Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cefae802cfbecd2725077d9393d82fe538f1becaea47fc1680c97e3fc9caeb6
+oid sha256:09b83e4520d2faac0a44fd3666ca6e85059aafeb42755438c0c137479572f7d7
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6b462c18b2bbaf5e3948040483b0c1fd7977c05e7964e4bedfe341e0a854c79
+oid sha256:02c00055b5bd03e4890f1ce79bb80d46ddf81ae1aa9064d1c8fdab8f5ba06aac
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a715695621b29a5bc3a047f2409a8533344cff46a1200fae816a8ba63da770
+oid sha256:2bce8ad87f00a02b0d2a3d827e73ac036f343d9552caa13a5ae85d423ed6d4b0
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed812891698c785c43e6b058c6acf6649c2fbbcf6509f75e58beb0e45a7d710
+oid sha256:60fe2b14e82d752da652953a5bae182d24c7ff34775d2753b9c2e6fa092203d0
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7429991960525513,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 0.8014571948998178,
+  "best_metric": 1.7218060493469238,
+  "best_model_checkpoint": "./outputs/checkpoint-1200",
+  "epoch": 0.8743169398907104,
   "eval_steps": 100,
-  "global_step": 1100,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -161,13 +161,27 @@
       "eval_samples_per_second": 43.722,
       "eval_steps_per_second": 5.47,
       "step": 1100
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002,
+      "loss": 1.7218,
+      "step": 1200
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 1.7218060493469238,
+      "eval_runtime": 143.5245,
+      "eval_samples_per_second": 43.714,
+      "eval_steps_per_second": 5.469,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.550064066907341e+16,
+  "total_flos": 7.145822849964442e+16,
   "trial_name": null,
   "trial_params": null
 }