Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:664c2fbe785c94205306c98c136271e0df9cf583fc4c013b72b44f5b1ab1ebf9
+oid sha256:4bfe2a504334d48c9875e85716fdd4485555d601c499148f91e255ecff468d5c
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdafd04209038e4d3a176b84fe2315352919e7f5f4480450bbe3ee0b363abf97
+oid sha256:855dac096325c658df97ee8cd0e9c96c5f6dbab5a686ae64a94820d953a935ee
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed490e04c6dbbc7419c7365a93701b5d2a1915c9651cc1654bfd578cd611575f
+oid sha256:41eb3cc90529708ec3050e7a2a3e956faee68b39027a1409168255234e541c3d
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
+oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.421610116958618,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.5100182149362478,
+  "best_metric": 2.401268720626831,
+  "best_model_checkpoint": "./outputs/checkpoint-800",
+  "epoch": 0.5828779599271403,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -105,13 +105,27 @@
       "eval_samples_per_second": 30.433,
       "eval_steps_per_second": 3.808,
       "step": 700
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002,
+      "loss": 2.4059,
+      "step": 800
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 2.401268720626831,
+      "eval_runtime": 206.1413,
+      "eval_samples_per_second": 30.435,
+      "eval_steps_per_second": 3.808,
+      "step": 800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.055883980423168e+16,
+  "total_flos": 2.349160133935104e+16,
   "trial_name": null,
   "trial_params": null
 }