Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4269d3b9b509e5eed5409c2e16fd7d195914f88586d1ad09ccc74ded67b204a5
+oid sha256:4f43f1a6738f983616ef9181d252b9c12dd97bc40630e3faed7808619f6f0274
 size 50349441

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0f6b2f0ccfa41cd106da53f5e14bf7d59953ae5d9323f2a9877b8417e5f496b
+oid sha256:eba013c6a23ae64f89bf510557c06c2a3eb39e5a9106660abb711cded9be9dda
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99f1c1111b8d1f0cb2cc4b559a49a0a42b0bb5df350eda9361510f1ff2ab08e2
+oid sha256:367394aed610ff7068eaf27da3eb89a6cd4769f26c2abeadffb65a7a6d3952cd
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
+oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6567240953445435,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 0.6557377049180327,
+  "best_metric": 1.6352009773254395,
+  "best_model_checkpoint": "./outputs/checkpoint-1000",
+  "epoch": 0.7285974499089253,
   "eval_steps": 100,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,13 +133,27 @@
       "eval_samples_per_second": 43.55,
       "eval_steps_per_second": 5.449,
       "step": 900
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002,
+      "loss": 1.6469,
+      "step": 1000
+    },
+    {
+      "epoch": 0.73,
+      "eval_loss": 1.6352009773254395,
+      "eval_runtime": 144.0664,
+      "eval_samples_per_second": 43.549,
+      "eval_steps_per_second": 5.449,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.365902922462003e+16,
+  "total_flos": 5.962359246697267e+16,
   "trial_name": null,
   "trial_params": null
 }