Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca8fe9f4d3b1eda4a732430841ce9a13e294d4165cbbeecd8e420652e2ca1d59
+oid sha256:5fab592c67f9aa38c48d9dab26dc2834ae1fde2e535f26faed2bb0a9f4e0cef2
 size 267832560

run-1/checkpoint-1072/config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.45.0",
   "vocab_size": 30522
 }

run-1/checkpoint-1072/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9992887f6907f8916987f3e3d5b5cd5f9a668b44cebeae398a79e142aced221
+oid sha256:5fab592c67f9aa38c48d9dab26dc2834ae1fde2e535f26faed2bb0a9f4e0cef2
 size 267832560

run-1/checkpoint-1072/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fc9517b39355720ca587337ba7563051682d885fb178f3d079846331368417c
+oid sha256:0d64bd1b3cd64174fcf21cc7191339a20d65d127c808ebb360e7cbfed0e4ab6f
 size 535727290

run-1/checkpoint-1072/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32ddadbd4e9ce4478d8580a2b23d53d37db7c6d53eeed56612b957a8c00b76dc
-size 14308
+oid sha256:9be557abd511148330f4618597443cd2d735141778483b075e669b8068a498e5
+size 14244

run-1/checkpoint-1072/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3765e02ab4bcae5228f1b22b52d5b68ecef8a19a4fc159b8e8f029723c547b6
+oid sha256:7ee211d1f52c748ba0df37e854b3aeed772675565bd36b91a1cfe786c1df4766
 size 1064

run-1/checkpoint-1072/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.46849580082104064,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-804",
+  "best_metric": 0.44997112166326025,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-1072",
   "epoch": 4.0,
   "eval_steps": 500,
   "global_step": 1072,
@@ -10,52 +10,52 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.5035493969917297,
-      "eval_matthews_correlation": 0.4141806938515634,
-      "eval_runtime": 0.7419,
-      "eval_samples_per_second": 1405.832,
-      "eval_steps_per_second": 88.96,
+      "eval_loss": 0.5182795524597168,
+      "eval_matthews_correlation": 0.3637991719695883,
+      "eval_runtime": 0.8749,
+      "eval_samples_per_second": 1192.137,
+      "eval_steps_per_second": 75.437,
       "step": 268
     },
     {
-      "epoch": 1.87,
-      "grad_norm": 4.896795749664307,
-      "learning_rate": 5.453884401804003e-06,
-      "loss": 0.4997,
+      "epoch": 1.8656716417910446,
+      "grad_norm": 5.394637107849121,
+      "learning_rate": 4.082371431187213e-06,
+      "loss": 0.5021,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.4967799484729767,
-      "eval_matthews_correlation": 0.44251427534495513,
-      "eval_runtime": 0.8433,
-      "eval_samples_per_second": 1236.743,
-      "eval_steps_per_second": 78.26,
+      "eval_loss": 0.5294386148452759,
+      "eval_matthews_correlation": 0.44429652763655303,
+      "eval_runtime": 0.8769,
+      "eval_samples_per_second": 1189.431,
+      "eval_steps_per_second": 75.266,
       "step": 536
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.49384433031082153,
-      "eval_matthews_correlation": 0.46849580082104064,
-      "eval_runtime": 1.1521,
-      "eval_samples_per_second": 905.341,
-      "eval_steps_per_second": 57.289,
+      "eval_loss": 0.4963017404079437,
+      "eval_matthews_correlation": 0.446244823436024,
+      "eval_runtime": 0.9086,
+      "eval_samples_per_second": 1147.897,
+      "eval_steps_per_second": 72.638,
       "step": 804
     },
     {
-      "epoch": 3.73,
-      "grad_norm": 8.912487030029297,
-      "learning_rate": 6.865029316956087e-07,
-      "loss": 0.3522,
+      "epoch": 3.7313432835820897,
+      "grad_norm": 8.369268417358398,
+      "learning_rate": 5.138649353941947e-07,
+      "loss": 0.379,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_loss": 0.5385918021202087,
-      "eval_matthews_correlation": 0.430812413056651,
-      "eval_runtime": 0.8323,
-      "eval_samples_per_second": 1253.098,
-      "eval_steps_per_second": 79.295,
+      "eval_loss": 0.5046903491020203,
+      "eval_matthews_correlation": 0.44997112166326025,
+      "eval_runtime": 1.1052,
+      "eval_samples_per_second": 943.695,
+      "eval_steps_per_second": 59.716,
       "step": 1072
     }
   ],
@@ -64,13 +64,25 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 500,
-  "total_flos": 192081608932020.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 191790801595908.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.0221265871912396e-05,
+    "learning_rate": 7.650877926980232e-06,
     "num_train_epochs": 4,
     "per_device_train_batch_size": 32,
-    "seed": 8
+    "seed": 28
   }
 }

