Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9c67c0a5a8a6973079665278f8b4a493769bafbc5cb7a655c29401784ad09a5
+oid sha256:efadc57c43ab1bb09ca5343f621a804e49d6e724fbd0fe8e0c8d7049b7e12267
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfce265431541d4b2d4b1ecd41c03fe1631b51321eb87f8654322608e36947f7
+oid sha256:5f53e2bfd754abb1c40e64e96638d45bec91eaa7a704ca3a3aae04bd5ec86428
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d9abb419b80aead609e3d25aa188a530b509237800785868036d93ad22750d1
+oid sha256:85b8d8a0a56f8ce0b08c306c81d4db681fbeb82d63bb46ab4a99289fc27b309a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e41ec466e37d3e777474b32690d472b15b70497f93b8ea178e488be3afc4f79
+oid sha256:6e344dbb70c54f30c60c22f1398076ef585152c9f0b0476d99664e0abfde6e31
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.679748773574829,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.0200364298724955,
+  "best_metric": 1.6615930795669556,
+  "best_model_checkpoint": "./outputs/checkpoint-1500",
+  "epoch": 1.092896174863388,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,13 +203,27 @@
       "eval_samples_per_second": 43.728,
       "eval_steps_per_second": 5.471,
       "step": 1400
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0002,
+      "loss": 1.6509,
+      "step": 1500
+    },
+    {
+      "epoch": 1.09,
+      "eval_loss": 1.6615930795669556,
+      "eval_runtime": 143.519,
+      "eval_samples_per_second": 43.715,
+      "eval_steps_per_second": 5.47,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.337729485790413e+16,
+  "total_flos": 8.93301054106583e+16,
   "trial_name": null,
   "trial_params": null
 }