Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5676b1fab164f622838fb60ae0630b3dfd94ff147bbf20dfe9452014d3db366e
+oid sha256:a885f6acca0cb5d90ee9857e1f8d860f84588c30d5936e2e8de39201865c4468
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3520d799ef2880ad29434999856bc553c6b5d32958a06a467be9ff6400b33603
+oid sha256:c57fbe09dd098852f0bda93bb9393c9c15feae756c341d3d216b16fbab2aac01
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cfd169eaaa2e100acfe8ba68db24784222eedca4046124bbd3f932d9cc2b713
+oid sha256:ac8af46479364885d03a3cf2664989b965bd7a398b8d1d5d9293a9bfc767a0b9
 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": 0.016586921850079744,
+  "epoch": 0.02126528442317916,
   "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": 0.552,
       "step": 35
+    },
+    {
+      "epoch": 0.01701222753854333,
+      "grad_norm": 0.4537512958049774,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5682,
+      "step": 40
+    },
+    {
+      "epoch": 0.01701222753854333,
+      "eval_loss": 0.5585330724716187,
+      "eval_runtime": 105.982,
+      "eval_samples_per_second": 9.341,
+      "eval_steps_per_second": 4.671,
+      "step": 40
+    },
+    {
+      "epoch": 0.019138755980861243,
+      "grad_norm": 0.4814342260360718,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5492,
+      "step": 45
+    },
+    {
+      "epoch": 0.02126528442317916,
+      "grad_norm": 0.4501843750476837,
+      "learning_rate": 0.0,
+      "loss": 0.5529,
+      "step": 50
+    },
+    {
+      "epoch": 0.02126528442317916,
+      "eval_loss": 0.5569940209388733,
+      "eval_runtime": 105.8358,
+      "eval_samples_per_second": 9.354,
+      "eval_steps_per_second": 4.677,
+      "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": 1.1744732975726592e+16,
+  "total_flos": 1.5166426834796544e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null