Training in progress, step 4100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fcec9eda6988c6e43ece1d1b39d77fd0ad0e8e3d23dbccbd022775fe4aca3f8
+oid sha256:2606650d70cd1ab731b123e499bd2332844af64c994afbf46c945c9dad1a99b6
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4b05eef6bd7359eeb74067569403e939dbc3ef0b144df6694a2a904323af24f
+oid sha256:bbb2be7476218e29787790776da5591d4560347de472f833edae717866b9ebe6
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f8f8f48e0f8845915511c966c3679cf0755fa470bbf416453e88ad9a89e363e
+oid sha256:c3dc329a0255f098244dba06047a5cfcf6462bf87da74eba7aead60769732677
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:593f43b0c83adb27a2db37a6418c2ef12a213bbc2a02f2dc881de6846a69a931
+oid sha256:f55ebe991e4838deda9ff3044672335e03697b65b3fe0753cca61998e974ee51
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.991615891456604,
-  "best_model_checkpoint": "./outputs/checkpoint-4000",
-  "epoch": 2.9143897996357016,
+  "best_metric": 1.9813369512557983,
+  "best_model_checkpoint": "./outputs/checkpoint-4100",
+  "epoch": 2.987249544626594,
   "eval_steps": 100,
-  "global_step": 4000,
+  "global_step": 4100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -567,13 +567,27 @@
       "eval_samples_per_second": 30.446,
       "eval_steps_per_second": 3.809,
       "step": 4000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0002,
+      "loss": 1.9572,
+      "step": 4100
+    },
+    {
+      "epoch": 2.99,
+      "eval_loss": 1.9813369512557983,
+      "eval_runtime": 206.2632,
+      "eval_samples_per_second": 30.417,
+      "eval_steps_per_second": 3.806,
+      "step": 4100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.1667957018181632e+17,
+  "total_flos": 1.1959366338920448e+17,
   "trial_name": null,
   "trial_params": null
 }