Training in progress, step 64000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4308792b2a033acdce96ce47703119686ade603de91305623f9a41bb3db8197d
+oid sha256:3fe8795e671335d7bddeedb39821f0948379d742e636bab99e4d84da9158869a
 size 3871543575

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24918df0f1f9d1f5aadf7b8e4933628be882e87804ac0114cbca0ad2c83737f7
+oid sha256:c80a0783dcb4761d467c9fccd3ad9305d694cfd8a74940361136dfaf12ce4dfa
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:836afdbaf7ed0232c311bb2609eff325953c229bbc4edb90bdadf6a7412ce2aa
+oid sha256:e989135ee750e533a2b907997960a8cf01e270032e6a00adbd8dce6e9b4179f2
 size 14511

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df056184eca867a0b00a4f1fa76891f3c4f5cedd6a7d840fcd41506dafeb0b63
+oid sha256:8474830dbb0ee2555c7fca1ddb59c3a8703100405178d69f471e9f9597100d49
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ae4577bcc43ac54c56a413372da787f2adba41ace305a09ecc065c5e91b0b80
+oid sha256:b7ba5db5b81b6826d9b84207559dd8cdb0b9297845fc72cde43cb565faf3a995
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6359907145355678,
-  "global_step": 60000,
+  "epoch": 0.6783900955046056,
+  "global_step": 64000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -726,11 +726,59 @@
       "learning_rate": 4.95030419957734e-06,
       "loss": 1.7637,
       "step": 60000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 4.9494749648583875e-06,
+      "loss": 1.7161,
+      "step": 60500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.94863893948379e-06,
+      "loss": 1.7069,
+      "step": 61000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.9477978181718865e-06,
+      "loss": 1.7084,
+      "step": 61500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.946949937970748e-06,
+      "loss": 1.7007,
+      "step": 62000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.946093581740578e-06,
+      "loss": 1.714,
+      "step": 62500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.9452304442289365e-06,
+      "loss": 1.7228,
+      "step": 63000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.944360527828692e-06,
+      "loss": 1.7279,
+      "step": 63500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.943483834951505e-06,
+      "loss": 1.7026,
+      "step": 64000
     }
   ],
   "max_steps": 943410,
   "num_train_epochs": 10,
-  "total_flos": 3.379573384711373e+16,
+  "total_flos": 3.605231193396019e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24918df0f1f9d1f5aadf7b8e4933628be882e87804ac0114cbca0ad2c83737f7
+oid sha256:c80a0783dcb4761d467c9fccd3ad9305d694cfd8a74940361136dfaf12ce4dfa
 size 1944201353

runs/May14_19-37-01_15e842f7c026/events.out.tfevents.1684094526.15e842f7c026.771.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de578695d7b19188bd6bbd53f9a0638874a8dcac4a1771e6bcf927b6589c26eb
-size 5743
+oid sha256:77b91fb82c97d3bca0eb4dfcc9806cd209db085bb56a651dc6901c0500042a65
+size 7023