Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70375a54792e3785c0d5b61db58facd0c5da0bd8b551841c28f169c3955d3d9a
+oid sha256:83f6107a757a3cfd31ad84b2fb4d9ac275bf2270930aa6f731b14a898803834a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bbdee0ebfc20c0d7a1c435f12b4ebd92dd8be574e74102460a7304fafe5e3df
+oid sha256:d57390b7fbcc0d37c13052e8c20619ffbc7cb632ebd97bca005a50c20e311f84
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79860259ff731f0b1c006300fee3fbd1e0fb1cad375751b62eee5d8cabbc13f0
+oid sha256:65941554dfccfdcf0ed28341039200adb2012eef3c09ec7b1fbc4a815a622955
 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": 0.0006908432273007072,
+  "epoch": 0.000885696445257317,
   "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": 1.6083,
       "step": 35
+    },
+    {
+      "epoch": 0.0007085571562058535,
+      "grad_norm": 7.160251140594482,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4506,
+      "step": 40
+    },
+    {
+      "epoch": 0.0007085571562058535,
+      "eval_loss": 1.5205236673355103,
+      "eval_runtime": 1600.3605,
+      "eval_samples_per_second": 14.853,
+      "eval_steps_per_second": 7.426,
+      "step": 40
+    },
+    {
+      "epoch": 0.0007971268007315853,
+      "grad_norm": 9.940959930419922,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1803,
+      "step": 45
+    },
+    {
+      "epoch": 0.000885696445257317,
+      "grad_norm": 10.175341606140137,
+      "learning_rate": 0.0,
+      "loss": 1.3866,
+      "step": 50
+    },
+    {
+      "epoch": 0.000885696445257317,
+      "eval_loss": 1.4981493949890137,
+      "eval_runtime": 1604.4754,
+      "eval_samples_per_second": 14.815,
+      "eval_steps_per_second": 7.407,
+      "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": 7259539673972736.0,
+  "total_flos": 9386538559340544.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null