Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c614bcbaffebb9df913d1a95482cb61b5bcdea179c022a8b8688a4b2ea20bc74
+oid sha256:4658ca5e48d564d0874412a684d976d74cb3153cea5db2321581c7bbf2accb97
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca0c8943c81d0d955127dfa2b731aae5959f41706b319bc62d5f2d0b524604bc
+oid sha256:4124a83b0fcd5cf2c453f9866287f4746d4d73478f2facde97eaa8c3056cad8b
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd42064bd4fb4eec8036fb285c03c704810bfb9590c79f20aac0cfa140f4e28
+oid sha256:2a7aea1bef86b1056125513432a9481c64077b07ee990116c26b3bfaebd6be37
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
+oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1649450063705444,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.8,
+  "best_metric": 1.161731481552124,
+  "best_model_checkpoint": "./outputs/checkpoint-700",
+  "epoch": 0.9333333333333333,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,6 +91,20 @@
       "eval_samples_per_second": 10.153,
       "eval_steps_per_second": 1.273,
       "step": 600
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 0.9654,
+      "step": 700
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 1.161731481552124,
+      "eval_runtime": 177.4185,
+      "eval_samples_per_second": 10.878,
+      "eval_steps_per_second": 1.364,
+      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -98,7 +112,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.481983825772544e+16,
+  "total_flos": 5.2320035432448e+16,
   "trial_name": null,
   "trial_params": null
 }