Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ccd62b779e31a9e0f81b74a773eaa0c658e750fa8d9604edabc7f9807b687a0
+oid sha256:c614bcbaffebb9df913d1a95482cb61b5bcdea179c022a8b8688a4b2ea20bc74
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d2b1fb8faf93203bfa23b694242ee971b02d2b858005f0adf558fb264e03357
+oid sha256:ca0c8943c81d0d955127dfa2b731aae5959f41706b319bc62d5f2d0b524604bc
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16429469a49bff10e4c592f3a9a29ce1bd33c24708692eafba2bae5fee5e8095
+oid sha256:8dd42064bd4fb4eec8036fb285c03c704810bfb9590c79f20aac0cfa140f4e28
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
+oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1772679090499878,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.6666666666666666,
+  "best_metric": 1.1649450063705444,
+  "best_model_checkpoint": "./outputs/checkpoint-600",
+  "epoch": 0.8,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,20 @@
       "eval_samples_per_second": 9.981,
       "eval_steps_per_second": 1.251,
       "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 0.9722,
+      "step": 600
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.1649450063705444,
+      "eval_runtime": 190.0877,
+      "eval_samples_per_second": 10.153,
+      "eval_steps_per_second": 1.273,
+      "step": 600
     }
   ],
   "logging_steps": 100,
@@ -84,7 +98,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.735371896897536e+16,
+  "total_flos": 4.481983825772544e+16,
   "trial_name": null,
   "trial_params": null
 }