Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b76fd8513d2eb4b9e992e35f901b9d8c49095078308cfa8e1607a1f84942d3cd
+oid sha256:5bdc5d17300ac116dce8754738106bb968cf28014ce048dd417ded47e38f8cc1
 size 47235968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12a4f42b78f38297969036d6c9976573ebd2cbcc3fb824a725b8881bc97c5b4e
+oid sha256:65d170581f0c73adcdad375b28faf3843723b0be8f7a3fe528d57d1c638e4ded
 size 24410836

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6011dbc1beaf916a24aa0692a7ad3787fe62f4d3127d9859b27643438838594d
+oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.018258587241812164,
+  "epoch": 0.027387880862718247,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 68.017,
       "eval_steps_per_second": 34.045,
       "step": 10
+    },
+    {
+      "epoch": 0.020084445965993382,
+      "grad_norm": 1.2413709163665771,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.9181,
+      "step": 11
+    },
+    {
+      "epoch": 0.021910304690174597,
+      "grad_norm": 1.4612451791763306,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.0087,
+      "step": 12
+    },
+    {
+      "epoch": 0.023736163414355815,
+      "grad_norm": 1.5164417028427124,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.7626,
+      "step": 13
+    },
+    {
+      "epoch": 0.02556202213853703,
+      "grad_norm": 2.2981152534484863,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.9643,
+      "step": 14
+    },
+    {
+      "epoch": 0.027387880862718247,
+      "grad_norm": 1.6825339794158936,
+      "learning_rate": 5e-05,
+      "loss": 1.8795,
+      "step": 15
+    },
+    {
+      "epoch": 0.027387880862718247,
+      "eval_loss": 1.9565916061401367,
+      "eval_runtime": 13.5223,
+      "eval_samples_per_second": 68.258,
+      "eval_steps_per_second": 34.166,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2925853220536320.0,
+  "total_flos": 4331570410291200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null