Training in progress, step 100000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:074aae3be36ece720227c7d5704e6c459a837d5e9816c40e062f7d71f8a7ce90
+oid sha256:d082cb4b72cfdb4254a34e305011b454d31bb30dbd27c42aa24b574147c540e9
 size 3871544599

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e19e2e264275220026b221d7bd9bb2485aa9d99a2f9b2280088444e28714ea1
+oid sha256:112a525385ef4b2920ca2e4ee2218f98e8c63380cb36d3d525690ca7a1c7da52
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a0459cecd0f6210ddc54ea326d85e85954cf661a179b72074a382bb5f0d54b3
+oid sha256:41cdaa8da95e94cc1e97cd08cfc56ef217e59ee59f7687ac8419775c4bc80984
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:260d8130ef6fe72af25504bb5a639384b37c9ba0958144b30ad87da616600c37
+oid sha256:7953899316608ec70beb2202d2f7cbae5152dd2b0e53df4aac9eef077d77e70d
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea86b41f09818c6bd10502d4bb8bdc8400743097d02b351deb58e5fb424dae99
+oid sha256:12799c4bd0d2d9858c0d7696e12e998a91a87a7a92ec0bf0a40a0e286e746cf8
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6783876985697326,
-  "global_step": 96000,
+  "epoch": 0.7066538526768048,
+  "global_step": 100000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1158,11 +1158,59 @@
       "learning_rate": 4.943485406239044e-06,
       "loss": 1.5726,
       "step": 96000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.942897190956574e-06,
+      "loss": 1.5713,
+      "step": 96500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.9423059657304774e-06,
+      "loss": 1.5863,
+      "step": 97000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.941711731289216e-06,
+      "loss": 1.6008,
+      "step": 97500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.941115685852782e-06,
+      "loss": 1.609,
+      "step": 98000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.9405154411961575e-06,
+      "loss": 1.6016,
+      "step": 98500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.939913399034342e-06,
+      "loss": 1.5992,
+      "step": 99000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.939307147114736e-06,
+      "loss": 1.6742,
+      "step": 99500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.938697889674869e-06,
+      "loss": 1.689,
+      "step": 100000
     }
   ],
   "max_steps": 1415120,
   "num_train_epochs": 10,
-  "total_flos": 4.69878476684329e+16,
+  "total_flos": 4.83002072753111e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e19e2e264275220026b221d7bd9bb2485aa9d99a2f9b2280088444e28714ea1
+oid sha256:112a525385ef4b2920ca2e4ee2218f98e8c63380cb36d3d525690ca7a1c7da52
 size 1944201353

runs/May15_17-32-55_19599b9fb4f0/events.out.tfevents.1684173637.19599b9fb4f0.1168.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9508222cf629cc8c15c6c6fe7cc63d0f5c27a274c448d029b1102a9154d2351b
-size 8303
+oid sha256:ef30ab0bad199cc307dca07844477268dc4ed31ab93798a295ba8e4bfd265751
+size 9583