Training in progress, step 40000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdba9fc8bab1c4c1c4cda6b1a7669b8bdf3e5bf4fd94cb0ba959df548e18dbb3
+oid sha256:354ba10ebc308001d4962c34661a8b4b0018d23c0c76b41e17787d26889f66e6
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:028e92528a1564f73541be1bbe7bec84eb830ebb58252e907fd62e2fcd01894d
+oid sha256:c58d3111213f9decf5b467b7a9451ca4618a5ac83c7d6653282bdb4621eb614c
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69634962f2d8a04acc70b2b675fe946c82e0396238fbf4a5d6dcdd201b20a59b
+oid sha256:28b66a547b30bb0f6d0472863be4967b31509f44e757837a03afe57cbd2cdac3
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.889546351084813,
+  "epoch": 15.779092702169626,
   "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": 0.002,
       "step": 20000
+    },
+    {
+      "epoch": 9.861932938856016,
+      "grad_norm": 0.050606127828359604,
+      "learning_rate": 5e-05,
+      "loss": 0.0016,
+      "step": 25000
+    },
+    {
+      "epoch": 11.834319526627219,
+      "grad_norm": 0.041334349662065506,
+      "learning_rate": 5e-05,
+      "loss": 0.0012,
+      "step": 30000
+    },
+    {
+      "epoch": 13.806706114398422,
+      "grad_norm": 0.04540463909506798,
+      "learning_rate": 5e-05,
+      "loss": 0.0011,
+      "step": 35000
+    },
+    {
+      "epoch": 15.779092702169626,
+      "grad_norm": 0.03727077320218086,
+      "learning_rate": 5e-05,
+      "loss": 0.001,
+      "step": 40000
     }
   ],
   "logging_steps": 5000,
@@ -54,7 +82,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.727285191748233e+17,
+  "total_flos": 3.454391836863656e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null