Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c85407f600156ac5243f7ac7bdb2f99fd52e0d2b9dd155377e6984b280b8cdb
+oid sha256:a28a7dbac8b0f0d79134828ccfcc7e75778b4778c9b07150cd8125a691efe3ae
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b37174927714cec2e61c454712290368ccd8a8714b0ebd27ab7511b87c550a1
+oid sha256:01c2b09fc35aa9333839387ec3971d2e5d10cd453971cb6fa8508a6f3a2dd19d
 size 1342555602

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a07938138ec004ff3d5081b07253c4357b50bd72ea7c1cfabba2e25e891013e5
+oid sha256:db154dc44f1fc7dfd122d5f2c612cf938a41c48875c24a85ef3d6b41a2850665
 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": 0.4576271186440678,
+  "epoch": 0.5338983050847458,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,28 @@
       "eval_samples_per_second": 18.891,
       "eval_steps_per_second": 2.384,
       "step": 54
+    },
+    {
+      "epoch": 0.4661016949152542,
+      "grad_norm": 0.5448825359344482,
+      "learning_rate": 8.963177415120962e-05,
+      "loss": 0.7919,
+      "step": 55
+    },
+    {
+      "epoch": 0.5084745762711864,
+      "grad_norm": 0.5443424582481384,
+      "learning_rate": 7.5e-05,
+      "loss": 0.7779,
+      "step": 60
+    },
+    {
+      "epoch": 0.5338983050847458,
+      "eval_loss": 0.799988329410553,
+      "eval_runtime": 22.2537,
+      "eval_samples_per_second": 18.873,
+      "eval_steps_per_second": 2.382,
+      "step": 63
     }
   ],
   "logging_steps": 5,
@@ -152,7 +174,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.409963201508147e+16,
+  "total_flos": 9.84305110131671e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null