Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a92b715fe8596794c3cc9c282406baeeedb154cb6fde102a455a0463d4c773b
+oid sha256:84ce5f5e3ad779f586e26075dbfc17debe31caf534f8485635c22741e6b17c58
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af64cfff14825e0676e4add08f661b8ec13b6e0224a2d8a49379393e538563a5
+oid sha256:56f9727dc07c5bc389be4899ef0032159124294011cc13d105222913c92d85d0
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ef6f9afaee6b3c66bd6603d6f0a1ae70b2f238fe9e271cbda545439817d0f6c
+oid sha256:7240fd7a7fef23174636d23a112dffe186d187eae2f35ae7e0e17c53ea3679db
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0b2d0c48b553cb761ed72f66ac5dc41e40acbef7cd18d2608a3a45cba61a88
+oid sha256:93943bccc582002e393297195c9250188e6670053bc276c333b5b6ec7a12b16e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20781379883624274,
+  "epoch": 0.3117206982543641,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,13 @@
       "learning_rate": 1.86173455250762e-05,
       "loss": 0.5316,
       "step": 1000
+    },
+    {
+      "epoch": 0.3117206982543641,
+      "grad_norm": 1.404678225517273,
+      "learning_rate": 1.7924632862288724e-05,
+      "loss": 0.4832,
+      "step": 1500
     }
   ],
   "logging_steps": 500,
@@ -40,7 +47,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1217915781120000.0,
+  "total_flos": 1826873671680000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null