Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08f18e99c662ff028bfb7af898495cb6ff49c45441cbd14914da93879dd0df93
+oid sha256:b9dc3a8b046f0ea6e9aeb64f708459c15f6d72dc4ad60fc0cb943be1b90628b0
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65e3f523c634512d291dcdc66563a4a8d8227b87ae1202fc261535f6cd1d834c
+oid sha256:0a155a7289540023b7a179c8a8bc08700da0e2f74a5305c67bfb53a7dd7c6f33
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cbfbff5445caae9f2668acaf55142bb15a402c199154485e79ab39da1e78943
+oid sha256:7092244c60798e1ab03d4fe68ee97ba243124819620dca59a1f7c2ad2682481a
 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": 0.0015285126396237508,
+  "epoch": 0.0019596315892612187,
   "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": 2.5803,
       "step": 35
+    },
+    {
+      "epoch": 0.0015677052714089751,
+      "grad_norm": 0.8234419822692871,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.5542,
+      "step": 40
+    },
+    {
+      "epoch": 0.0015677052714089751,
+      "eval_loss": 2.580919027328491,
+      "eval_runtime": 411.7251,
+      "eval_samples_per_second": 26.095,
+      "eval_steps_per_second": 13.048,
+      "step": 40
+    },
+    {
+      "epoch": 0.001763668430335097,
+      "grad_norm": 0.8764637112617493,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.5428,
+      "step": 45
+    },
+    {
+      "epoch": 0.0019596315892612187,
+      "grad_norm": 0.7842684388160706,
+      "learning_rate": 0.0,
+      "loss": 2.6029,
+      "step": 50
+    },
+    {
+      "epoch": 0.0019596315892612187,
+      "eval_loss": 2.575305223464966,
+      "eval_runtime": 414.8734,
+      "eval_samples_per_second": 25.897,
+      "eval_steps_per_second": 12.949,
+      "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": 1264763208204288.0,
+  "total_flos": 1621491292569600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null