Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06f67bb2d37064c0ca1dadc058430a1da30e19464a55198831f97bac39f9e657
+oid sha256:8a1d84ea17937cd9f06c3759118d86dadb9729b48209f514e1917c5b35389542
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91eb086e4f2a517351c821c05f087f8d9321c14cd3b6b2d8f473598e6dc78a70
+oid sha256:3eb068e2af2a6540fbfac7600c671d5fe22e12e261ec5c267a382f7bc7662b2c
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8aefa3075f62c4cd00dd5263713be019055862c4e14255d03ba1618ba3077b5
+oid sha256:8c61993168353c8d250f3af4b44e28b5ee9094b106e3aa05b160282ff8ed2ef0
 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": 0.056074766355140186,
+  "epoch": 0.08411214953271028,
   "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": 4.572,
       "eval_steps_per_second": 2.337,
       "step": 6
+    },
+    {
+      "epoch": 0.06542056074766354,
+      "grad_norm": 2.8733081817626953,
+      "learning_rate": 0.00014,
+      "loss": 0.8193,
+      "step": 7
+    },
+    {
+      "epoch": 0.07476635514018691,
+      "grad_norm": 2.0992445945739746,
+      "learning_rate": 0.00016,
+      "loss": 0.5052,
+      "step": 8
+    },
+    {
+      "epoch": 0.08411214953271028,
+      "grad_norm": 1.654015064239502,
+      "learning_rate": 0.00018,
+      "loss": 0.2479,
+      "step": 9
+    },
+    {
+      "epoch": 0.08411214953271028,
+      "eval_loss": 0.18080545961856842,
+      "eval_runtime": 9.8815,
+      "eval_samples_per_second": 4.554,
+      "eval_steps_per_second": 2.328,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7841498422837248.0,
+  "total_flos": 1.1762247634255872e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null