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:e8996a8c9ae397e747b91aa4fbe0e5e5cbd8b4d01c11fd2f92b48513013c93c4
+oid sha256:4ebd51e27b75f61b4784841bdc3e84cec0110751aea14d0bd97a2fb53819cf49
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f2da546a0529aea45eb5a6daf25a9fedd4bb3076b756ebe67614c218c02b9c2
+oid sha256:d65eaa0340c25c90d740ae8182d3ebccb58c13db3e01a2a2bc42ff4f73036a44
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbe94f3c099526d2d0ffee989f862b44e24dbf9220e583fff14c71db11059188
+oid sha256:92942cd27ddd53a4c545428e2cc49f7db59067ae104a2b7a947f9d90e3f8e9f3
 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": 1.5129507780075073,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.4,
+  "best_metric": 1.4979034662246704,
+  "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": 15.549,
       "eval_steps_per_second": 1.95,
       "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002,
+      "loss": 1.2673,
+      "step": 400
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.4979034662246704,
+      "eval_runtime": 93.4276,
+      "eval_samples_per_second": 15.531,
+      "eval_steps_per_second": 1.948,
+      "step": 400
     }
   ],
   "logging_steps": 100,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.753797686280192e+16,
+  "total_flos": 2.340946069733376e+16,
   "trial_name": null,
   "trial_params": null
 }