Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e339a88e171cf68560fad94c2de34387fcc1fa0841dc0997fb3782ba3b12e1df
+oid sha256:30f4e9548471ed4ffad58c93aa048da4c43864ff312fefc44f489d5327cd82e9
 size 267832560

run-4/checkpoint-108/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-4/checkpoint-108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43575d5b47a35037f164bda47d1644a541411ecede49a6284228de7e568b6e98
+size 267832560

run-4/checkpoint-108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7397c0092d4f49d28e070678269407c368acb366ee33a24227a6128717c31655
+size 535727290

run-4/checkpoint-108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd538b40b5e376328ac0270ddd397017a003ad0a9a2a76406475d6253e3ccebb
+size 14308

run-4/checkpoint-108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e939f2de27b3194629126c2f551fba52f68e18767e544a78be909b11cd798c0
+size 1064

run-4/checkpoint-108/special_tokens_map.json

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

run-4/checkpoint-108/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-4/checkpoint-108/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.3328300141630132,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-108",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 108,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5779895782470703,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.2676,
+      "eval_samples_per_second": 822.8,
+      "eval_steps_per_second": 52.066,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6206706762313843,
+      "eval_matthews_correlation": 0.3308080012085053,
+      "eval_runtime": 1.1954,
+      "eval_samples_per_second": 872.513,
+      "eval_steps_per_second": 55.212,
+      "step": 54
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.7836025357246399,
+      "eval_matthews_correlation": 0.32126041966530916,
+      "eval_runtime": 0.7675,
+      "eval_samples_per_second": 1358.922,
+      "eval_steps_per_second": 85.991,
+      "step": 81
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.9205455183982849,
+      "eval_matthews_correlation": 0.3328300141630132,
+      "eval_runtime": 1.7602,
+      "eval_samples_per_second": 592.531,
+      "eval_steps_per_second": 37.495,
+      "step": 108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.5246354176486404e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 29
+  }
+}

run-4/checkpoint-108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e00559bb0da783ae52b61b6a8510ccb795226928432dd308acf4d541364e8625
+size 4984

run-4/checkpoint-135/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-4/checkpoint-135/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a86f2ea9912f1e0c5c93dc90c7756b8bd6cb912b6aee0c86aacc432240eded2
+size 267832560

run-4/checkpoint-135/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d101c689decbb623abd053ea34ceb233af8e29ea5f82aa28e97d6506363d5e
+size 535727290

run-4/checkpoint-135/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498ed256df9a7e8cbaa8109e99b00f876288489cc2c6e90af78f1b2a903f8fef
+size 14308

run-4/checkpoint-135/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef74e72d67ff271acbc2c9d741499fd220bb8a0821dff9f8d61fe1ebbd556da5
+size 1064

run-4/checkpoint-135/special_tokens_map.json

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

run-4/checkpoint-135/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-4/checkpoint-135/trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_metric": 0.3328300141630132,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-108",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 135,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5779895782470703,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 1.2676,
+      "eval_samples_per_second": 822.8,
+      "eval_steps_per_second": 52.066,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6206706762313843,
+      "eval_matthews_correlation": 0.3308080012085053,
+      "eval_runtime": 1.1954,
+      "eval_samples_per_second": 872.513,
+      "eval_steps_per_second": 55.212,
+      "step": 54
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.7836025357246399,
+      "eval_matthews_correlation": 0.32126041966530916,
+      "eval_runtime": 0.7675,
+      "eval_samples_per_second": 1358.922,
+      "eval_steps_per_second": 85.991,
+      "step": 81
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.9205455183982849,
+      "eval_matthews_correlation": 0.3328300141630132,
+      "eval_runtime": 1.7602,
+      "eval_samples_per_second": 592.531,
+      "eval_steps_per_second": 37.495,
+      "step": 108
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.9759761691093445,
+      "eval_matthews_correlation": 0.31765323876865625,
+      "eval_runtime": 1.3534,
+      "eval_samples_per_second": 770.639,
+      "eval_steps_per_second": 48.765,
+      "step": 135
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.5246354176486404e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 29
+  }
+}

run-4/checkpoint-135/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e00559bb0da783ae52b61b6a8510ccb795226928432dd308acf4d541364e8625
+size 4984

run-4/checkpoint-27/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b9b8a8ddd3b961d8a615d72d44899f4f014544b243b6416621b85ccbf3c8ad2
+oid sha256:e339a88e171cf68560fad94c2de34387fcc1fa0841dc0997fb3782ba3b12e1df
 size 267832560

run-4/checkpoint-27/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85498800da8611a8057920e8be110cf578d5cf56a24ae7cd09ee7ad158ff4b53
+oid sha256:583eb060bade705f1543db53a8550bdb70b961b4d973fbd92d6278f820aa7732
 size 535727290

run-4/checkpoint-27/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f761fe2fb07cec4ef5993902bc6b59ee56ccbea032a6f7671ae20a095d6c4ae
-size 14244
+oid sha256:c19cd7dd6dac13f782bb9a7cca6e61f0d827113a5b105c2a8e7757b44c6f5bfe
+size 14308

