Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a781eb016f93954b38a29f25d06e7e282baa7cc5d44030f9bdef07a4f8c46b2f
+oid sha256:1eb61e0638b5dcf14662ad5375e1bf989e1459f766b82d6962385c54ff45b38a
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d69ebb13f864fe73e357f3dd476638fe9db8e18dbfd3ddf4578cb515a9184394
+oid sha256:b7c825500ba425bc580f3654c6c8aeee72a10f9b6c640aba743414c69c63aaa7
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d72637e6cf5ac03358ca59d9f0e56e73e8fcc3ca2a82aeac8e0c5dca17bd18
+oid sha256:d851545478967cc7c2e593b62f547a51df81d646f155d97e969bce2c2b83f681
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0408423739629866,
+  "epoch": 0.05105296745373325,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,13 @@
       "eval_samples_per_second": 63.487,
       "eval_steps_per_second": 31.936,
       "step": 4
+    },
+    {
+      "epoch": 0.05105296745373325,
+      "grad_norm": 31.183809280395508,
+      "learning_rate": 5e-05,
+      "loss": 40.4888,
+      "step": 5
     }
   ],
   "logging_steps": 1,
@@ -73,12 +80,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1468725404368896.0,
+  "total_flos": 1835906755461120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null