Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f14b8f7b9087016403701eec6a7862b2894ae7a0353d88bb7236d699972d717
+oid sha256:e1dff4353db7bc3ba1aa3780108c7a6a7f67a13388688505fc850bf024e62813
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d676101575c5d7e889c442d5c94a5fa466ccc42648cf9c9ab6990cb06ec0b6e2
+oid sha256:60effbf7a199d0315ab3f676c2bd690f2d0f53fe379655540649a79e951e1fdb
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2b52d82f73e570b1698336d070d85ea4c32ca359687f3058f1f92bb220326cb
+oid sha256:67614312c1d6bdffeb060b44c3dda6a1d76fa4797cd7f644d2f81b287adb0cdc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9120c40acc17c5b623355fbfb43e37d51967de752e9eedd3525b8954bac5054
+oid sha256:5506f0a4e691947c301507541e57d2a952036580bd1fff1d0b54c9702747e9ae
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.41562759767248547,
+  "epoch": 0.6234413965087282,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,13 @@
       "learning_rate": 1.72346910501524e-05,
       "loss": 0.4047,
       "step": 1000
+    },
+    {
+      "epoch": 0.6234413965087282,
+      "grad_norm": 0.43808215856552124,
+      "learning_rate": 1.5849265724577447e-05,
+      "loss": 0.3844,
+      "step": 1500
     }
   ],
   "logging_steps": 500,
@@ -40,7 +47,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2435831562240000.0,
+  "total_flos": 3653747343360000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null