Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fb4c50fce6fb3ef0e1ee2c02f352b528a6e87352552e2d9bdad3439caefb6b8
+oid sha256:999f91917a35556723c8741ce673150bd690871e90bc931c3ed28efa16b3e29b
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e1f301da5a493c8102dfa3afdb6231ed4e7102065535f7b164d016dd6c2f988
+oid sha256:e7ed733050717b1f3bc86bb5be21ca753b7a985d1733f8c43f74f4b161321234
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81e080bbaaf7f398e3c31827b98141f7e6ea8bca33ad66752d1d4dadd3b7436a
+oid sha256:e60237dfefe2ec38327a3f797bcf1870bd78d91e3de3554cb260d6b17f89100c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003827751196172249,
+  "epoch": 0.004253056884635832,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,13 @@
       "eval_samples_per_second": 28.889,
       "eval_steps_per_second": 14.444,
       "step": 9
+    },
+    {
+      "epoch": 0.004253056884635832,
+      "grad_norm": 21.274797439575195,
+      "learning_rate": 0.0002,
+      "loss": 6.2291,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -108,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 149138561826816.0,
+  "total_flos": 162297846693888.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null