run-4/checkpoint-27/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d93fb8c98d95af7dba0793a224be7ba577b66fa6470d047fa200f1ad07308e3
+oid sha256:452c1b4f234af6097134e42856f2661cc61c96b0bf935203dd74311d0fb8ebd3
 size 1064

run-4/checkpoint-27/trainer_state.json

@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.598613440990448,
+      "eval_loss": 0.5779895782470703,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.7931,
-      "eval_samples_per_second": 1315.11,
-      "eval_steps_per_second": 83.219,
+      "eval_runtime": 1.2676,
+      "eval_samples_per_second": 822.8,
+      "eval_steps_per_second": 52.066,
       "step": 27
     }
   ],
   "logging_steps": 500,
-  "max_steps": 81,
+  "max_steps": 135,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 3.6796428408677604e-05,
-    "num_train_epochs": 3,
+    "learning_rate": 5.5246354176486404e-05,
+    "num_train_epochs": 5,
     "per_device_train_batch_size": 32,
-    "seed": 1
+    "seed": 29
   }
 }

run-4/checkpoint-27/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bcf9d16a39b36f26738ac27ccd3d625cd9d28ed3e5f9694dea854578c72fb9e
+oid sha256:e00559bb0da783ae52b61b6a8510ccb795226928432dd308acf4d541364e8625
 size 4984

run-4/checkpoint-54/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:341e92457360435fb9f32395253c06f0d5eeb92dbf408559787ed14ebe2d01f0
+oid sha256:44ce2283c20379ad32cfc170c803f57d884c82e04c348e1393567b19d2a88931
 size 267832560

run-4/checkpoint-54/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22e45aee2b5c34e073e8f19912e9e0b351e8cbe890f77d8b5b3a37b35f8036a9
+oid sha256:884ac677d0c38ba1baff53f458acb9521d827eb872278fffdc1ec597906a0e03
 size 535727290

run-4/checkpoint-54/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2032ba244bd2dafbbf529f865ea2d23c61262b0fed6820b9b52930307b4df882
-size 14244
+oid sha256:b66a2fa1cff907046cb769c2c23d55bfab9701864d47b50571e12b3b51b706c6
+size 14308

run-4/checkpoint-54/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61f20c597357d88f9f47e8abae0da1330535f50b9e39477c18ccef7d4e9cb300
+oid sha256:4c04adaf183823123667b0a8f8770050f83d89fd090a4f7253da98b3729296c8
 size 1064

run-4/checkpoint-54/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.0863794254719202,
+  "best_metric": 0.3308080012085053,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-54",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,35 +10,35 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.598613440990448,
+      "eval_loss": 0.5779895782470703,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.7931,
-      "eval_samples_per_second": 1315.11,
-      "eval_steps_per_second": 83.219,
+      "eval_runtime": 1.2676,
+      "eval_samples_per_second": 822.8,
+      "eval_steps_per_second": 52.066,
       "step": 27
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.5975402593612671,
-      "eval_matthews_correlation": 0.0863794254719202,
-      "eval_runtime": 0.7965,
-      "eval_samples_per_second": 1309.539,
-      "eval_steps_per_second": 82.866,
+      "eval_loss": 0.6206706762313843,
+      "eval_matthews_correlation": 0.3308080012085053,
+      "eval_runtime": 1.1954,
+      "eval_samples_per_second": 872.513,
+      "eval_steps_per_second": 55.212,
       "step": 54
     }
   ],
   "logging_steps": 500,
-  "max_steps": 81,
+  "max_steps": 135,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 3.6796428408677604e-05,
-    "num_train_epochs": 3,
+    "learning_rate": 5.5246354176486404e-05,
+    "num_train_epochs": 5,
     "per_device_train_batch_size": 32,
-    "seed": 1
+    "seed": 29
   }
 }

run-4/checkpoint-54/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bcf9d16a39b36f26738ac27ccd3d625cd9d28ed3e5f9694dea854578c72fb9e
+oid sha256:e00559bb0da783ae52b61b6a8510ccb795226928432dd308acf4d541364e8625
 size 4984

run-4/checkpoint-81/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ee0caa10715f887372eaa0e30df712fed4d1f683ea968d185e4ff7026bfe302
+oid sha256:a52fdd03517d209c5f7867ff4d1fd569a598e951d0ce9de7d7b4c60e299ffa30
 size 267832560

run-4/checkpoint-81/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:221a71dfefb4cff2007102961583abe8e353f0703234a3d38d569ab62ae51d17
+oid sha256:a6172df73a6ea11e70015f9b0c0a529784f142a25222f09d76aef9a53673f875
 size 535727290

run-4/checkpoint-81/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:790f23647dc62293b735d826a0a1c199bddc650af4e9f8c8a6a48fcacdfcf34e
-size 14244
+oid sha256:90ba11e095f2bce4cc3e84a1d73066fa99734a63bf6e277e2f29599058cf2c56
+size 14308

