Training in progress, step 2500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab92723c53b61690dd4e6adc89be4bad87f23308b597935371f7baa5fd7092e
+oid sha256:be12ef0a38bf4e4dcc92e8ff1767d03c1f4096ee59439b78cb474a6afb9882b0
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b043a5e02a43092868d088ed3b37cff8e6699603c9bcf82b104e8089a4ad566c
+oid sha256:dca05e51c2e961d3af4fa697fb574661f71937782ffa8ff823d201656810b267
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:751be9ef02bac0823c942ed1bd370540e3227b7fe38581b0d6ab7b85fc6f4018
+oid sha256:163686e579ab72f4ce428c90f75efc40575ddda1a75bb1752f18267d320f6828
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7af67e15c7ea7b999b8506cb053f1ebebef8ff413acf74ef75da83a900869e05
+oid sha256:45e667a5923b49e2d14253c05982e681212adba5ec3fa9ad39459ff7ad98fd01
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3069367710251688,
+  "epoch": 0.38367096378146104,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -31,13 +31,19 @@
       "learning_rate": 0.0009386126457949663,
       "loss": 0.6057,
       "step": 2000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0009232658072437078,
+      "loss": 0.6143,
+      "step": 2500
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1057438183194624.0,
+  "total_flos": 1322010257915904.0,
   "trial_name": null,
   "trial_params": null
 }