Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:473cc1b7c18be2967d46f87ef1c27dd2455038c0dbbd14e00e3ea51f96a5b490
+oid sha256:e24236def62dcea983f4d2e6ba6fed88fa39b62f4691affd4ed1d8c2d8d8795a
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd220ddd424e463fcdc9d22a69889fc47893f491dcec5f0285a4e718ba580980
+oid sha256:a1129b9bdbc1f927b8794bd561f20c2710281cfd606fac34cd745c281e940db8
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1483fe5ee1de3351fec80a493a35970862157e2df5a1f01c39c538d167a91ab7
+oid sha256:f6f8a3071cc811ae52946b6ee778ddcd861ec51849b9667e2fa077e5381edaa2
 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": 0.02456571328303211,
+  "epoch": 0.02807510089489384,
   "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": 460.341,
       "eval_steps_per_second": 57.543,
       "step": 35
+    },
+    {
+      "epoch": 0.025267590805404458,
+      "grad_norm": 0.12015967071056366,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 10.366,
+      "step": 36
+    },
+    {
+      "epoch": 0.027373223372521495,
+      "grad_norm": 0.1509571224451065,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 10.3625,
+      "step": 39
+    },
+    {
+      "epoch": 0.02807510089489384,
+      "eval_loss": 10.361713409423828,
+      "eval_runtime": 5.2202,
+      "eval_samples_per_second": 459.755,
+      "eval_steps_per_second": 57.469,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3987936116736.0,
+  "total_flos": 4629352415232.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null