Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e21664bb6c1d1ae2c109122f4b3938bed613da6ad3c1ac0fc53a51bb2edd6857
+oid sha256:50d9d0fe97dd00ea24e362c2d4a38a7cfc959182bb488ce1c6e781603e99e7dd
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dea6e9aaa3c56756ed19a39c205a6002e9f082dc3c344c6d133fc719df87039f
+oid sha256:03a650f331294a60c42095545195ee4508b3b3960f3e06880545f1fe18a873e5
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5926316ccbdc15291fd4d44c743eae350fd67684d89bb86c8ec5f6337921754f
+oid sha256:cb96314f638b348daeef3cbf80664074d3f6eb420eca89e7a3cb931e87c179aa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
+oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3582089552238806,
+  "epoch": 0.417910447761194,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,21 @@
       "eval_samples_per_second": 4.169,
       "eval_steps_per_second": 0.532,
       "step": 30
+    },
+    {
+      "epoch": 0.3940298507462687,
+      "grad_norm": 2.7453272342681885,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 5.4128,
+      "step": 33
+    },
+    {
+      "epoch": 0.417910447761194,
+      "eval_loss": 1.3384729623794556,
+      "eval_runtime": 33.805,
+      "eval_samples_per_second": 4.171,
+      "eval_steps_per_second": 0.532,
+      "step": 35
     }
   ],
   "logging_steps": 3,
@@ -152,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.585988053925888e+16,
+  "total_flos": 1.0016986062913536e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null