Training in progress, step 100000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134d6d1a136e6964ae2ed697436824732ef4204be572a5639879cde01c496fb4
+oid sha256:db2e288361a09b4b7188ac62d2aadda977c3d294af8ad3f73e2b72bd0663ea87
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f633f40ddd88931a1bcbba40dbb7908be8ffc1f11ca88c044ce2b036b207de26
+oid sha256:6dfd008c5411020d58a84a813d4db30ca837b9cce0a2b859586eb276a2928563
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5672e7460ec4bb20926333b87c1de2eb753f75f0449ae9dd507ee1cf812c0bce
+oid sha256:e4f9af544e31603097b82ac1d9757b18d1e77cd9d3f5e0d82ff6f70151a0ec04
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cefa1feb46fb134136cae0514a9b4d7f5ee7c548f72ebedcd52cca0c9d5a1399
+oid sha256:80e543431b9b9286d502e9e435479120e37dfd67af853c03aa4e1515f6425d35
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:811c50c92fcf0d94c6c776ed6e8ceff3da691c7f85fb718fb2430787c3ac61c5
+oid sha256:52d6b11ee335cf1f946095db74d4fad452219b5271b7968de8a4d7e06234c4ee
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bbf02a4081ed4b267df817f2c1eebe3e21fb0c27efa334683d9878792c81135
+oid sha256:4b705ae3e4d654b3daa3e7cb177baf9ea0f4c55d7b0f6bedb7d163c3dc6d902c
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbbaa3fc76ce5e36303621f0b3c2a3411cdf79310693a1e151a2d13a1eef02ee
+oid sha256:ab0b752b3079dc9be868ddd61d4a48c6f227ceaa95b4267c4d5e0911b7baba7b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3743185670438407,
-  "global_step": 90000,
+  "epoch": 1.527020630048712,
+  "global_step": 100000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -672,11 +672,85 @@
       "eval_samples_per_second": 1079.167,
       "eval_steps_per_second": 17.267,
       "step": 90000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0001493575743364286,
+      "loss": 0.3766,
+      "step": 91000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00014932590533664808,
+      "loss": 0.3745,
+      "step": 92000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.0001492934781998738,
+      "loss": 0.3741,
+      "step": 93000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.0001492602932807237,
+      "loss": 0.3729,
+      "step": 94000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00014922635094210277,
+      "loss": 0.3709,
+      "step": 95000
+    },
+    {
+      "epoch": 1.45,
+      "eval_runtime": 0.9895,
+      "eval_samples_per_second": 1010.579,
+      "eval_steps_per_second": 16.169,
+      "step": 95000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.000149191651555199,
+      "loss": 0.3699,
+      "step": 96000
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.0001491561954994793,
+      "loss": 0.3688,
+      "step": 97000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00014911998316268537,
+      "loss": 0.3678,
+      "step": 98000
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00014908301494082963,
+      "loss": 0.3666,
+      "step": 99000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00014904529123819054,
+      "loss": 0.3654,
+      "step": 100000
+    },
+    {
+      "epoch": 1.53,
+      "eval_runtime": 1.0046,
+      "eval_samples_per_second": 995.424,
+      "eval_steps_per_second": 15.927,
+      "step": 100000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 6.309016922049755e+21,
+  "total_flos": 7.010019532353227e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f633f40ddd88931a1bcbba40dbb7908be8ffc1f11ca88c044ce2b036b207de26
+oid sha256:6dfd008c5411020d58a84a813d4db30ca837b9cce0a2b859586eb276a2928563
 size 449471589