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:c3259410213f71972c5e084cfb4b3533792e0d83aec4fd313939eef10673ed4a
+oid sha256:f76734e28204792f1c9602dbde1f5c026064dd1a28454ce0e382330d42314704
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:012aa51818c4458bc844cdc7cd8dd1e8655a6a70f8c4d71986db5bcd5c1bdc9c
+oid sha256:7f3c21d4cb5319aa1931d819302b04d98e988babb95416bbaade61cf9818a914
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3b054ae045b714f7e85cf547e62356e2e1fe97d70e4f0c74b5d95786c4a60c9
+oid sha256:b538b38de5a7e672b21469b3c4da1961004ba3e774fabb355fed626d305c65f0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8634170e919c9d99c690b0056337094258fdb77569d2feaf905b96c380dc695e
+oid sha256:17c2b58d0bfac7076f5bfb2b6f6c91fe0cdc02aea0282c1fa48c426ea9abd87a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003036437246963563,
+  "epoch": 0.00354251012145749,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -98,6 +98,21 @@
       "eval_samples_per_second": 26.057,
       "eval_steps_per_second": 13.028,
       "step": 54
+    },
+    {
+      "epoch": 0.0033738191632928477,
+      "grad_norm": 4.84288215637207,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 3.0761,
+      "step": 60
+    },
+    {
+      "epoch": 0.00354251012145749,
+      "eval_loss": 0.7605909109115601,
+      "eval_runtime": 289.3206,
+      "eval_samples_per_second": 25.881,
+      "eval_steps_per_second": 12.941,
+      "step": 63
     }
   ],
   "logging_steps": 10,
@@ -117,7 +132,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0195377730879488e+16,
+  "total_flos": 1.1909255883915264e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null