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:f7f96df7bd3e5349d9b49a62d34bd8d027187e64e2eb7dc3e3ac0c4297d69fa7
+oid sha256:365cb56c31e75ba2d93b92e523ff2b41ef30cbe8b35a4281a0ba0dae02713a48
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1260b98c53015862559a109342940a588476d9d02238617f300208dcf4e19807
-size 100692937
+oid sha256:d88ee7bf1a4f8afad068b633acbb1f55ab26c488991d0a4f91e60a3682dbd7c1
+size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:548719e8fcb17ef09c89c53de77f37623dd6f564e0e5fd5f6e820e579f2f66b5
+oid sha256:176b5f7c8c5709a1b112b6a38d5b74f578a857aeda04052f8a5e247ab8150858
 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": 0.8006419539451599,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 1.0666666666666667,
+  "best_metric": 0.7660272717475891,
+  "best_model_checkpoint": "./outputs/checkpoint-300",
+  "epoch": 1.6,
   "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": 8.407,
       "eval_steps_per_second": 1.054,
       "step": 200
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 0.8356,
+      "step": 300
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 0.7660272717475891,
+      "eval_runtime": 229.5539,
+      "eval_samples_per_second": 8.408,
+      "eval_steps_per_second": 1.054,
+      "step": 300
     }
   ],
   "logging_steps": 100,
@@ -42,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.40647601737728e+17,
+  "total_flos": 2.10987888611328e+17,
   "trial_name": null,
   "trial_params": null
 }