Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1dff4353db7bc3ba1aa3780108c7a6a7f67a13388688505fc850bf024e62813
+oid sha256:3e5df61f042594bdcf440df5c2750da3a3adebab8a36e1d3b1903402c4fc3091
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60effbf7a199d0315ab3f676c2bd690f2d0f53fe379655540649a79e951e1fdb
+oid sha256:7ff826d4f45c57b5599542715ce59b0e1300878f883547db063dfb3f453c1877
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67614312c1d6bdffeb060b44c3dda6a1d76fa4797cd7f644d2f81b287adb0cdc
+oid sha256:7889ea0c99419f757623bd536c886c76ec1b2bc48f8905f0fbdab85178a3efa4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5506f0a4e691947c301507541e57d2a952036580bd1fff1d0b54c9702747e9ae
+oid sha256:a0c3706980993013e323b4cb71cb92383ee3053aec5ea4cdc2e4fe52fced544d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6234413965087282,
+  "epoch": 0.8312551953449709,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -28,6 +28,13 @@
       "learning_rate": 1.5849265724577447e-05,
       "loss": 0.3844,
       "step": 1500
+    },
+    {
+      "epoch": 0.8312551953449709,
+      "grad_norm": 0.4758487045764923,
+      "learning_rate": 1.4463840399002496e-05,
+      "loss": 0.3804,
+      "step": 2000
     }
   ],
   "logging_steps": 500,
@@ -47,7 +54,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3653747343360000.0,
+  "total_flos": 4871663124480000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null