Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a5622480e30566be339ad28bbd6fdb664e32edb72b044b1614427513a4f987f
+oid sha256:f84df6fff3c6598d64de47d7b2385e2182dcd14a428c9ed5263cb969fbeda422
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:270167bbd2b2d3fdf350847a3bb03312fcd5aa6144f55b39e0e50ca84852a229
+oid sha256:694147a7ed8c6555c06c713a14aa08da200714f820f972ace7bf0831bd0a58c2
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ed3b47a63b9294dd3cccd5a7af478334530cd4326a571908e0e9b923be746e1
+oid sha256:59c87fed3f07be2f5b1754a9acc31ee22fa492fd83d82cd0dc130f910850a60f
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba980d0dd777b13a25b75d07d706d906386a446bee53ae1a0004b9a461c1f2bc
+oid sha256:ce2391d576c8d5f287c1fdfe89c77be035c9f70c37dbb5e4b710cb238f013ffa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1806620133652252,
+  "epoch": 0.24088268448696692,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -14,6 +14,13 @@
       "learning_rate": 9.95984903236168e-05,
       "loss": 12057152.512,
       "step": 1000
+    },
+    {
+      "epoch": 0.24088268448696692,
+      "grad_norm": 1.6864832639694214,
+      "learning_rate": 9.91969806472336e-05,
+      "loss": 446417.568,
+      "step": 2000
     }
   ],
   "logging_steps": 1000,
@@ -33,7 +40,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7502907360411648.0,
+  "total_flos": 1.0003876480548864e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null