run-1/checkpoint-1072/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29d6b485a188c4e5c57b6f3bb948e3315674066d3a6ec8f44d6d328263cd659b
-size 4984
+oid sha256:55916040b5530f85fbbef38cd42dcd18934cd6b77c8a8a1a110fdc3d400f34d0
+size 5304

run-1/checkpoint-536/config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.45.0",
   "vocab_size": 30522
 }

run-1/checkpoint-536/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:362d9c0cd2587fbb0107cad0126e6f5d8cff717dff52b10facf7769e2fb5712d
+oid sha256:4d47c92c5e36c8a03fde5daea74331ab41f371d64d924be029b623731f380590
 size 267832560

run-1/checkpoint-536/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5212b8745eb1c4c6ef881e3d21b4023283b2bc6765d8cb3aab22e3fe10e74e9
+oid sha256:a9302b24adc716d30cf9a7ae2582dd2e7391d94d421be52de496081e5fb9e75b
 size 535727290

run-1/checkpoint-536/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c3a6d458d1ea31703d0759423a03a8df70fee2479aeb6598078341111b8adb
-size 14308
+oid sha256:5f9e3aaf6b37b75264fbb2c562b3c32515689962db3ac97d7b0606726a5f7b4f
+size 14244

run-1/checkpoint-536/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b05a47d04eae8f5a42931783c79ad8a5775116597c4d7a406555dd541bfaf966
+oid sha256:b92c13dbfb54f85d196c6521b1ca7b6d5d3d5505259ca1f56b826b83152adafb
 size 1064

run-1/checkpoint-536/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.44251427534495513,
+  "best_metric": 0.44429652763655303,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-536",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,27 +10,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.5035493969917297,
-      "eval_matthews_correlation": 0.4141806938515634,
-      "eval_runtime": 0.7419,
-      "eval_samples_per_second": 1405.832,
-      "eval_steps_per_second": 88.96,
+      "eval_loss": 0.5182795524597168,
+      "eval_matthews_correlation": 0.3637991719695883,
+      "eval_runtime": 0.8749,
+      "eval_samples_per_second": 1192.137,
+      "eval_steps_per_second": 75.437,
       "step": 268
     },
     {
-      "epoch": 1.87,
-      "grad_norm": 4.896795749664307,
-      "learning_rate": 5.453884401804003e-06,
-      "loss": 0.4997,
+      "epoch": 1.8656716417910446,
+      "grad_norm": 5.394637107849121,
+      "learning_rate": 4.082371431187213e-06,
+      "loss": 0.5021,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.4967799484729767,
-      "eval_matthews_correlation": 0.44251427534495513,
-      "eval_runtime": 0.8433,
-      "eval_samples_per_second": 1236.743,
-      "eval_steps_per_second": 78.26,
+      "eval_loss": 0.5294386148452759,
+      "eval_matthews_correlation": 0.44429652763655303,
+      "eval_runtime": 0.8769,
+      "eval_samples_per_second": 1189.431,
+      "eval_steps_per_second": 75.266,
       "step": 536
     }
   ],
@@ -39,13 +39,25 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 500,
-  "total_flos": 96116481642000.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 95730204637716.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.0221265871912396e-05,
+    "learning_rate": 7.650877926980232e-06,
     "num_train_epochs": 4,
     "per_device_train_batch_size": 32,
-    "seed": 8
+    "seed": 28
   }
 }

run-1/checkpoint-536/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29d6b485a188c4e5c57b6f3bb948e3315674066d3a6ec8f44d6d328263cd659b
-size 4984
+oid sha256:55916040b5530f85fbbef38cd42dcd18934cd6b77c8a8a1a110fdc3d400f34d0
+size 5304

