Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91b9bbdd755c53c0e737d7e661686c38f23d60d1782fcbf1d45edeeba9d87b95
+oid sha256:2505e88b0a82388da6d8385ddc2b423be64283d12610f87792ca2a058e44892a
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfee0acd7960658f9aa003a100cb4c569de6a3bb0e0e233660c579db5df84976
+oid sha256:e1ec5726b17102540d1cf518de614c69ef3cd64ac316a2b8ee07030241290bfc
 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:d3fb3881e58ff0c357457e26af721d36ad38644f638c6a34d44b118fd264af5e
+oid sha256:f4953537583c171fed6606a5b67ff141ae8b37530eae865be18180585423f010
 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": 1.8618730950401776e-05,
       "loss": 0.5316,
       "step": 1000
+    },
+    {
+      "epoch": 0.3117206982543641,
+      "grad_norm": 1.4351526498794556,
+      "learning_rate": 1.79260182876143e-05,
+      "loss": 0.483,
+      "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