Training in progress, step 2900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dbea9d99327f08b5e2f4c41f3c505dd3407a2016da7ac4bb1f7c468202a0443
+oid sha256:e81834b3b8ce8a84668f373441f0d50637fb84cd037399793dbd007eae58e5f5
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6ca561cedc2b983dbdc1d6be07f1ac8544bb7f315a0e8463d7e2e8309743384
+oid sha256:b9c1215701e6b6e5b69da3135df5870e6f8747aed9e256a4eb58e36b25200add
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:119e0e6feea8782c2d5cfd3117e6d646e92bd2a074259490f6554f07264c2392
+oid sha256:4661af03204b37126651ed054d902327a755c23a1b8ab409aa9200fc8c97a842
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c08a7148c570c3d4c87a735e3acef3af52d256eb019f3a3f3feeab8a656949
+oid sha256:097f95efaf3ced711759e9e49c3b8b3ef906ff28483e958d227db85b3ea360b9
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9102813601493835,
-  "best_model_checkpoint": "./outputs/checkpoint-2800",
-  "epoch": 3.7333333333333334,
+  "best_metric": 0.9069462418556213,
+  "best_model_checkpoint": "./outputs/checkpoint-2900",
+  "epoch": 3.8666666666666667,
   "eval_steps": 100,
-  "global_step": 2800,
+  "global_step": 2900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -399,6 +399,20 @@
       "eval_samples_per_second": 2.482,
       "eval_steps_per_second": 0.311,
       "step": 2800
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 0.0002,
+      "loss": 0.7222,
+      "step": 2900
+    },
+    {
+      "epoch": 3.87,
+      "eval_loss": 0.9069462418556213,
+      "eval_runtime": 778.8375,
+      "eval_samples_per_second": 2.478,
+      "eval_steps_per_second": 0.311,
+      "step": 2900
     }
   ],
   "logging_steps": 100,
@@ -406,7 +420,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 7.253666659583693e+17,
+  "total_flos": 7.511437778626253e+17,
   "trial_name": null,
   "trial_params": null
 }