Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dc66d6108ac1dc72fc0f91fccb209b711f92e1e8f84b73b851c9b4e570debf0
+oid sha256:bf8e24880158795840c932e820aae6deea370acb3a19ddf07ea9e5d52759e460
 size 267832560

run-0/checkpoint-10690/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-10690/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8e24880158795840c932e820aae6deea370acb3a19ddf07ea9e5d52759e460
+size 267832560

run-0/checkpoint-10690/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140e8a01f0e9e13101f700c7b4048f9cbfcb23ce4ec8cb8948e6ed3e2ee7a087
+size 535727290

run-0/checkpoint-10690/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22a2ffb369e82afc10200872aab0d9890beada13739ada253864da0f4bf0115b
+size 14308

run-0/checkpoint-10690/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e98ccc3dd6a04299cff9e498bc91df85d0f21a66c58dae005e24043b1311dda8
+size 1064

run-0/checkpoint-10690/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-10690/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-10690/trainer_state.json

@@ -0,0 +1,197 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-2138",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 10690,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.456689869150003e-05,
+      "loss": 0.6195,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 8.992671720516538e-05,
+      "loss": 0.6229,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 8.528653571883074e-05,
+      "loss": 0.6157,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 8.064635423249609e-05,
+      "loss": 0.6166,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6419090628623962,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7217,
+      "eval_samples_per_second": 1445.223,
+      "eval_steps_per_second": 91.452,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.600617274616145e-05,
+      "loss": 0.6097,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 7.13659912598268e-05,
+      "loss": 0.6152,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 6.672580977349217e-05,
+      "loss": 0.6082,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.208562828715752e-05,
+      "loss": 0.6177,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6392126083374023,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7452,
+      "eval_samples_per_second": 1399.645,
+      "eval_steps_per_second": 88.568,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 5.7445446800822885e-05,
+      "loss": 0.6101,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 5.2805265314488234e-05,
+      "loss": 0.6274,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 4.81650838281536e-05,
+      "loss": 0.6133,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 4.352490234181895e-05,
+      "loss": 0.5974,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6237232089042664,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.757,
+      "eval_samples_per_second": 1377.809,
+      "eval_steps_per_second": 87.186,
+      "step": 6414
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 3.888472085548431e-05,
+      "loss": 0.608,
+      "step": 6500
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 3.4244539369149664e-05,
+      "loss": 0.6216,
+      "step": 7000
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 2.960435788281502e-05,
+      "loss": 0.6076,
+      "step": 7500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 2.4964176396480383e-05,
+      "loss": 0.6187,
+      "step": 8000
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 2.0323994910145736e-05,
+      "loss": 0.5935,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6235376000404358,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7514,
+      "eval_samples_per_second": 1388.129,
+      "eval_steps_per_second": 87.839,
+      "step": 8552
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 1.568381342381109e-05,
+      "loss": 0.6258,
+      "step": 9000
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 1.104363193747645e-05,
+      "loss": 0.62,
+      "step": 9500
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 6.403450451141807e-06,
+      "loss": 0.6027,
+      "step": 10000
+    },
+    {
+      "epoch": 4.91,
+      "learning_rate": 1.7632689648071642e-06,
+      "loss": 0.6029,
+      "step": 10500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6506770253181458,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7746,
+      "eval_samples_per_second": 1346.479,
+      "eval_steps_per_second": 85.204,
+      "step": 10690
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 171363138586368.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.920708017783467e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 31
+  }
+}

run-0/checkpoint-10690/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c864ad0b0686dfaa2454427080519f24d7ce414d236604b49409835d4e23b3cb
+size 4792

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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-6414/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14dd7232312fa3de498499afe6b679f2023f024f439950f6abd03b349d535cdb
+size 267832560

run-0/checkpoint-6414/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71bb50f45f5cc8ca163d7c64a25689d25a944167a8988b9906aabfdf1d751e3e
+size 535727290

run-0/checkpoint-6414/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cf45ff203d40a7da65bf1517c38d5c60b21193bc79079199baa779d11e41481
+size 14308

