Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4650f9955c1655120e0107081c0047294b2af0923537c7dc2e5a24afe5daab87
+oid sha256:79c7a23d41d76dd3c71ac58f09cc2da9d8f36efb2ffecf12c1318ab51f307df1
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4b9f4a3b80ec66c98f904b0d99efc41390ca0ee26b684ef4ea43aa51c5b3a77
+oid sha256:4a40b5f89a1f23f6a0ae60b3ad69602b5b719032bf028990bd7bf0267ffafd9a
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8ef5338eaf3429c06a4ea99d294ad8d90f65c79341e8186d482d4dcfac70fde
+oid sha256:7b52d2891588f3bc22db833fbe6cf2657d7384a09063c47d00a63155fa7f7707
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f68b4a4ba4603d307a8be653dd70e693a9f3506ea1af5f24d2d241dc54cfcb1
+oid sha256:d85eac2daddfe8e3f78a5d6ef1e9ba13c04651694635a9ed76369a20726389db
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9004689942678479,
+  "epoch": 1.051068264721209,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 119.883,
       "eval_steps_per_second": 60.237,
       "step": 54
+    },
+    {
+      "epoch": 0.9504950495049505,
+      "grad_norm": 0.08994650840759277,
+      "learning_rate": 8.381530480933783e-05,
+      "loss": 11.7425,
+      "step": 57
+    },
+    {
+      "epoch": 1.0010422094841063,
+      "grad_norm": 0.09454693645238876,
+      "learning_rate": 7.5e-05,
+      "loss": 12.021,
+      "step": 60
+    },
+    {
+      "epoch": 1.051068264721209,
+      "grad_norm": 0.09124528616666794,
+      "learning_rate": 6.618469519066217e-05,
+      "loss": 11.7571,
+      "step": 63
+    },
+    {
+      "epoch": 1.051068264721209,
+      "eval_loss": 11.738404273986816,
+      "eval_runtime": 1.6952,
+      "eval_samples_per_second": 119.753,
+      "eval_steps_per_second": 60.171,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 100943617720320.0,
+  "total_flos": 117793161216000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null