Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3661f4837b47d015cf3ebb943a72dfbb53383711df721357488b95a239611757
+oid sha256:3ea0bde5f564cc3e834a8c9296764b4c8a2791d557febdc8445624b6ec116e65
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5dc5fdfd09b87ccb55bc05ef356f936103f26200c74f86a9c1d60587a20e67
+oid sha256:ebc3e59cafe0c8f0d91c00515d5a6090cee1af1c1bece15a3cab3a57b1818a71
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:534e7c453aeda04ef26a9783b095419e7223ca9b7e276c9ec61094ca16162658
+oid sha256:4d1e6991dad8bc748d0e31f4e5e35bbe2e9420c339e4c98abd7035294eef3c2b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
+oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.23003194888178913,
+  "epoch": 0.268370607028754,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 36.225,
       "eval_steps_per_second": 4.585,
       "step": 54
+    },
+    {
+      "epoch": 0.24281150159744408,
+      "grad_norm": 0.7546740174293518,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.6759,
+      "step": 57
+    },
+    {
+      "epoch": 0.25559105431309903,
+      "grad_norm": 0.7903650403022766,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.6119,
+      "step": 60
+    },
+    {
+      "epoch": 0.268370607028754,
+      "grad_norm": 0.5551833510398865,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.5778,
+      "step": 63
+    },
+    {
+      "epoch": 0.268370607028754,
+      "eval_loss": 0.5682376027107239,
+      "eval_runtime": 10.9169,
+      "eval_samples_per_second": 36.182,
+      "eval_steps_per_second": 4.58,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4107703437688832e+16,
+  "total_flos": 1.6458987343970304e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null