Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a4ce6e3019d681836212151027d3064c0c5b3831c54fadc12c280e9b33449b
+oid sha256:7ad109b7efaf7ba16b7611da3bd4c3ee2260763ad029ccc25a8e2e3ed70ec9ec
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5434657c40ace709bfa11fef9723c821fd3a81e9b2803d594b2f479abdaaaaeb
+oid sha256:a54f24628b0ca17af5af748cac645e7936caae1db25eb77c6f669747e817737e
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:354fcbfab35beb320321fc72abe28e2ba17d63b820a2c10b34cfe337af85be52
+oid sha256:cd9f9fa4f12eb656180c05ab6d0e11868fa1b817f9a6c422f3c0302601735f4e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010900705750821046,
+  "epoch": 0.013975263783103906,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 20.223,
       "eval_steps_per_second": 10.118,
       "step": 39
+    },
+    {
+      "epoch": 0.011180211026483125,
+      "grad_norm": 2.5868406295776367,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.529,
+      "step": 40
+    },
+    {
+      "epoch": 0.011459716302145203,
+      "grad_norm": 1.970118761062622,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 0.4402,
+      "step": 41
+    },
+    {
+      "epoch": 0.01173922157780728,
+      "grad_norm": 2.0284950733184814,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.5627,
+      "step": 42
+    },
+    {
+      "epoch": 0.01201872685346936,
+      "grad_norm": 1.4307758808135986,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 0.3497,
+      "step": 43
+    },
+    {
+      "epoch": 0.012298232129131437,
+      "grad_norm": 2.6283090114593506,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.5966,
+      "step": 44
+    },
+    {
+      "epoch": 0.012577737404793515,
+      "grad_norm": 2.379211902618408,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.5158,
+      "step": 45
+    },
+    {
+      "epoch": 0.012857242680455594,
+      "grad_norm": 1.5609519481658936,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.3514,
+      "step": 46
+    },
+    {
+      "epoch": 0.013136747956117672,
+      "grad_norm": 2.671844720840454,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.6922,
+      "step": 47
+    },
+    {
+      "epoch": 0.01341625323177975,
+      "grad_norm": 1.539504051208496,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.3575,
+      "step": 48
+    },
+    {
+      "epoch": 0.013695758507441829,
+      "grad_norm": 2.156888484954834,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 0.4189,
+      "step": 49
+    },
+    {
+      "epoch": 0.013975263783103906,
+      "grad_norm": 1.5501902103424072,
+      "learning_rate": 0.0,
+      "loss": 0.3632,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.234820118085632e+16,
+  "total_flos": 1.5831027154944e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null