Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e9517a59c37b235c662d3e8dc603c34ff4305844f32bbe8409888f13cd43d1
+oid sha256:478d0d5beda024617161afe23e197bd45cd4bfdfd0fdc70f5cd5fef5d7d70f6a
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeca3804d5ad05514170db769621bc6f6a13a53c71723cf4d655d8f12ee1cabe
+oid sha256:3072fd0de72d1b5e810cb09126a37a642cd93827db927bf74f39bdf447c10b90
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45ad477311de1f6b2e96cccdadfdec5df765b9531fbd21a05f460c15a1263a8a
+oid sha256:c9db3df1f7e3c6108cf2455f42014ea709c97a495fd74faf2761323ee28fc169
 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": 1.0421228408813477,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.4,
+  "best_metric": 1.033984661102295,
+  "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": 5.462,
       "eval_steps_per_second": 0.685,
       "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002,
+      "loss": 0.8945,
+      "step": 400
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.033984661102295,
+      "eval_runtime": 353.6405,
+      "eval_samples_per_second": 5.458,
+      "eval_steps_per_second": 0.684,
+      "step": 400
     }
   ],
   "logging_steps": 100,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.485409566683955e+16,
+  "total_flos": 1.1319907133059891e+17,
   "trial_name": null,
   "trial_params": null
 }