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:c7bf06c3dd60bace286de37675533cc4c41c87d98a8ac647b844f650fd7e2622
+oid sha256:69b542b2dc380b90f6e8f1f4d499a71b4ecc9cd3a445c4f74dd8b3de39c050b6
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:717ed77b4177d6e44d4e6e75bee25f8c57f6703a2170d3f3c75c5474370a884d
+oid sha256:bdf389984ab72e79c5d3fc90258d5a54e3f5440af4e17e2d22561bf13b58af31
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cfb045d2aace0aa6b48f6b2659a883d08eab7c39a2384b021a9dd36bdce66b0
+oid sha256:07b0c0e9355f330a071fd2644eab0c2d0dc9097bcf6d687b22b8b9f923110172
 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": 1.1315025091171265,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.4,
+  "best_metric": 1.1221688985824585,
+  "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": 10.35,
       "eval_steps_per_second": 1.298,
       "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002,
+      "loss": 0.9798,
+      "step": 400
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.1221688985824585,
+      "eval_runtime": 186.7425,
+      "eval_samples_per_second": 10.335,
+      "eval_steps_per_second": 1.296,
+      "step": 400
     }
   ],
   "logging_steps": 100,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.242711954033869e+16,
+  "total_flos": 5.659963132546253e+16,
   "trial_name": null,
   "trial_params": null
 }