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:d260f92882a84837c4e7aebad481dc5cf54290b3e23989c3edf8baf1bfba79cd
+oid sha256:d6022cd6a15ae496b2bb95abd5e27fd8406adb9ca72724694227a5c98d960add
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:362d10c695590078eef947e16fe545c2e951b944d930912d6e060497aefb2b24
+oid sha256:cc56cba6a4bf7711b421b280b6e898dd235a141747c263c75e6cd50225d3e809
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b71e7d5985870b6965f25a8a7214a793a5c935f0b038f27ab6a11f462f8b5f40
+oid sha256:74271b9b39fd27649c7799aa26d72c4af111394d232d582ba9f32e8c3fae0f52
 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": 0.0025429116338207248,
+  "epoch": 0.0032601431202829803,
   "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": 9.8223,
       "step": 35
+    },
+    {
+      "epoch": 0.0026081144962263846,
+      "grad_norm": 8.541926383972168,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.513,
+      "step": 40
+    },
+    {
+      "epoch": 0.0026081144962263846,
+      "eval_loss": 2.542236804962158,
+      "eval_runtime": 361.8354,
+      "eval_samples_per_second": 17.848,
+      "eval_steps_per_second": 8.924,
+      "step": 40
+    },
+    {
+      "epoch": 0.002934128808254682,
+      "grad_norm": 10.6914701461792,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 9.9373,
+      "step": 45
+    },
+    {
+      "epoch": 0.0032601431202829803,
+      "grad_norm": 10.446704864501953,
+      "learning_rate": 0.0,
+      "loss": 9.6477,
+      "step": 50
+    },
+    {
+      "epoch": 0.0032601431202829803,
+      "eval_loss": 2.536726713180542,
+      "eval_runtime": 361.4827,
+      "eval_samples_per_second": 17.865,
+      "eval_steps_per_second": 8.933,
+      "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": 6366664319827968.0,
+  "total_flos": 8162390153625600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null