Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b380ef8f071ad957f4cf263a34e91e6bd7df176f75f7ad67052509b886737d
+oid sha256:c665c14fd878a8a8e5be4d7263a4b93bc39c83656da15a9939a683f3be5c5ca7
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a03d60009e87d27059eb66dfde00adee7eda5655869416d54b704093d8a354b
+oid sha256:e1781cabea83280802cdfc165b2441847ca0842eaaa9ea7c54e28a4250946dca
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e65111cb0ec46764a764d8f16e44e4defb1d1070a215e01443ea2b6acb2325fb
+oid sha256:e0a43b2bf8fa4dec06b5fb5d37d9b9ceb42f52f8e240513c811a6517380a3e2c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6135693215339233,
+  "epoch": 0.7866273352999017,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,36 @@
       "eval_samples_per_second": 15.67,
       "eval_steps_per_second": 1.972,
       "step": 30
+    },
+    {
+      "epoch": 0.6293018682399213,
+      "grad_norm": 0.04831311106681824,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0032,
+      "step": 40
+    },
+    {
+      "epoch": 0.6293018682399213,
+      "eval_loss": 0.001506477128714323,
+      "eval_runtime": 27.3858,
+      "eval_samples_per_second": 15.665,
+      "eval_steps_per_second": 1.972,
+      "step": 40
+    },
+    {
+      "epoch": 0.7866273352999017,
+      "grad_norm": 0.09499865770339966,
+      "learning_rate": 0.0,
+      "loss": 0.0024,
+      "step": 50
+    },
+    {
+      "epoch": 0.7866273352999017,
+      "eval_loss": 0.001404269365593791,
+      "eval_runtime": 27.4771,
+      "eval_samples_per_second": 15.613,
+      "eval_steps_per_second": 1.965,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +104,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1925210437517312e+17,
+  "total_flos": 1.52887313301504e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null