run-0/checkpoint-6414/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:574602e528e440ef14c64c6444be920beff890fae30c87eae31b39fe165b05ea
+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 +1,125 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-2138",
+  "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,
+      "learning_rate": 9.456689869150003e-05,
+      "loss": 0.6195,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 8.992671720516538e-05,
+      "loss": 0.6229,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 8.528653571883074e-05,
+      "loss": 0.6157,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 8.064635423249609e-05,
+      "loss": 0.6166,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6419090628623962,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7217,
+      "eval_samples_per_second": 1445.223,
+      "eval_steps_per_second": 91.452,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.600617274616145e-05,
+      "loss": 0.6097,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 7.13659912598268e-05,
+      "loss": 0.6152,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 6.672580977349217e-05,
+      "loss": 0.6082,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.208562828715752e-05,
+      "loss": 0.6177,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6392126083374023,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7452,
+      "eval_samples_per_second": 1399.645,
+      "eval_steps_per_second": 88.568,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 5.7445446800822885e-05,
+      "loss": 0.6101,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 5.2805265314488234e-05,
+      "loss": 0.6274,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 4.81650838281536e-05,
+      "loss": 0.6133,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 4.352490234181895e-05,
+      "loss": 0.5974,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6237232089042664,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.757,
+      "eval_samples_per_second": 1377.809,
+      "eval_steps_per_second": 87.186,
+      "step": 6414
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 97840368902244.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.920708017783467e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 31
+  }
+}

run-0/checkpoint-6414/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c864ad0b0686dfaa2454427080519f24d7ce414d236604b49409835d4e23b3cb
+size 4792

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 sha256:90c3391f2aea2542cc44981721756eed910903e9da44116fd3f1de2926ff6e6f
+size 267832560

run-0/checkpoint-8552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303bb1dee8f3c624330d4e45174e9beab17ea9448d6d5d6a67e435b23058cccc
+size 535727290

run-0/checkpoint-8552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68abdd6c7ec4be76c8ac7ae5566ae833dd284ed9158ed288de43cfeb71a64af4
+size 14308

run-0/checkpoint-8552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22f8d6941a227700968e85a611fe68ce9c5f665293094020803454a3ea01f306
+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": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-2138",
+  "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": 9.456689869150003e-05,
+      "loss": 0.6195,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 8.992671720516538e-05,
+      "loss": 0.6229,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 8.528653571883074e-05,
+      "loss": 0.6157,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 8.064635423249609e-05,
+      "loss": 0.6166,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6419090628623962,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7217,
+      "eval_samples_per_second": 1445.223,
+      "eval_steps_per_second": 91.452,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.600617274616145e-05,
+      "loss": 0.6097,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 7.13659912598268e-05,
+      "loss": 0.6152,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 6.672580977349217e-05,
+      "loss": 0.6082,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.208562828715752e-05,
+      "loss": 0.6177,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6392126083374023,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7452,
+      "eval_samples_per_second": 1399.645,
+      "eval_steps_per_second": 88.568,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 5.7445446800822885e-05,
+      "loss": 0.6101,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 5.2805265314488234e-05,
+      "loss": 0.6274,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 4.81650838281536e-05,
+      "loss": 0.6133,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 4.352490234181895e-05,
+      "loss": 0.5974,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6237232089042664,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.757,
+      "eval_samples_per_second": 1377.809,
+      "eval_steps_per_second": 87.186,
+      "step": 6414
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 3.888472085548431e-05,
+      "loss": 0.608,
+      "step": 6500
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 3.4244539369149664e-05,
+      "loss": 0.6216,
+      "step": 7000
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 2.960435788281502e-05,
+      "loss": 0.6076,
+      "step": 7500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 2.4964176396480383e-05,
+      "loss": 0.6187,
+      "step": 8000
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 2.0323994910145736e-05,
+      "loss": 0.5935,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6235376000404358,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7514,
+      "eval_samples_per_second": 1388.129,
+      "eval_steps_per_second": 87.839,
+      "step": 8552
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 138735797356464.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.920708017783467e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 31
+  }
+}

run-0/checkpoint-8552/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c864ad0b0686dfaa2454427080519f24d7ce414d236604b49409835d4e23b3cb
+size 4792

runs/Dec23_01-55-51_48296f50e732/events.out.tfevents.1703297718.48296f50e732.508.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b57ca38167e9b934816345fb56352033d46be0d403319f358f23a03055d4bf5
-size 6271
+oid sha256:8bda058147eca9d75f0a91663585b9aa2040dcddf1bc2d8d316ae5d69a5c69ea
+size 9671