Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a964e75fe2e3951181cf3880ccf035be33831c87d38643ff34a9a2d3c403c6fa
+oid sha256:5a30b074d67ccd797477243d3b1bc5052a821c55d0bfde992f4e2298c80cfc07
 size 267832560

run-5/checkpoint-1340/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": "4.48.3",
+  "vocab_size": 30522
+}

run-5/checkpoint-1340/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e08bf0199bb15767120a6ee23c16e7f8ead7fafdc0ad06426c3bde43ffc10218
+size 267832560

run-5/checkpoint-1340/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd747fbb80ebeeb861635b3461b959a803507688272f169d0ada05afb06b59c3
+size 535727290

run-5/checkpoint-1340/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79aa44be1ef7fdc1c485216bc854d747aa742cbc691fb8972cc5dbbcac1eb041
+size 14308

run-5/checkpoint-1340/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e1d24877dac829cb0186721a5c8a1fb0f1958c1a3769d2c832a1ca3a83ff63
+size 1064

run-5/checkpoint-1340/special_tokens_map.json

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

run-5/checkpoint-1340/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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-5/checkpoint-1340/trainer_state.json

@@ -0,0 +1,97 @@
+{
+  "best_metric": 0.4774618517292431,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-1340",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1340,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5259255766868591,
+      "eval_matthews_correlation": 0.3778486229848452,
+      "eval_runtime": 0.7696,
+      "eval_samples_per_second": 1355.216,
+      "eval_steps_per_second": 85.757,
+      "step": 268
+    },
+    {
+      "epoch": 1.8656716417910446,
+      "grad_norm": 6.19685173034668,
+      "learning_rate": 4.16921192631477e-06,
+      "loss": 0.5223,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5131245851516724,
+      "eval_matthews_correlation": 0.45314237018673453,
+      "eval_runtime": 0.7936,
+      "eval_samples_per_second": 1314.232,
+      "eval_steps_per_second": 83.163,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5032510161399841,
+      "eval_matthews_correlation": 0.46092393422967476,
+      "eval_runtime": 0.7773,
+      "eval_samples_per_second": 1341.766,
+      "eval_steps_per_second": 84.906,
+      "step": 804
+    },
+    {
+      "epoch": 3.7313432835820897,
+      "grad_norm": 8.043768882751465,
+      "learning_rate": 1.6875381606512164e-06,
+      "loss": 0.3969,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.507060170173645,
+      "eval_matthews_correlation": 0.46481173360635625,
+      "eval_runtime": 0.757,
+      "eval_samples_per_second": 1377.81,
+      "eval_steps_per_second": 87.186,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5162538290023804,
+      "eval_matthews_correlation": 0.4774618517292431,
+      "eval_runtime": 0.8572,
+      "eval_samples_per_second": 1216.701,
+      "eval_steps_per_second": 76.992,
+      "step": 1340
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 190973229369828.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.650885691978323e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 26
+  }
+}

run-5/checkpoint-1340/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a750443dbfdafacdc0fbf5edeb5c7cbfed04d276af227da6895d6396b37c0f
+size 5432

run-6/checkpoint-535/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": "4.48.3",
+  "vocab_size": 30522
+}

run-6/checkpoint-535/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a30b074d67ccd797477243d3b1bc5052a821c55d0bfde992f4e2298c80cfc07
+size 267832560

run-6/checkpoint-535/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1db6216ce68958ac9d79aa3e419b207533eaf0e81789117415dd9e519417a2f
+size 535727290

run-6/checkpoint-535/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1019ffe52189fc9309a6d474017990d28be822109bb3cad22b215a8e46829032
+size 14308

run-6/checkpoint-535/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93b36208c4e76d1c14db3206a8fdefa1dd0545ec24b41113f68acf103fe2c8eb
+size 1064

run-6/checkpoint-535/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-535/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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-535/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.23415050823672504,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-535",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 535,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9345794392523364,
+      "grad_norm": 4.418112277984619,
+      "learning_rate": 2.6223556776404837e-06,
+      "loss": 0.5858,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5560063123703003,
+      "eval_matthews_correlation": 0.23415050823672504,
+      "eval_runtime": 0.7994,
+      "eval_samples_per_second": 1304.716,
+      "eval_steps_per_second": 82.561,
+      "step": 535
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 42828365827968.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.4218543598479485e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 14
+  }
+}

run-6/checkpoint-535/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dd004c7e78c99be78f0dd560b18c0e6e8d339da58015a8b03439515c2545f81
+size 5432

runs/Mar20_11-54-05_c50c1849b8cd/events.out.tfevents.1742472948.c50c1849b8cd.231.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c7278fbbe92f179f06040f2357e4cf189799ffd4b22cb1c4f4a83da6d0de4e5
+size 6850

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42a750443dbfdafacdc0fbf5edeb5c7cbfed04d276af227da6895d6396b37c0f
+oid sha256:0dd004c7e78c99be78f0dd560b18c0e6e8d339da58015a8b03439515c2545f81
 size 5432