Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:244075e61cfba6fce1d39bcf9cb324d2c15855a85c8c9f070b1b02b583d79191
+oid sha256:768f0b8494dbbcf1be7bddd66e8a45aba3a89ab318446e1c533ebcad4abea7de
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14820837fa543088ed4263945cb71d78b076dc75cfbe8bb7b9d8cbc14d270e49
-size 39357765
+oid sha256:cd61636d4608e89896d8e81c483bbcceedf8964299c41d158ab15b3114ba3efa
+size 39357829

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74da0cfd2909a0206b76154a6dfea7012609d0bc75531627f94fba04ca74d753
+oid sha256:915191ad61436a667d8d45034f27c7110941984405576e8ef009354f6c5821a4
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
+oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0682977437973022,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.26666666666666666,
+  "best_metric": 1.0527396202087402,
+  "best_model_checkpoint": "./outputs/checkpoint-300",
+  "epoch": 0.4,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,20 @@
       "eval_samples_per_second": 2.167,
       "eval_steps_per_second": 0.272,
       "step": 200
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002,
+      "loss": 0.8814,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.0527396202087402,
+      "eval_runtime": 888.2495,
+      "eval_samples_per_second": 2.173,
+      "eval_steps_per_second": 0.272,
+      "step": 300
     }
   ],
   "logging_steps": 100,
@@ -42,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.173848389492736e+16,
+  "total_flos": 7.772891970699264e+16,
   "trial_name": null,
   "trial_params": null
 }