Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f6ad556bd97da50e305b98c8a484073658e36cc49bb538e31e71541abe6e6e4
+oid sha256:171ce7830b9c10355bdad8a79c53bc338e90a4970378fd8b0afcf9acbca9a682
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6126a4c3dfc2e6bc13772ba8501d4b23f13634afef8cc8c57a97816cc4b69be2
+oid sha256:815fa70668c4593dde78692197fd65de4a93cdc1dbd16c81fd8161a6d50b15c6
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9dbdd915e523edf9fbadf618141dbc0ab0a7ef9e84774dcab8a9237c5a21f51
+oid sha256:e3bc68ed2edac47b7ad5543f96be38b55d18efd2ed351d107e1a33fa8224f3bc
 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": 0.02741652021089631,
+  "epoch": 0.0351493848857645,
   "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": 1.6692,
       "step": 35
+    },
+    {
+      "epoch": 0.028119507908611598,
+      "grad_norm": 0.27632302045822144,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8322,
+      "step": 40
+    },
+    {
+      "epoch": 0.028119507908611598,
+      "eval_loss": 1.731584906578064,
+      "eval_runtime": 114.2842,
+      "eval_samples_per_second": 5.241,
+      "eval_steps_per_second": 2.625,
+      "step": 40
+    },
+    {
+      "epoch": 0.03163444639718805,
+      "grad_norm": 0.2888457179069519,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.799,
+      "step": 45
+    },
+    {
+      "epoch": 0.0351493848857645,
+      "grad_norm": 0.28239622712135315,
+      "learning_rate": 0.0,
+      "loss": 1.7241,
+      "step": 50
+    },
+    {
+      "epoch": 0.0351493848857645,
+      "eval_loss": 1.7305543422698975,
+      "eval_runtime": 114.4401,
+      "eval_samples_per_second": 5.234,
+      "eval_steps_per_second": 2.621,
+      "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": 1.3592561159503872e+16,
+  "total_flos": 1.74263604609024e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null