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:e6a54b485fe58a06f47f292916d7d164dcd7871580bb83c5e68a49b8742a415b
+oid sha256:bf83d28559a820d29191df998d0a2bcfbe8d657ca31860db82a4d4ea8e5321d5
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4742c93f3b5c46b0ca16bfd73ac47197e95607cd612d605bd8977490cce92b6
+oid sha256:311cadb44da511f1f7baa694e9efb0e00dd30e152da7acb19834ae88cfc833a2
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bebbe731bd9094c7ae8f274487d73bb48b05017603343298a02474cb28c07b94
+oid sha256:fdedc6314c9f75a198e58bac1038c3adc8fc2a5f73e82a6a71a371fdac27e199
 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": 0.03192305724663631,
+  "epoch": 0.04092699647004656,
   "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": 168.772,
       "eval_steps_per_second": 21.102,
       "step": 30
+    },
+    {
+      "epoch": 0.032741597176037245,
+      "grad_norm": 0.016216600313782692,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.9312,
+      "step": 40
+    },
+    {
+      "epoch": 0.032741597176037245,
+      "eval_loss": 11.930665969848633,
+      "eval_runtime": 48.5505,
+      "eval_samples_per_second": 169.514,
+      "eval_steps_per_second": 21.194,
+      "step": 40
+    },
+    {
+      "epoch": 0.04092699647004656,
+      "grad_norm": 0.01642616279423237,
+      "learning_rate": 0.0,
+      "loss": 11.9304,
+      "step": 50
+    },
+    {
+      "epoch": 0.04092699647004656,
+      "eval_loss": 11.930656433105469,
+      "eval_runtime": 48.9823,
+      "eval_samples_per_second": 168.02,
+      "eval_steps_per_second": 21.008,
+      "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": 140848398336.0,
+  "total_flos": 180668792832.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null