Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f3dfd99327127c44a54ded5b1d648b2641c6d228f1148211aff63a9fbbaef40
+oid sha256:8060226dd6d3d9274a19b9bf54fe2538d2c6053ae30e67dd8de26664256351f4
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5f1d7d04429dedcb4cf7f05a353b62092e5dfbafb94c568cd2a38b344fbd866
+oid sha256:2137b8d3ea04197fc4cb770204a1eb00c536caa804ef95cec80eb5b71e51e90e
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:779eeafbe0c1c0f7dc4120d0cf57fb8c8208196a6a9531bcb510db9c74fea0b0
+oid sha256:df82e2ad66698703ec6bbc02163c1d18a74d693c733fca642bd2a3f12f630e7c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
+oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.019392131269811673,
+  "epoch": 0.02908819690471751,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 311.789,
       "eval_steps_per_second": 156.171,
       "step": 26
+    },
+    {
+      "epoch": 0.02237553608055193,
+      "grad_norm": 1.6799416542053223,
+      "learning_rate": 0.0001,
+      "loss": 44.1579,
+      "step": 30
+    },
+    {
+      "epoch": 0.02908819690471751,
+      "eval_loss": 10.987164497375488,
+      "eval_runtime": 1.8342,
+      "eval_samples_per_second": 308.04,
+      "eval_steps_per_second": 154.292,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 501529706496.0,
+  "total_flos": 749883359232.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null