Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b791fbecb6b88664aa79f119dff8f288aa75b9b87dd0dd34e19411dbce854289
+oid sha256:05a674fab1302b21ca09374d55300acb133b868799b5a89059807bbe5940e72f
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ad68c170613ee4fb6dd9cc941512acc1d3c2e781098dbe881bd4cfe8efeecfc
+oid sha256:4e5eb28d2aab11186249c608b8dea707f2ff8896e074965b515c45602208d729
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89d109ac320325ce5994a75dba2574533dce01656e0a672c348391e584969cd4
+oid sha256:7d98c1d6ddc8d6251f378064e080be6b3b902cbfa14b91558d4aa1686eb53ac1
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e63d039dcd74cce40e5b0ae616878e231197e581fdff19eeed08507ad6e3f131
+oid sha256:a7c3cf1238c41ea98e467a79fddf8f1f64b327ca5320d4658e9575b16bffd97b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,13 +1,21 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06022067112174173,
+  "epoch": 0.12044134224348346,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
-  "log_history": [],
+  "log_history": [
+    {
+      "epoch": 0.12044134224348346,
+      "grad_norm": 1.711878776550293,
+      "learning_rate": 9.95984903236168e-05,
+      "loss": 12057152.512,
+      "step": 1000
+    }
+  ],
   "logging_steps": 1000,
   "max_steps": 249060,
   "num_input_tokens_seen": 0,
@@ -25,7 +33,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2500969120137216.0,
+  "total_flos": 5001938240274432.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null