Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63032741a7fe23ca45903e22d7c0da503ce18374c09ebc8573f580e40714603a
+oid sha256:f211d42eb761df8581278f39533413f5e4154a5981cc9c870902b7998d375799
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c0a2da5e1e8be9d887b1b3abae0480246ee61517416e19119c12ed2e43920a8
+oid sha256:fbc88c9960fda91318ed89a0a148cf9e7f57d10716cc0927753e03a9ac56e005
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e24ee25a852e4bccfaf30d5bb4faf1e6a8bbd9e10f131bfb0436af716b822b9c
+oid sha256:74dc1ad0e98e0db95a26d7764c58c1ed4015e89e0dabed8505302378845c8b0b
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
+oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.6377696990966797,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.2185792349726776,
+  "best_metric": 2.6048855781555176,
+  "best_model_checkpoint": "./outputs/checkpoint-400",
+  "epoch": 0.29143897996357016,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,13 +49,27 @@
       "eval_samples_per_second": 30.623,
       "eval_steps_per_second": 3.832,
       "step": 300
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002,
+      "loss": 2.6248,
+      "step": 400
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 2.6048855781555176,
+      "eval_runtime": 204.7551,
+      "eval_samples_per_second": 30.641,
+      "eval_steps_per_second": 3.834,
+      "step": 400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8537730427699200.0,
+  "total_flos": 1.139596603342848e+16,
   "trial_name": null,
   "trial_params": null
 }