Training in progress, step 2900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20860ba6347679ef5c8629e2d9997a161c6f8d42530a0ff001171a8d3b1de68a
+oid sha256:302b1e49506cf8a2f6be7df9eb914a5a22181a7f48998aea098da889929fe70b
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f51ee15e5aee3e7c34486e28a2ee5fb0dc82c5912c2ae25bbdf733453984cd6e
+oid sha256:782e2d2a139a42c65b5869d28871ff2018b39607a728c43f4593938ed277e3b4
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9454c9535ad3811e6becd57363e61aef16e6c76875f30d1bdcd4191265ac8ce1
+oid sha256:a16dbd92b02a89cf372eb0be8faed673d0065b4c507cdb24698df320c511fb2f
 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": 2.1790666580200195,
-  "best_model_checkpoint": "./outputs/checkpoint-2800",
-  "epoch": 2.040072859744991,
+  "best_metric": 2.167008638381958,
+  "best_model_checkpoint": "./outputs/checkpoint-2900",
+  "epoch": 2.1129326047358834,
   "eval_steps": 100,
-  "global_step": 2800,
+  "global_step": 2900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -399,13 +399,27 @@
       "eval_samples_per_second": 30.628,
       "eval_steps_per_second": 3.832,
       "step": 2800
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.0002,
+      "loss": 2.1105,
+      "step": 2900
+    },
+    {
+      "epoch": 2.11,
+      "eval_loss": 2.167008638381958,
+      "eval_runtime": 204.8809,
+      "eval_samples_per_second": 30.623,
+      "eval_steps_per_second": 3.831,
+      "step": 2900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.971491799484416e+16,
+  "total_flos": 8.255440339421184e+16,
   "trial_name": null,
   "trial_params": null
 }