run-4/checkpoint-81/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c2143573de3c71ec0df8d247132422493cc42d6fdd0ee4056c09505b0486112
+oid sha256:28a008f873ea45d6cfa6fd7c4e7dad1d22b21b1d84b9f20671ee295314d68c3a
 size 1064

run-4/checkpoint-81/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.2462710523446019,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-81",
+  "best_metric": 0.3308080012085053,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-54",
   "epoch": 3.0,
   "eval_steps": 500,
   "global_step": 81,
@@ -10,44 +10,44 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.598613440990448,
+      "eval_loss": 0.5779895782470703,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.7931,
-      "eval_samples_per_second": 1315.11,
-      "eval_steps_per_second": 83.219,
+      "eval_runtime": 1.2676,
+      "eval_samples_per_second": 822.8,
+      "eval_steps_per_second": 52.066,
       "step": 27
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.5975402593612671,
-      "eval_matthews_correlation": 0.0863794254719202,
-      "eval_runtime": 0.7965,
-      "eval_samples_per_second": 1309.539,
-      "eval_steps_per_second": 82.866,
+      "eval_loss": 0.6206706762313843,
+      "eval_matthews_correlation": 0.3308080012085053,
+      "eval_runtime": 1.1954,
+      "eval_samples_per_second": 872.513,
+      "eval_steps_per_second": 55.212,
       "step": 54
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.5608728528022766,
-      "eval_matthews_correlation": 0.2462710523446019,
-      "eval_runtime": 1.1904,
-      "eval_samples_per_second": 876.167,
-      "eval_steps_per_second": 55.443,
+      "eval_loss": 0.7836025357246399,
+      "eval_matthews_correlation": 0.32126041966530916,
+      "eval_runtime": 0.7675,
+      "eval_samples_per_second": 1358.922,
+      "eval_steps_per_second": 85.991,
       "step": 81
     }
   ],
   "logging_steps": 500,
-  "max_steps": 81,
+  "max_steps": 135,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 3.6796428408677604e-05,
-    "num_train_epochs": 3,
+    "learning_rate": 5.5246354176486404e-05,
+    "num_train_epochs": 5,
     "per_device_train_batch_size": 32,
-    "seed": 1
+    "seed": 29
   }
 }

run-4/checkpoint-81/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bcf9d16a39b36f26738ac27ccd3d625cd9d28ed3e5f9694dea854578c72fb9e
+oid sha256:e00559bb0da783ae52b61b6a8510ccb795226928432dd308acf4d541364e8625
 size 4984

run-5/checkpoint-27/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b7264777c389cb61e3202e49cd712d6a0a7c71278279effc9d1901b3bd91bac
+oid sha256:30f4e9548471ed4ffad58c93aa048da4c43864ff312fefc44f489d5327cd82e9
 size 267832560

run-5/checkpoint-27/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0f772f075bb533b3e4c635270bf552c850b145a89978ebcbbc5303c26837565
+oid sha256:afc6f78f1cbc7b827a101714a2fabe5f7eddc45f98edec52e6acf41d1bea2fd0
 size 535727290

run-5/checkpoint-27/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22f40887a9aa64436f373c2378e34877cfef171d5714e7005f6563bf4cdadc6d
-size 14308
+oid sha256:3edc3ea9c0f5f72945bdf38de857511e571e8880416455d373d303b9579bc180
+size 14244

run-5/checkpoint-27/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b1cfe251fe716f208540e6f5d0e55c8a1c32c5ace5bb2879270776ed8a783bd
+oid sha256:006c4bfc292d594d01a271e51b2f78ed5356468489f917401f851ad07318b173
 size 1064

run-5/checkpoint-27/trainer_state.json

@@ -10,11 +10,11 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6698710918426514,
+      "eval_loss": 0.6356618404388428,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.8001,
-      "eval_samples_per_second": 1303.648,
-      "eval_steps_per_second": 82.494,
+      "eval_runtime": 0.7718,
+      "eval_samples_per_second": 1351.417,
+      "eval_steps_per_second": 85.516,
       "step": 27
     }
   ],
@@ -27,9 +27,9 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.8122310780931108e-06,
+    "learning_rate": 3.7805000392532386e-06,
     "num_train_epochs": 5,
     "per_device_train_batch_size": 32,
-    "seed": 21
+    "seed": 39
   }
 }

run-5/checkpoint-27/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12789646f1ace8590d718854a0dcb7cbdcd7655dfa3e3b9eea3031d650c025e3
+oid sha256:994323cb4d85b1be62c90aa51db25a1c278952252319cd5846250f9a6537ab3f
 size 4984

runs/Feb28_19-52-39_5620ed9b2fff/events.out.tfevents.1709151577.5620ed9b2fff.209.24

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed5a53f78700e088e1a7eccff9e4328eaf3bbb3e9bc98ca4fb90b5f38d9e6b6
+size 5201

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e00559bb0da783ae52b61b6a8510ccb795226928432dd308acf4d541364e8625
+oid sha256:994323cb4d85b1be62c90aa51db25a1c278952252319cd5846250f9a6537ab3f
 size 4984