Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f818eed3b71ae86bf60325ca842c29db729092a3a00f068d37dc3f8bc0e71f7b
+oid sha256:71d593a166093506cff6ad983870b1972ed87c3ca52d1a9177fec94514c522d6
 size 2610104820

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c7f95b813a9cd3ec4c03febae19edca2984f716b88224e7f0858d8e07ac8181
+oid sha256:e2ccc17548892e36c8966cf50ffec82ca4c0d9aa652a15f51e1c05b63b216bf0
 size 5210004271

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef182b3769d944b189f876a5cac490559ff2ea07b4cbd3762299fdab1ce127f7
+oid sha256:032043679e88a4670001d7081f04bfea8360f4b5cce74f2dc24d2448e791dd14
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c384e9de8d22769c457fde7ec327a8b66d9e5e7803cfc2f5ad081bf4e28105c
+oid sha256:5e79c42299ae7a8c91c22377dcb5abd815ce8e10be1fead95ab281382c55da75
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.997206530510894,
+  "epoch": 9.997206530510894,
   "eval_steps": 50,
-  "global_step": 2259,
+  "global_step": 2510,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -682,6 +682,81 @@
       "eval_samples_per_second": 31.356,
       "eval_steps_per_second": 15.678,
       "step": 2250
+    },
+    {
+      "epoch": 9.162890309764729,
+      "grad_norm": 0.03132237493991852,
+      "learning_rate": 8.366533864541832e-06,
+      "loss": 0.0286,
+      "step": 2300
+    },
+    {
+      "epoch": 9.162890309764729,
+      "eval_loss": 0.07365094125270844,
+      "eval_runtime": 27.0251,
+      "eval_samples_per_second": 31.378,
+      "eval_steps_per_second": 15.689,
+      "step": 2300
+    },
+    {
+      "epoch": 9.361537028990005,
+      "grad_norm": 0.024464119225740433,
+      "learning_rate": 6.374501992031872e-06,
+      "loss": 0.0271,
+      "step": 2350
+    },
+    {
+      "epoch": 9.361537028990005,
+      "eval_loss": 0.07335445284843445,
+      "eval_runtime": 27.016,
+      "eval_samples_per_second": 31.389,
+      "eval_steps_per_second": 15.694,
+      "step": 2350
+    },
+    {
+      "epoch": 9.560183748215284,
+      "grad_norm": 0.02511492557823658,
+      "learning_rate": 4.382470119521913e-06,
+      "loss": 0.0278,
+      "step": 2400
+    },
+    {
+      "epoch": 9.560183748215284,
+      "eval_loss": 0.07323840260505676,
+      "eval_runtime": 27.0119,
+      "eval_samples_per_second": 31.394,
+      "eval_steps_per_second": 15.697,
+      "step": 2400
+    },
+    {
+      "epoch": 9.75883046744056,
+      "grad_norm": 0.0219442006200552,
+      "learning_rate": 2.3904382470119524e-06,
+      "loss": 0.0268,
+      "step": 2450
+    },
+    {
+      "epoch": 9.75883046744056,
+      "eval_loss": 0.07320257276296616,
+      "eval_runtime": 26.9808,
+      "eval_samples_per_second": 31.43,
+      "eval_steps_per_second": 15.715,
+      "step": 2450
+    },
+    {
+      "epoch": 9.95747718666584,
+      "grad_norm": 0.030443966388702393,
+      "learning_rate": 3.98406374501992e-07,
+      "loss": 0.027,
+      "step": 2500
+    },
+    {
+      "epoch": 9.95747718666584,
+      "eval_loss": 0.07312251627445221,
+      "eval_runtime": 27.0283,
+      "eval_samples_per_second": 31.375,
+      "eval_steps_per_second": 15.687,
+      "step": 2500
     }
   ],
   "logging_steps": 50,
@@ -696,7 +771,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }