Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1f4c9b3c8b855f7066cead11c427078c6889100333c837f6ee19c763f78206d
+oid sha256:64b2e9a8cd38c5d36cb5bfc550da0cfecc84915a63ea7d8e3df324b6727169d3
 size 15156512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3756d60363bc065e16a02456ea32d2bae76fa2a01011e733082f274beb018666
+oid sha256:7df5de490fe94c336968e5e61fa603f19aa594ce85fc4f61af0840a4251f16de
 size 7825914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4a4a168c2c87c2a3e04c6c7431e5aad706de606250e155ecc2a2948e00359de
+oid sha256:5ec828114a9f823c079e9a002c62811de494f0b068f4847b658d0732d7ab7f53
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06334841628959276,
+  "epoch": 0.07239819004524888,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 152.009,
       "eval_steps_per_second": 19.058,
       "step": 63
+    },
+    {
+      "epoch": 0.06636500754147813,
+      "grad_norm": 3.022951364517212,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 4.6649,
+      "step": 66
+    },
+    {
+      "epoch": 0.0693815987933635,
+      "grad_norm": 2.6910369396209717,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 4.456,
+      "step": 69
+    },
+    {
+      "epoch": 0.07239819004524888,
+      "grad_norm": 2.79231858253479,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 4.3638,
+      "step": 72
+    },
+    {
+      "epoch": 0.07239819004524888,
+      "eval_loss": 4.356507301330566,
+      "eval_runtime": 11.0721,
+      "eval_samples_per_second": 151.282,
+      "eval_steps_per_second": 18.967,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5399886321156096.0,
+  "total_flos": 6171298652749824.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null