End of training

logs/events.out.tfevents.1702876267.f99763f5b9a6.723.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf5c26c710428f462abcbc580360375f22cb30a81faaa74421ccb6250c88498e
+size 4513

logs/events.out.tfevents.1702876859.f99763f5b9a6.4535.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:248ff1d181b42cb91a09739a9f89a17a2b78a1fab5d824eecced7267ad4d77c6
+size 4513

logs/events.out.tfevents.1702878467.f99763f5b9a6.10920.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e6e4794f886388425eb77f6201f004600f10ccce8e75844ecc5e380e3e5de5
+size 4184

logs/events.out.tfevents.1702878800.f99763f5b9a6.13297.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39cfa47ccf68f2fbed9dfe5c29d570f7dbabcc9b83b9b717b470016320868226
+size 4513

logs/events.out.tfevents.1702880315.f99763f5b9a6.18132.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f714c78d9c2b52d288115f6477442cd90fb87eaea78fd453f5a416aecdf3fe64
+size 4513

logs/events.out.tfevents.1702880779.f99763f5b9a6.21780.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6d58af316b8de561f0c5a1e6412408e316dc14577ded1196af0921c53dc66c9
+size 4661

logs/events.out.tfevents.1702881497.f99763f5b9a6.25112.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:009961e1cee8aab1ede9a12c3a40240eb2a81bbc71316c808c9c008889cf1b47
+size 4661

logs/events.out.tfevents.1702881777.f99763f5b9a6.26487.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3a5da954c8b9a89b12b39dc2878586d19057d886e745061640e41c748dc941
+size 4661

logs/events.out.tfevents.1702884329.f99763f5b9a6.33712.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36b422e32dd33ea2cdaba8d760c9d6755ea062d40480a39dc65299d4295e7b00
+size 4661

logs/events.out.tfevents.1702884796.f99763f5b9a6.39113.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02d5012b27cb0c9eda2ceb05ebe396f6b316f93f1f06d7258600be0c57eeb853
+size 4507

logs/events.out.tfevents.1702884946.f99763f5b9a6.39113.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e6b134c35e6133dc688d8718617c7fef7c46fec3d2e5995f5981d7416f8a44
+size 4855

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5783b94e2123ea92a2fcb12f597daf94cce815710a6a4759832dcc278ace309
+oid sha256:9e7dc4954663319ae553f7c8324f0be8209074fd1a7d694d36b48d737871b3fb
 size 497918592

trainer_state.json

@@ -1,46 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09002246976143806,
-  "eval_steps": 8000,
-  "global_step": 5649,
+  "epoch": 0.25,
+  "eval_steps": 10,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.01,
-      "step": 628,
-      "total_flos": 1312731168768000.0,
-      "train_loss": 1.1908922134690982,
-      "train_runtime": 322.5365,
-      "train_samples_per_second": 62.257,
-      "train_steps_per_second": 1.947
-    },
-    {
-      "epoch": 0.09,
-      "step": 5648,
-      "total_flos": 1.1806219173888e+16,
-      "train_loss": 1.0376979406427054,
-      "train_runtime": 2474.3011,
-      "train_samples_per_second": 73.04,
-      "train_steps_per_second": 2.283
-    },
-    {
-      "epoch": 0.09,
-      "step": 5649,
-      "total_flos": 1.1808309510144e+16,
-      "train_loss": 0.00021651981783917697,
-      "train_runtime": 2.6879,
-      "train_samples_per_second": 67235.558,
-      "train_steps_per_second": 2101.269
+      "epoch": 0.25,
+      "step": 1,
+      "total_flos": 2090336256000.0,
+      "train_loss": 1.2067252397537231,
+      "train_runtime": 2.2969,
+      "train_samples_per_second": 3.918,
+      "train_steps_per_second": 0.435
     }
   ],
-  "logging_steps": 8000,
-  "max_steps": 5648,
+  "logging_steps": 10,
+  "max_steps": 1,
   "num_train_epochs": 1,
-  "save_steps": 8000,
-  "total_flos": 1.1808309510144e+16,
+  "save_steps": 10,
+  "total_flos": 2090336256000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38704735567bbcf51c349997edab9d7540450f26004fd210e7261e2de78eb5fc
+oid sha256:6bbcb94865a2bf4b60e2a118abbff3a420d0f7d45d582f1b90c7cbc704e6f54d
 size 4600