Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46927eb7f44466a1ba4fea38fee7cfd01e70fe7441140288a7d7427551f825b5
+oid sha256:564ce9ac36d1141528e4172d0347047e6f8ca54e1e5b4a27ce0f640a71ad0619
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c188ce8aee542ede6f5a5529abea22bf64c05794fe771ca6aa6188696394964
+oid sha256:e1fa433ffb43f9528864f1659dcb8f39d996c62c5998fb7a30fd038d99e35a2a
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f40a4c065023b7c7e84169852874083c9c8aff5ea2268e61269a141fdbb1b4f
+oid sha256:9e331ef2a3c31b8085c139afa029f7a7bec4b0c238a8a66416325de12e6bb446
 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": 0.085199344620426,
+  "epoch": 0.10922992900054615,
   "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": 0.8317,
       "step": 35
+    },
+    {
+      "epoch": 0.08738394320043692,
+      "grad_norm": 14.620291709899902,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.9143,
+      "step": 40
+    },
+    {
+      "epoch": 0.08738394320043692,
+      "eval_loss": 0.8667392134666443,
+      "eval_runtime": 15.046,
+      "eval_samples_per_second": 12.827,
+      "eval_steps_per_second": 6.447,
+      "step": 40
+    },
+    {
+      "epoch": 0.09830693610049153,
+      "grad_norm": 21.33104133605957,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8446,
+      "step": 45
+    },
+    {
+      "epoch": 0.10922992900054615,
+      "grad_norm": 14.127695083618164,
+      "learning_rate": 0.0,
+      "loss": 0.8292,
+      "step": 50
+    },
+    {
+      "epoch": 0.10922992900054615,
+      "eval_loss": 0.8796916604042053,
+      "eval_runtime": 14.9708,
+      "eval_samples_per_second": 12.892,
+      "eval_steps_per_second": 6.479,
+      "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": 7501033808855040.0,
+  "total_flos": 9603234366750720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null