Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99be2d9480730205d445f0d44cef7eff87f59710f611220e66c14d3e15afec63
+oid sha256:69cdb48e0a4ecafd9feb0b91c31888b5615560dc7661640a8f664458feb28c88
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec51f82f55b1648d2a60aeff863391bdc858f29282bb2d549709992fd88b40b7
+oid sha256:fbfc8343814c91c194d54f5f7d921a7df81ff0fa18a719650d61daf0ecd94c61
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e01b308d35065e47f7da0742804743053e8a4561ea8fce8c9953e13f2c159d2
+oid sha256:767bc8a6f0ce209c5888baa62e92fcbb0825f5a364f7b7c5405d1d6cadb028c8
 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": 0.066006600660066,
+  "epoch": 0.07543611504007544,
   "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": 12.99,
       "eval_steps_per_second": 1.629,
       "step": 35
+    },
+    {
+      "epoch": 0.06789250353606789,
+      "grad_norm": 0.2198489010334015,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 1.3563,
+      "step": 36
+    },
+    {
+      "epoch": 0.07355021216407355,
+      "grad_norm": 0.23230212926864624,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 1.2303,
+      "step": 39
+    },
+    {
+      "epoch": 0.07543611504007544,
+      "eval_loss": 1.2861415147781372,
+      "eval_runtime": 68.8353,
+      "eval_samples_per_second": 12.973,
+      "eval_steps_per_second": 1.627,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.118799267233792e+16,
+  "total_flos": 5.86529082703872e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null