Training in progress, step 17000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41e8da3285afb054fc58b07fbf4b823f1115245f3c85bd47c8bc13ecaf835e72
+oid sha256:d76e26f8180a8ca365fccdc986f5f5dd6b31dbd98ec1ecd24532659fdb7c74eb
 size 497774208

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8d4f41dd127b82a0f8b3cfed37273fb76385fd40156a7f3b4e4b37cc4930215
+oid sha256:5083b6dfdf47ae52bbfe086541035254d21a4c3ab8c66d9adffffc3c214c4c3f
 size 995642298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60153a6a2c9a93ee576034e0ae37f8901abd96844c5a08987b9ed3e55610eb00
+oid sha256:dad554bdcfd5bf1d23db04f3ae398370a12079d1067c60f97decd644e9cabc57
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:885d3a275aa741e5a383624a34b9e59f08654bb3a3fc0e27631d10fe406f39ef
+oid sha256:039bded7dd264852d846202378b4a2ec5377c4f6c21ff59fdb35561d327140e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,13 +1,29 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.985545335085414,
+  "epoch": 1.0154103452395173,
   "eval_steps": 500,
-  "global_step": 16500,
+  "global_step": 17000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
-  "log_history": [],
+  "log_history": [
+    {
+      "epoch": 0.9999402699796918,
+      "grad_norm": 1.324739933013916,
+      "learning_rate": 1.3336518934416438e-05,
+      "loss": 4.0956,
+      "step": 16741
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.856391191482544,
+      "eval_runtime": 281.5542,
+      "eval_samples_per_second": 210.485,
+      "eval_steps_per_second": 6.578,
+      "step": 16742
+    }
+  ],
   "logging_steps": 16741,
   "max_steps": 50226,
   "num_input_tokens_seen": 0,
@@ -25,7 +41,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.4490548224e+16,
+  "total_flos": 3.5534932475904e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null