Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ae53f5561a22819b9fd470830d7d640c9be9431e44bbaacf1613c834a672e61
+oid sha256:dae7c02ca9fca5a9513244691abde07a51d330cacc98c96365a04ed8ff94fe23
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddfd2e56b0344c5282584822191ed4024e28497a32fe2e8528505641cbc55f72
+oid sha256:a6a05b4a9413b77b75f5f9b076245a5504b8fc8ba9f72a621f0749c29164b76e
 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": 0.003105590062111801,
+  "epoch": 0.003981525720656155,
   "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": 1.3195,
       "step": 35
+    },
+    {
+      "epoch": 0.0031852205765249245,
+      "grad_norm": 6.3843092918396,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3911,
+      "step": 40
+    },
+    {
+      "epoch": 0.0031852205765249245,
+      "eval_loss": 0.34334591031074524,
+      "eval_runtime": 449.44,
+      "eval_samples_per_second": 11.766,
+      "eval_steps_per_second": 5.883,
+      "step": 40
+    },
+    {
+      "epoch": 0.00358337314859054,
+      "grad_norm": 5.103909015655518,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.4029,
+      "step": 45
+    },
+    {
+      "epoch": 0.003981525720656155,
+      "grad_norm": 4.658137798309326,
+      "learning_rate": 0.0,
+      "loss": 1.548,
+      "step": 50
+    },
+    {
+      "epoch": 0.003981525720656155,
+      "eval_loss": 0.34125182032585144,
+      "eval_runtime": 448.7319,
+      "eval_samples_per_second": 11.784,
+      "eval_steps_per_second": 5.892,
+      "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