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:a0b2b6a37f68a11b4f33f5a8d24f4d13ad60306376de9562a934051a026e48e4
+oid sha256:1d4008eca5ef3d8f7b6cef2f96365d3416a1d5ac39bec4ec64d55c4509cd1478
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccfc3b592f19525a7f25f6a68dcfd22a73155cc759fb742fcf2bde0a33d0871c
+oid sha256:15e8072284e3ac33c828f927c6a2db1a1627affe98337ea3c0000518d98143b5
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0b94d1122471aca26c892d9b2d4a4e37ccc99bccd12a642f92316f84a6a18ef
+oid sha256:f4f1181e0e3e2c9c9c4867f3c8fa0bba665e663473833a2ab7b385cf778c0261
 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": 1.202022671699524,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.4,
+  "best_metric": 1.1907917261123657,
+  "best_model_checkpoint": "./outputs/checkpoint-400",
+  "epoch": 0.5333333333333333,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,6 +49,20 @@
       "eval_samples_per_second": 10.809,
       "eval_steps_per_second": 1.355,
       "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002,
+      "loss": 0.9918,
+      "step": 400
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.1907917261123657,
+      "eval_runtime": 177.5912,
+      "eval_samples_per_second": 10.868,
+      "eval_steps_per_second": 1.363,
+      "step": 400
     }
   ],
   "logging_steps": 100,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.242334722424832e+16,
+  "total_flos": 2.9915995189248e+16,
   "trial_name": null,
   "trial_params": null
 }