Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:850a0780811b7e944d82012ca6c61a0f12d4f19e5e11a3d768ff77378417df3e
+oid sha256:a01fe9598cfd007302c50e735ddd2b483de958d905ac7ca2984cf080a6fd3ff2
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b4b307af65eb907a3afe1e2c916d795d29627b628955b23b72bdfc57d57f658
+oid sha256:a7b6e03e4eeb9b44e5699a0e7f4f286ee120e8ad11a10e2000c25576dde79eb3
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24cf931618f4f7ceb21beb676f434312c3b214f3f1474068e69b596f961b47a9
+oid sha256:aedfcc2691b41c4bda0578944319b14b031a234a54db6cc75febfcc884969cab
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd036b10b8d5375fd193c0c61ce0f3c488671f8caba167559ea82531d6e0d4f6
+oid sha256:8b570cf230c80e94a4e6c783199e9749d42656cc0cf6c468c73301ec6bf16703
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7998750195281987,
+  "epoch": 0.9998437744102484,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,21 @@
       "learning_rate": 9.733333333333335e-05,
       "loss": 1.3804,
       "step": 400
+    },
+    {
+      "epoch": 0.9998437744102484,
+      "grad_norm": 0.09610690176486969,
+      "learning_rate": 9.666666666666667e-05,
+      "loss": 1.3666,
+      "step": 500
+    },
+    {
+      "epoch": 0.9998437744102484,
+      "eval_loss": 1.2211335897445679,
+      "eval_runtime": 781.18,
+      "eval_samples_per_second": 19.87,
+      "eval_steps_per_second": 2.485,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -54,7 +69,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.242998847526666e+17,
+  "total_flos": 7.803748559408333e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null