Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:710e9fa8fd54f2c7fa5b3953a7a36335bcad1b94d1553b0c5e8cf5630febf85a
+oid sha256:633ca9e2eef59d3bfec0fa314224157fc1d9be871c2307fc9065380150ade008
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b2164a0bb29a36d7a715bdb338e2da0d52e4f170eb2f0dabeb399a898b471d6
+oid sha256:7d6e6159cfe11c299979137155d520d9b6789375ed0e5ddf4bdfa678d7991cb4
 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": 1.1637059450149536,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.8,
+  "best_metric": 1.1604684591293335,
+  "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": 10.879,
       "eval_steps_per_second": 1.364,
       "step": 600
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 0.9653,
+      "step": 700
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 1.1604684591293335,
+      "eval_runtime": 177.5251,
+      "eval_samples_per_second": 10.872,
+      "eval_steps_per_second": 1.363,
+      "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
 }