Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:640119df5b7f685678918310f3c63d7c4737dcfab118e0c74e50cc2a8c4b80d1
+oid sha256:8d97b25b0c8cae1063956cd6b696448b2242c750505715542a7bd244bccb29f9
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42d550d9542a5f3c1f0dbd99b3ed137d0a2b78a8d60a4e0a916f7dbee62767e8
+oid sha256:521a966b236a477b591b604ca788cf12158854d8b90c5873f2965b25006cad3a
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f6132c086c411e9bdb0c32c2a53364b7f55dda21e5dfc4747b9c3b8e7b9d6df
+oid sha256:05903a3f9bd20d677c99c3e506efa2d1a286732f42b0455337aa37751cf18687
 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": 0.0017069140962655783,
+  "epoch": 0.00218835140546869,
   "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": 5.2927,
       "step": 35
+    },
+    {
+      "epoch": 0.0017506811243749522,
+      "grad_norm": 63.27540969848633,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.9622,
+      "step": 40
+    },
+    {
+      "epoch": 0.0017506811243749522,
+      "eval_loss": NaN,
+      "eval_runtime": 1117.7667,
+      "eval_samples_per_second": 8.607,
+      "eval_steps_per_second": 4.304,
+      "step": 40
+    },
+    {
+      "epoch": 0.001969516264921821,
+      "grad_norm": 97.67462158203125,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.3854,
+      "step": 45
+    },
+    {
+      "epoch": 0.00218835140546869,
+      "grad_norm": 109.79862976074219,
+      "learning_rate": 0.0,
+      "loss": 2.933,
+      "step": 50
+    },
+    {
+      "epoch": 0.00218835140546869,
+      "eval_loss": NaN,
+      "eval_runtime": 1116.4721,
+      "eval_samples_per_second": 8.617,
+      "eval_steps_per_second": 4.309,
+      "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": 1.3627007585746944e+16,
+  "total_flos": 1.7482881114832896e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null