Training in progress, step 240, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38525614635b5a1802bada9dfb35967342f89a8f39cef59178364b0e09a3606b
+oid sha256:a8055d2764c12216b0e46e9e6bf1bdb2ed21e379d85c4c630698a9f4b56f3abe
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73c8b2403ce009418422c824501cf772c8ea12de61f38702a0e9951a24f18af6
+oid sha256:002030670da2c6c1d5f6f14b7e7d0cf24108da51304d9ecb3a09892895958096
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfb84979c669ccc8d28e35aa58c2587b05a8b6df327dd2931fe3015d79e3a7fb
+oid sha256:eac82c9e97acc88aa1fa4930480a8fc2c4136df9608e7f4941250ac47b8c3ac9
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdb198a10323219718c28f69eda76ef66dcd9b432d9acb59767df7cf35ba400d
+oid sha256:10ac16ada9aeee5f77175e25a04261752f50812666958fe6ce8c2d82948a891d
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134925db3ae71cb88cb92756cc2cdea3066935b4ecbf838e78bbfa60c95c3818
+oid sha256:108ec0968af236f6199c1f716a40487225162213cb414b717c6f1aeb82bcbc29
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.923076923076923,
+  "epoch": 18.46153846153846,
   "eval_steps": 40,
-  "global_step": 220,
+  "global_step": 240,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -209,6 +209,28 @@
       "learning_rate": 0.00015000000000000001,
       "loss": 9.4381,
       "step": 220
+    },
+    {
+      "epoch": 17.692307692307693,
+      "grad_norm": 0.39453125,
+      "learning_rate": 0.00014515333583108896,
+      "loss": 9.4021,
+      "step": 230
+    },
+    {
+      "epoch": 18.46153846153846,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 9.3725,
+      "step": 240
+    },
+    {
+      "epoch": 18.46153846153846,
+      "eval_loss": 9.3687162399292,
+      "eval_runtime": 5.2722,
+      "eval_samples_per_second": 284.702,
+      "eval_steps_per_second": 4.552,
+      "step": 240
     }
   ],
   "logging_steps": 10,
@@ -228,7 +250,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 90014880890880.0,
+  "total_flos": 98198051880960.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null