Training in progress, step 40000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31bdc100ec33c5cc9ceb7d25df38c6bc73ccb1bf21fe4779b8c41687ea533d99
+oid sha256:2af3f4a1f133742ba96dae3c45f770a27ea62c2e568471f10d66b5855eb2dc1d
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83043627f0b085b535e0816fe564fca74eaa0f7b1f30ea74a5e0862f180c25a1
+oid sha256:509f3c88035b7e9fb05ec96eb47bdd5e2808c2d07898812b41f063bc86b89bbf
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b53e134a457f989a320cac37a5c1901d5b22cc7775ac770c8c1f5df456090d0c
+oid sha256:9643649b2a55e6c3d1369ebca0f19dd3fdfc0858f9b4499b8fb83e2169b0729e
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9727756954034326,
+  "epoch": 3.945551390806865,
   "eval_steps": 20000,
-  "global_step": 20000,
+  "global_step": 40000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,34 @@
       "learning_rate": 5e-05,
       "loss": 0.0017,
       "step": 20000
+    },
+    {
+      "epoch": 2.465969619254291,
+      "grad_norm": 0.03086615726351738,
+      "learning_rate": 5e-05,
+      "loss": 0.0012,
+      "step": 25000
+    },
+    {
+      "epoch": 2.959163543105149,
+      "grad_norm": 0.04374952241778374,
+      "learning_rate": 5e-05,
+      "loss": 0.0011,
+      "step": 30000
+    },
+    {
+      "epoch": 3.4523574669560073,
+      "grad_norm": 0.06215918809175491,
+      "learning_rate": 5e-05,
+      "loss": 0.0009,
+      "step": 35000
+    },
+    {
+      "epoch": 3.945551390806865,
+      "grad_norm": 0.03970140591263771,
+      "learning_rate": 5e-05,
+      "loss": 0.0008,
+      "step": 40000
     }
   ],
   "logging_steps": 5000,
@@ -54,7 +82,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7328802956260813e+17,
+  "total_flos": 3.465293207841869e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null