Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a84d54e7dac167ad6ed1c8e8ac75ef013f30fd116a499ae540611054d7acdd65
+oid sha256:fc4ec51b1e0bb577f2fc1e297f82b1d8e8ae8b0c21efc5e3317dd770c19f71ff
 size 47235968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43e99482450f25ca9f43ce52b781267ad9fdb79c450cda8adb6f4f3e56338879
+oid sha256:5b18970e36ba3b2e6b0cbb5c3fb327a2529be7273de023659852c6b173a6a370
 size 24410836

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed21dc73e071bcc758c0a979a7a8476b0e0d055723292046cb5a5b8162c8f2ac
+oid sha256:d70fa16559b3ce702ed6ee9aaad638266e876fa44a0dbae225f0560c038a2f1d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0498960498960499,
+  "epoch": 0.07484407484407485,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 36.132,
       "eval_steps_per_second": 18.42,
       "step": 6
+    },
+    {
+      "epoch": 0.058212058212058215,
+      "grad_norm": 3.0713138580322266,
+      "learning_rate": 0.00014,
+      "loss": 0.7636,
+      "step": 7
+    },
+    {
+      "epoch": 0.06652806652806653,
+      "grad_norm": 3.598985195159912,
+      "learning_rate": 0.00016,
+      "loss": 0.9892,
+      "step": 8
+    },
+    {
+      "epoch": 0.07484407484407485,
+      "grad_norm": 5.25281286239624,
+      "learning_rate": 0.00018,
+      "loss": 0.7988,
+      "step": 9
+    },
+    {
+      "epoch": 0.07484407484407485,
+      "eval_loss": 0.7632012367248535,
+      "eval_runtime": 1.4245,
+      "eval_samples_per_second": 35.801,
+      "eval_steps_per_second": 18.252,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 474020912824320.0,
+  "total_flos": 702858594877440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null