Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98f7cc0df27b42faacb17ee8a065ec28367e4261d78510cfea42b1578da766f5
+oid sha256:e762ba4f21d8ac501b65f4e5f30841019f510e0dd47273fe6a9332dc755d18ae
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39e4a1150c1cfa610f53dc74ef94e82a5a96af126a0a1734d52f5861c1f2ec35
+oid sha256:00e47e864cf0bde982771776408c956ef9c7f70b233e450d8cb028509264b7b9
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e23e570a096e506720de336b086077d52febc7c90915813563d6f5969e0c68c2
+oid sha256:9bc9d59fade5c32432d168a1733323120abe43da9328cb3b9ed170adf092d2bd
 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": 0.6292134831460674,
+  "epoch": 0.7191011235955056,
   "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": 96.054,
       "eval_steps_per_second": 24.524,
       "step": 35
+    },
+    {
+      "epoch": 0.647191011235955,
+      "grad_norm": 0.4191032648086548,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 11.9021,
+      "step": 36
+    },
+    {
+      "epoch": 0.701123595505618,
+      "grad_norm": 0.4025208055973053,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 11.8995,
+      "step": 39
+    },
+    {
+      "epoch": 0.7191011235955056,
+      "eval_loss": 11.898837089538574,
+      "eval_runtime": 0.976,
+      "eval_samples_per_second": 96.312,
+      "eval_steps_per_second": 24.59,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 330829332480.0,
+  "total_flos": 377832407040.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null