Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44d5a69b5f1ebda02e68939c126da3a9a8f77b44605b71c2dbbed7798f40079d
+oid sha256:cf44ba971c6ef1f961437f9ae25a0803e6ce8bc377964eac8b8009c9c20624fd
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82208daa56a18be13aa6cebc801f4c1c58d43a3670299a2b8be630a1655cdd97
+oid sha256:74199d1ede2c8d7fb2f8140a99cf4e09e7e95ebbd1a7a591e962285ae9377e9c
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
+oid sha256:572c5653b97399d6dc550389d4e48df5479adab7c80147f357d4d04c0f7252da
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00577408877661494,
+  "epoch": 0.007217610970768676,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,13 @@
       "eval_samples_per_second": 4.824,
       "eval_steps_per_second": 2.414,
       "step": 4
+    },
+    {
+      "epoch": 0.007217610970768676,
+      "grad_norm": 8.078629493713379,
+      "learning_rate": 5e-05,
+      "loss": 23.6548,
+      "step": 5
     }
   ],
   "logging_steps": 1,
@@ -73,12 +80,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.013191777714176e+16,
+  "total_flos": 1.26648972214272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null