Training in progress, step 6500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b383873c26832688de8d1c4e2cec99e2c080f55c2a733ed72ff54f5da6db032
+oid sha256:a2e5cdc9dff7009cf191fc86f71688a7613da51fb0119218244fd774f0caa4e4
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48a6854066078859b7042e8ef23c5376c7c9fab782496447aa1d2049a5072914
+oid sha256:bf7cc0b437668626634032a08d68507bacc08fbd587751a5700dfc606754c8c1
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:455992e41bd4da0ca76dc0d3b1d29b2d2a3f92f6143e641ebfdcc3ceccc55b08
+oid sha256:bc7fdf8c182446ff929c4d6b8817e2a9c07e01e2bc3377cd65a3690518f7f0db
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79b2a778b609ad3bfe944c34ea5338f4a67422eb690449bc00076aa57ca39206
+oid sha256:222fb7c0eded3ab234f2346c8ed78f8af5f7173be11b6ae063272604dce5250a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9208103130755064,
+  "epoch": 0.9975445058317987,
   "eval_steps": 500,
-  "global_step": 6000,
+  "global_step": 6500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -79,13 +79,19 @@
       "learning_rate": 0.0008158686310620012,
       "loss": 0.617,
       "step": 6000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0008005524861878454,
+      "loss": 0.6089,
+      "step": 6500
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 3179276193497088.0,
+  "total_flos": 3445446993248256.0,
   "trial_name": null,
   "trial_params": null
 }