Training in progress, step 3, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7d8ab371318f22944fbfa556aab06b73ace7d8ab52611a50ab5df0010541c3d
+oid sha256:59ecccf6b077063fd8fb96ba780006c0cb1ecf2c0ef87ffa48915bb67cb51254
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4d97a4bb38b7cf9d1264c5194a24202d8aae6b1ccaff17e29bb1f35befaf898
+oid sha256:541bce2e77c7190805415564216c849ab765af3ab1a5745b2ab5524059284bfc
 size 23337174

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e9764c8ecd69e28ff0cf17a2cc5bcd769560177c0aa4929b4db5cbdc3bbbbcd
+oid sha256:42b016f79355f73691cefa484bd2e9e2e609f2c69645383098b7e10ff4c541b5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efa93b416dfbea8335c1db0893a6c65fa86dc6424abc0e0adc20158e3d87230c
+oid sha256:850ff809afd9758beeb8d912a2e6237674dbec15df8682b377a7a03e924a6f8a
 size 2080

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0003190269677483675,
+  "epoch": 0.0004785404516225512,
   "eval_steps": 1,
-  "global_step": 2,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,21 @@
       "eval_samples_per_second": 3.563,
       "eval_steps_per_second": 3.563,
       "step": 2
+    },
+    {
+      "epoch": 0.0004785404516225512,
+      "grad_norm": 41.42515182495117,
+      "learning_rate": 6.000000212225132e-05,
+      "loss": 12.9499,
+      "step": 3
+    },
+    {
+      "epoch": 0.0004785404516225512,
+      "eval_loss": 11.709774017333984,
+      "eval_runtime": 2963.9891,
+      "eval_samples_per_second": 3.562,
+      "eval_steps_per_second": 3.562,
+      "step": 3
     }
   ],
   "logging_steps": 1,
@@ -51,12 +66,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1803325141942272.0,
+  "total_flos": 2774346372218880.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null