Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d565e3d8ad2e00f157561ec5c14773d00a882b3917ce3cdab12b1ce3e9688af
+oid sha256:43f05ab2a4df53063917db36703fa1b2d390aff952c179f7cd5193e4c373e530
 size 267832560

run-3/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": "4.39.1",
+  "vocab_size": 30522
+}

run-3/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:105df316add1683a939726bf7bdb469b93060d2defa33e0509fdc17e3f5b87ef
+size 267832560

run-3/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0026bd10f1312a53e638a7d1114069ad55b3c33a1f811ad5bf5dfafd90a49872
+size 535727290

run-3/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48521d91ee34a4c1f95821c0eb213aaa9f302dfb8643742ab83500ca3d45eed
+size 14308

run-3/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a60f522988a4878bac96b95b85d76f06fc6862ff9048542ccddb56ddab931139
+size 1064

run-3/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-3/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-3/checkpoint-4276/trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_metric": 0.5543972545286807,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-4276",
+  "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,
+      "grad_norm": 10.753751754760742,
+      "learning_rate": 1.7977369076499405e-05,
+      "loss": 0.5382,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 9.229598999023438,
+      "learning_rate": 1.612211942980184e-05,
+      "loss": 0.4947,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4966508448123932,
+      "eval_matthews_correlation": 0.457686920201459,
+      "eval_runtime": 0.7777,
+      "eval_samples_per_second": 1341.196,
+      "eval_steps_per_second": 84.87,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 11.25524616241455,
+      "learning_rate": 1.4266869783104275e-05,
+      "loss": 0.3692,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 40.92118835449219,
+      "learning_rate": 1.2411620136406709e-05,
+      "loss": 0.3508,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6059253811836243,
+      "eval_matthews_correlation": 0.49547617383910947,
+      "eval_runtime": 0.8858,
+      "eval_samples_per_second": 1177.509,
+      "eval_steps_per_second": 74.512,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.43179455399513245,
+      "learning_rate": 1.0556370489709145e-05,
+      "loss": 0.2779,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 33.96426010131836,
+      "learning_rate": 8.70112084301158e-06,
+      "loss": 0.2518,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8006073236465454,
+      "eval_matthews_correlation": 0.542244787638552,
+      "eval_runtime": 0.8024,
+      "eval_samples_per_second": 1299.782,
+      "eval_steps_per_second": 82.249,
+      "step": 3207
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": 26.66070556640625,
+      "learning_rate": 6.845871196314015e-06,
+      "loss": 0.2005,
+      "step": 3500
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 0.43843144178390503,
+      "learning_rate": 4.9906215496164505e-06,
+      "loss": 0.1696,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.9382862448692322,
+      "eval_matthews_correlation": 0.5543972545286807,
+      "eval_runtime": 0.883,
+      "eval_samples_per_second": 1181.24,
+      "eval_steps_per_second": 74.748,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 150905463431820.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.983261872319697e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 17
+  }
+}

run-3/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2ec969fae7bee101c572269723cfc78fdfbd9ddc8090a6c9907a585baa38d24
+size 4984

run-3/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": "4.39.1",
+  "vocab_size": 30522
+}

run-3/checkpoint-5345/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43f05ab2a4df53063917db36703fa1b2d390aff952c179f7cd5193e4c373e530
+size 267832560

run-3/checkpoint-5345/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cd0eb342fc38dad671676f4e9b1d01ff057ae27703d9bcc35d7eaf9797ad255
+size 535727290

run-3/checkpoint-5345/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4229fbdb1e7531e56b3e2da5af893824a499ff5d1ab15654a32ad54779c6dc6
+size 14308

run-3/checkpoint-5345/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:733b01ed2a571f11c06e0b00b4c33c11cfc4aafb0b8a0ab10aa174767f0152f0
+size 1064

run-3/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-3/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-3/checkpoint-5345/trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": 0.5616581968995631,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-5345",
+  "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,
+      "grad_norm": 10.753751754760742,
+      "learning_rate": 1.7977369076499405e-05,
+      "loss": 0.5382,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 9.229598999023438,
+      "learning_rate": 1.612211942980184e-05,
+      "loss": 0.4947,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4966508448123932,
+      "eval_matthews_correlation": 0.457686920201459,
+      "eval_runtime": 0.7777,
+      "eval_samples_per_second": 1341.196,
+      "eval_steps_per_second": 84.87,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 11.25524616241455,
+      "learning_rate": 1.4266869783104275e-05,
+      "loss": 0.3692,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 40.92118835449219,
+      "learning_rate": 1.2411620136406709e-05,
+      "loss": 0.3508,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6059253811836243,
+      "eval_matthews_correlation": 0.49547617383910947,
+      "eval_runtime": 0.8858,
+      "eval_samples_per_second": 1177.509,
+      "eval_steps_per_second": 74.512,
+      "step": 2138
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.43179455399513245,
+      "learning_rate": 1.0556370489709145e-05,
+      "loss": 0.2779,
+      "step": 2500
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 33.96426010131836,
+      "learning_rate": 8.70112084301158e-06,
+      "loss": 0.2518,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8006073236465454,
+      "eval_matthews_correlation": 0.542244787638552,
+      "eval_runtime": 0.8024,
+      "eval_samples_per_second": 1299.782,
+      "eval_steps_per_second": 82.249,
+      "step": 3207
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": 26.66070556640625,
+      "learning_rate": 6.845871196314015e-06,
+      "loss": 0.2005,
+      "step": 3500
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 0.43843144178390503,
+      "learning_rate": 4.9906215496164505e-06,
+      "loss": 0.1696,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.9382862448692322,
+      "eval_matthews_correlation": 0.5543972545286807,
+      "eval_runtime": 0.883,
+      "eval_samples_per_second": 1181.24,
+      "eval_steps_per_second": 74.748,
+      "step": 4276
+    },
+    {
+      "epoch": 4.21,
+      "grad_norm": 65.19385528564453,
+      "learning_rate": 3.1353719029188846e-06,
+      "loss": 0.1399,
+      "step": 4500
+    },
+    {
+      "epoch": 4.68,
+      "grad_norm": 28.80259132385254,
+      "learning_rate": 1.28012225622132e-06,
+      "loss": 0.1096,
+      "step": 5000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.0170196294784546,
+      "eval_matthews_correlation": 0.5616581968995631,
+      "eval_runtime": 0.7941,
+      "eval_samples_per_second": 1313.454,
+      "eval_steps_per_second": 83.114,
+      "step": 5345
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5345,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 188407190971644.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.983261872319697e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 17
+  }
+}

run-3/checkpoint-5345/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2ec969fae7bee101c572269723cfc78fdfbd9ddc8090a6c9907a585baa38d24
+size 4984

runs/Mar23_02-09-13_2ed998b56e2c/events.out.tfevents.1711161152.2ed998b56e2c.195.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e16cf25412f6eafa5eeb91abe29830dbc60592b07b1753a79edc18b8cea03d50
-size 7284
+oid sha256:0a48bf307a06604019dbe88b2d31a55cd40b52ebf2f3ecb9b13c0e2edbecc744
+size 8730