Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50d9d0fe97dd00ea24e362c2d4a38a7cfc959182bb488ce1c6e781603e99e7dd
+oid sha256:720277acde4ee9020cddee66ee5a359ca8e2d3d041ae3562e4cb82d210cdb793
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03a650f331294a60c42095545195ee4508b3b3960f3e06880545f1fe18a873e5
+oid sha256:04befc22a65dba13687a4fa49e937511ef258aaca6dd9bf5dcff017dc9db2023
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb96314f638b348daeef3cbf80664074d3f6eb420eca89e7a3cb931e87c179aa
+oid sha256:7e081351a022c45bf031e060833aff1ba860157aceb2df94543881413eca763a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
+oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.417910447761194,
+  "epoch": 0.47761194029850745,
   "eval_steps": 5,
-  "global_step": 35,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,28 @@
       "eval_samples_per_second": 4.171,
       "eval_steps_per_second": 0.532,
       "step": 35
+    },
+    {
+      "epoch": 0.4298507462686567,
+      "grad_norm": 2.74045467376709,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 5.2587,
+      "step": 36
+    },
+    {
+      "epoch": 0.46567164179104475,
+      "grad_norm": 2.70888090133667,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 5.2953,
+      "step": 39
+    },
+    {
+      "epoch": 0.47761194029850745,
+      "eval_loss": 1.3347140550613403,
+      "eval_runtime": 33.828,
+      "eval_samples_per_second": 4.168,
+      "eval_steps_per_second": 0.532,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0016986062913536e+17,
+  "total_flos": 1.1447984071901184e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null