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:e15a2dcd50865060d9ffb3d7d58fa3fd04a2427bff340114b00965888dabcc6f
+oid sha256:442c854e7ae41ddfdbaac65873b562a34014858ee67aa84276b09961fcd6ffba
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abbb2bda55e7aab355b59c1e1b8ed339c8cc050328c7e4d97e77a4aa4182e059
+oid sha256:c709dcf7322fec840e15c11d494eade2a6ff1819823ba55b658778550d64e377
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5624827400e5ff3446346fe4dc702eac7ea71bf5e585cc6625d60e5201ce73a4
+oid sha256:99ca090cbabbbc6276e5a63bdc75efd3f7872d6abdf17c774328b833b6f41dee
 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": 1.256902813911438,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.9333333333333333,
+  "best_metric": 1.2442457675933838,
+  "best_model_checkpoint": "./outputs/checkpoint-800",
+  "epoch": 1.0666666666666667,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -105,6 +105,20 @@
       "eval_samples_per_second": 4.196,
       "eval_steps_per_second": 0.526,
       "step": 700
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002,
+      "loss": 1.0301,
+      "step": 800
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.2442457675933838,
+      "eval_runtime": 457.8978,
+      "eval_samples_per_second": 4.215,
+      "eval_steps_per_second": 0.529,
+      "step": 800
     }
   ],
   "logging_steps": 100,
@@ -112,7 +126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.33018219126784e+16,
+  "total_flos": 2.661849572995891e+16,
   "trial_name": null,
   "trial_params": null
 }