Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95fbef14f453f2f82867778c78588c9a4cb88a3ca4dbfcc10db83046b22a9b9d
+oid sha256:1dd4e52e0a694b622356c32f19c184fc23d8fb9c1ffdc34dea61c4177d6dc872
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7a80314d79e9f6624fa16e89522b6905263b4f113d17b2f926eb2b61ea8618a
+oid sha256:d7e4986a1abc988b386d23c1e81654596808f5f65c7d6014073a5a7531058d17
 size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9c39ce6b0873a5ec9d657fe833fd9cbd0b01bb8cfae95545a4d03900874ab13
+oid sha256:e9ecd1455bb3fc32a98fe70b8fb37696d4823754f4032a53a3810faccac9b739
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b38320f40535085de37905499e1385aa34aad6a41a68078b15be5cc295f0a80
+oid sha256:d0c8f35d62ab0308ea4f3d434e6ddceeb2288fdcf54813dbe06805202a497865
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09556966345825654,
+  "epoch": 0.10922247252372176,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -169,6 +169,28 @@
       "eval_samples_per_second": 35.124,
       "eval_steps_per_second": 8.781,
       "step": 700
+    },
+    {
+      "epoch": 0.10239606799098915,
+      "grad_norm": 93.90786743164062,
+      "learning_rate": 0.00025,
+      "loss": 8.9364,
+      "step": 750
+    },
+    {
+      "epoch": 0.10922247252372176,
+      "grad_norm": 77.11343383789062,
+      "learning_rate": 0.00025,
+      "loss": 9.0858,
+      "step": 800
+    },
+    {
+      "epoch": 0.10922247252372176,
+      "eval_loss": 2.4181454181671143,
+      "eval_runtime": 175.1085,
+      "eval_samples_per_second": 35.224,
+      "eval_steps_per_second": 8.806,
+      "step": 800
     }
   ],
   "logging_steps": 50,
@@ -188,7 +210,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.475384335499264e+17,
+  "total_flos": 2.829010669142016e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null