Training in progress, step 78, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:974949f77f0a14b4199397c8ba5e2711f830212568ab0bfb2ed01e6c7250c7e0
+oid sha256:b9f43328dd2d8116603704d5da077f1cdfcadf0ca60d4f6c67042c456d651e7e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0bc4aa4048af27fec57240e1206a51560d0aa8ae57d2f6ef5d4a90bcda27d0b
+oid sha256:7ddfc9cb48a268339574aadd00a883430d46df5729370a923adb4c5bc610f51c
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c150e7a0df1bbdf6fa35b33f81ebbc56fd08d0eb855b36785312a07efa2d1cde
+oid sha256:589530963918166f3856b646184357baa64b7df7b77ae1064a2164e37ebf14e7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15a153ae523f6f915c8c717e9164535eda8efd532a3b2e2efaf3c667d39d242b
+oid sha256:6e14b0e4bebf6d66c9099b7587b528a3013e8c4759510f4562172108e92d4284
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0734670810963549,
+  "epoch": 0.08816049731562588,
   "eval_steps": 13,
-  "global_step": 65,
+  "global_step": 78,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -202,6 +202,49 @@
       "eval_samples_per_second": 6.628,
       "eval_steps_per_second": 0.832,
       "step": 65
+    },
+    {
+      "epoch": 0.07459734388245268,
+      "grad_norm": 0.9956369996070862,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.5392,
+      "step": 66
+    },
+    {
+      "epoch": 0.07798813224074597,
+      "grad_norm": 1.1790428161621094,
+      "learning_rate": 3.110851015344735e-05,
+      "loss": 0.5354,
+      "step": 69
+    },
+    {
+      "epoch": 0.08137892059903927,
+      "grad_norm": 1.041911005973816,
+      "learning_rate": 2.9463922369965917e-05,
+      "loss": 0.5366,
+      "step": 72
+    },
+    {
+      "epoch": 0.08476970895733257,
+      "grad_norm": 1.101559042930603,
+      "learning_rate": 2.7799111902582696e-05,
+      "loss": 0.5158,
+      "step": 75
+    },
+    {
+      "epoch": 0.08816049731562588,
+      "grad_norm": 0.9680448174476624,
+      "learning_rate": 2.6121620758762877e-05,
+      "loss": 0.4675,
+      "step": 78
+    },
+    {
+      "epoch": 0.08816049731562588,
+      "eval_loss": 0.13185884058475494,
+      "eval_runtime": 224.7208,
+      "eval_samples_per_second": 6.63,
+      "eval_steps_per_second": 0.832,
+      "step": 78
     }
   ],
   "logging_steps": 3,
@@ -221,7 +264,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8281387903680512e+17,
+  "total_flos": 2.1937665484416614e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null