0/checkpoint-6414/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": "4.38.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-6414/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15609c8679ccf25b5c03992c8824881d4931e827f19e8d21deb9c5b48a6183f1
+size 267832560

run-0/checkpoint-6414/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0e4521057da3a37d5f218c9e659696b6d108a75db34b60e58bddf47cee2b6ce
+size 535727290

run-0/checkpoint-6414/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5effe086e3a1152c63f112399a47232954fc9841a28f5e07de5364fb2cd5a1b
+size 14308

run-0/checkpoint-6414/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d09d36c6826cfc8619d9ab4049cb53f21d507b006b3307d423ec47ddd4499c0
+size 1064

run-0/checkpoint-6414/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-6414/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-6414/trainer_state.json

@@ -0,0 +1,137 @@
+{
+  "best_metric": 0.4863630663948402,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-4276",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6414,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "grad_norm": 3.7270963191986084,
+      "learning_rate": 1.0277702544991746e-05,
+      "loss": 0.5849,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 16.02177619934082,
+      "learning_rate": 9.408772671387439e-06,
+      "loss": 0.5575,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 15.67810344696045,
+      "learning_rate": 8.539842797783132e-06,
+      "loss": 0.5369,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 19.78717041015625,
+      "learning_rate": 7.670912924178823e-06,
+      "loss": 0.5402,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5537068843841553,
+      "eval_matthews_correlation": 0.472806497515492,
+      "eval_runtime": 0.7082,
+      "eval_samples_per_second": 1472.658,
+      "eval_steps_per_second": 93.188,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 10.657214164733887,
+      "learning_rate": 6.801983050574517e-06,
+      "loss": 0.4772,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.260273933410645,
+      "learning_rate": 5.933053176970209e-06,
+      "loss": 0.4307,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.3461722433567047,
+      "learning_rate": 5.064123303365902e-06,
+      "loss": 0.4898,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 9.188729286193848,
+      "learning_rate": 4.195193429761595e-06,
+      "loss": 0.4323,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8039517402648926,
+      "eval_matthews_correlation": 0.4863630663948402,
+      "eval_runtime": 0.7133,
+      "eval_samples_per_second": 1462.131,
+      "eval_steps_per_second": 92.522,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.2265389859676361,
+      "learning_rate": 3.326263556157288e-06,
+      "loss": 0.4019,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.21080313622951508,
+      "learning_rate": 2.4573336825529805e-06,
+      "loss": 0.3251,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.7802304029464722,
+      "learning_rate": 1.5884038089486737e-06,
+      "loss": 0.3373,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 99.31454467773438,
+      "learning_rate": 7.194739353443664e-07,
+      "loss": 0.3688,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9660905599594116,
+      "eval_matthews_correlation": 0.48475890971255925,
+      "eval_runtime": 0.7748,
+      "eval_samples_per_second": 1346.116,
+      "eval_steps_per_second": 85.181,
+      "step": 6414
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6414,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 97838816549916.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1146632418596053e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 14
+  }
+}

run-0/checkpoint-6414/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd26d53ea6a56bf97ca32b87d1591bb17f3cfbb5b6e17b15ddad3a69357752cf
+size 4984

runs/Feb25_19-05-35_a56a1d5f314a/events.out.tfevents.1708888516.a56a1d5f314a.1698.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ca9ce702a3fd5141e42a1776c77fe398175c9681c94bd0ee40933661ba8882e
+size 8433

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f28ae92bdf34f74a5ba8528307f8f80db2614cc101b054bfeb8f03349fda441
+oid sha256:bd26d53ea6a56bf97ca32b87d1591bb17f3cfbb5b6e17b15ddad3a69357752cf
 size 4984