Training in progress, step 19500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:139b762c258c9eb5cc544fedb22991559230c273e6b61d624ac96e111319c69f
+oid sha256:3fac7573df3665aca930e09154f355ca6d3449141b44143ad426f34f0b18cb3a
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2382b216c6169368827bf00947023a9e337a5851fc9d5518f5344300bd0fe1fe
+oid sha256:35c7636aadeaaa3b4e4b80c9c98a5eed74be83a88386f925b61461fc79f0920f
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1932f6e219883f4a3f24819081a49b0aebfec1abfca44525a259e77652bf11c2
+oid sha256:d132c37ba28fcd192446b241d7468ba1fd4af4d9205fca20131e606422bb64e3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ccfc3f38f2e307720e2cbe200293361cc2776fbe89851498ed91ff727b05ff5
+oid sha256:91d0298361d4a2c2b0b89f5bfa900364a1d9e7ffef104c8c382fe4f783fecdc6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.9158993247391036,
+  "epoch": 2.992633517495396,
   "eval_steps": 500,
-  "global_step": 19000,
+  "global_step": 19500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -255,13 +255,19 @@
       "learning_rate": 0.00041703499079189687,
       "loss": 0.5266,
       "step": 19000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0004016881522406384,
+      "loss": 0.525,
+      "step": 19500
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1.0071282520424448e+16,
+  "total_flos": 1.0336717399130112e+16,
   "trial_name": null,
   "trial_params": null
 }