run-1/checkpoint-804/config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.45.0",
   "vocab_size": 30522
 }

run-1/checkpoint-804/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4784b2cdaf1f4f2a65b67673cf9a474f50aacc6b6b52a55770494552957df28b
+oid sha256:3a83a3ee2028627cff6d49c087171ffc2d96b89101278ec92ba41d203888f48d
 size 267832560

run-1/checkpoint-804/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:494174d39b2739ea5767bec872526ea91a8f51fb559ed3ecd20e2d63381bd46c
+oid sha256:fc803f94d7404c4fb2922a20bca972cf6c37b31c3ce75f8ac3fbd77275346de3
 size 535727290

run-1/checkpoint-804/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65c4502cc2c96e2c95cfbd885846a4486d9bbe6f82fd2b8441148c27de597eb2
-size 14308
+oid sha256:409b9078199aaff19d2f454e6d0a0a6b622f5595cbc7effb5585b7100c2cc7d8
+size 14244

run-1/checkpoint-804/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76cbf4faf8458eeab8085fe97b4e0f9442c5aa8273abf11a8f8bb22a481d6a86
+oid sha256:242b87443cb49e20de4211b0f90b9a4c63be961056ed1c678ddb6e4e0d78afe2
 size 1064

run-1/checkpoint-804/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.46849580082104064,
+  "best_metric": 0.446244823436024,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-804",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,36 +10,36 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.5035493969917297,
-      "eval_matthews_correlation": 0.4141806938515634,
-      "eval_runtime": 0.7419,
-      "eval_samples_per_second": 1405.832,
-      "eval_steps_per_second": 88.96,
+      "eval_loss": 0.5182795524597168,
+      "eval_matthews_correlation": 0.3637991719695883,
+      "eval_runtime": 0.8749,
+      "eval_samples_per_second": 1192.137,
+      "eval_steps_per_second": 75.437,
       "step": 268
     },
     {
-      "epoch": 1.87,
-      "grad_norm": 4.896795749664307,
-      "learning_rate": 5.453884401804003e-06,
-      "loss": 0.4997,
+      "epoch": 1.8656716417910446,
+      "grad_norm": 5.394637107849121,
+      "learning_rate": 4.082371431187213e-06,
+      "loss": 0.5021,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.4967799484729767,
-      "eval_matthews_correlation": 0.44251427534495513,
-      "eval_runtime": 0.8433,
-      "eval_samples_per_second": 1236.743,
-      "eval_steps_per_second": 78.26,
+      "eval_loss": 0.5294386148452759,
+      "eval_matthews_correlation": 0.44429652763655303,
+      "eval_runtime": 0.8769,
+      "eval_samples_per_second": 1189.431,
+      "eval_steps_per_second": 75.266,
       "step": 536
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.49384433031082153,
-      "eval_matthews_correlation": 0.46849580082104064,
-      "eval_runtime": 1.1521,
-      "eval_samples_per_second": 905.341,
-      "eval_steps_per_second": 57.289,
+      "eval_loss": 0.4963017404079437,
+      "eval_matthews_correlation": 0.446244823436024,
+      "eval_runtime": 0.9086,
+      "eval_samples_per_second": 1147.897,
+      "eval_steps_per_second": 72.638,
       "step": 804
     }
   ],
@@ -48,13 +48,25 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 500,
-  "total_flos": 96116481642000.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 95730204637716.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.0221265871912396e-05,
+    "learning_rate": 7.650877926980232e-06,
     "num_train_epochs": 4,
     "per_device_train_batch_size": 32,
-    "seed": 8
+    "seed": 28
   }
 }

run-1/checkpoint-804/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29d6b485a188c4e5c57b6f3bb948e3315674066d3a6ec8f44d6d328263cd659b
-size 4984
+oid sha256:55916040b5530f85fbbef38cd42dcd18934cd6b77c8a8a1a110fdc3d400f34d0
+size 5304

runs/Sep26_13-34-33_f266a1036e13/events.out.tfevents.1727358189.f266a1036e13.258.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebf518373c6afe38ee8e31b1e4a6d789d20ac210800b0f4d65682c148044d916
-size 5841
+oid sha256:809731c6da6eb614081da5f258bc5912713a5c1119ce0f3170b0c3a2a014040c
+size 7076