Training in progress, step 104000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d082cb4b72cfdb4254a34e305011b454d31bb30dbd27c42aa24b574147c540e9
+oid sha256:5b6b72e44546364141ee724a3720f7fcd3e0187baca4188905097793e58f73cf
 size 3871544599

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:112a525385ef4b2920ca2e4ee2218f98e8c63380cb36d3d525690ca7a1c7da52
+oid sha256:06e0f8fd34ad9689e90c51a6ce416bb3efe00164a6779e3a86f8096cf6b0c3e6
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41cdaa8da95e94cc1e97cd08cfc56ef217e59ee59f7687ac8419775c4bc80984
+oid sha256:406220ea58b0ef58e4c479dbacbea0d151a94a8fec8c33f3207fb059c4aaf735
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7953899316608ec70beb2202d2f7cbae5152dd2b0e53df4aac9eef077d77e70d
+oid sha256:c168c2a8f00ea281d9279e79fc22bf9baa2663e805bc63f10cd023cb5f2adac6
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12799c4bd0d2d9858c0d7696e12e998a91a87a7a92ec0bf0a40a0e286e746cf8
+oid sha256:92c4f8cd51d2e8c9949ea38c90ce4eb9bc18b9068fc7636cfea38097eac939ad
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7066538526768048,
-  "global_step": 100000,
+  "epoch": 0.734920006783877,
+  "global_step": 104000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1206,11 +1206,59 @@
       "learning_rate": 4.938697889674869e-06,
       "loss": 1.689,
       "step": 100000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.938085627465422e-06,
+      "loss": 1.6779,
+      "step": 100500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.937470361240773e-06,
+      "loss": 1.694,
+      "step": 101000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.936852091759006e-06,
+      "loss": 1.6757,
+      "step": 101500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.936230819781902e-06,
+      "loss": 1.7025,
+      "step": 102000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.935606546074945e-06,
+      "loss": 1.6897,
+      "step": 102500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.934980528951094e-06,
+      "loss": 1.7087,
+      "step": 103000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.9343502600952685e-06,
+      "loss": 1.6645,
+      "step": 103500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.9337169918266646e-06,
+      "loss": 1.6942,
+      "step": 104000
     }
   ],
   "max_steps": 1415120,
   "num_train_epochs": 10,
-  "total_flos": 4.83002072753111e+16,
+  "total_flos": 4.963728541905715e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:112a525385ef4b2920ca2e4ee2218f98e8c63380cb36d3d525690ca7a1c7da52
+oid sha256:06e0f8fd34ad9689e90c51a6ce416bb3efe00164a6779e3a86f8096cf6b0c3e6
 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:ef30ab0bad199cc307dca07844477268dc4ed31ab93798a295ba8e4bfd265751
-size 9583
+oid sha256:3f04fd7a7e58b8b6bf9158b672f823af500a6cb60bdddafb0354038ce68a02da
+size 10863