Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87fb1fa35d941e0f5d4c90d72f2425ba005d23383a6220f73ef191b2b5764e82
+oid sha256:de5a51c5be9fa15b3c5938d0499fabf85a5c7ec8877625564840fe26251d0510
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77876ec9f0681c1c77ed33423306a49717fd8261a9b569cd55502aae923baa81
+oid sha256:159e95f1842cb435bd6e9ec78d73edf6bce950999da2f0ba9283761629adb3d9
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbebb324d09ed3b79588ce704d8e867cae0d7b652313decf15a03bfb1ba6792e
+oid sha256:11aa39861938632d003f66031819c4dee0ab0456aa564ddd824501c0c83d2596
 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": 2.004894971847534,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.7102272727272727,
+  "best_metric": 1.9869917631149292,
+  "best_model_checkpoint": "./outputs/checkpoint-600",
+  "epoch": 0.8522727272727273,
   "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": 27.559,
       "eval_steps_per_second": 3.454,
       "step": 500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0002,
+      "loss": 2.1541,
+      "step": 600
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 1.9869917631149292,
+      "eval_runtime": 53.9116,
+      "eval_samples_per_second": 27.675,
+      "eval_steps_per_second": 3.469,
+      "step": 600
     }
   ],
   "logging_steps": 100,
@@ -84,7 +98,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.52069905096704e+16,
+  "total_flos": 1.824958403960832e+16,
   "trial_name": null,
   "trial_params": null
 }