Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f1e468389d5808ae38d27a766c36ec5d63ce8518e11b43a46d0558a94d6e466
+oid sha256:05dda7ebeb72859579c3d91edd76dda36544a3680bbd3c00fcfa7485fbf1583a
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9ffb6e5a2031d451a52dda721486be9ea0e094066b4f81fc615ded97d9e3ed2
+oid sha256:425ff0c8114146e1b90ef9c26935735572bd6acd71df52a4f1422c42456d4974
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4403875ec607cf3108caac6354185aadd4588ae4b29cc7dad762431733537e30
+oid sha256:89ffcad5a84b06fde95717df10413749838a6b711ecc83f3ebee00a93d200145
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009798379498775203,
+  "epoch": 0.012562024998429747,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 11.9243,
       "step": 35
+    },
+    {
+      "epoch": 0.010049619998743797,
+      "grad_norm": 0.21714992821216583,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9297,
+      "step": 40
+    },
+    {
+      "epoch": 0.010049619998743797,
+      "eval_loss": 11.927545547485352,
+      "eval_runtime": 40.6084,
+      "eval_samples_per_second": 41.272,
+      "eval_steps_per_second": 20.636,
+      "step": 40
+    },
+    {
+      "epoch": 0.011305822498586773,
+      "grad_norm": 0.2009456604719162,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.933,
+      "step": 45
+    },
+    {
+      "epoch": 0.012562024998429747,
+      "grad_norm": 0.1979771852493286,
+      "learning_rate": 0.0,
+      "loss": 11.9325,
+      "step": 50
+    },
+    {
+      "epoch": 0.012562024998429747,
+      "eval_loss": 11.927351951599121,
+      "eval_runtime": 40.1038,
+      "eval_samples_per_second": 41.792,
+      "eval_steps_per_second": 20.896,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4881081434112.0,
+  "total_flos": 6257796710400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null