Training in progress, step 90000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5c6edbd27558aca49d30391d1ef6740f42d89e02202741bfa6556c5bb200e6
+oid sha256:134d6d1a136e6964ae2ed697436824732ef4204be572a5639879cde01c496fb4
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1666258a1f724f902b9aa295ec67f13a120dd77f80fd4e6bc4d68349a651a63
+oid sha256:f633f40ddd88931a1bcbba40dbb7908be8ffc1f11ca88c044ce2b036b207de26
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67d9b61cee8ca67c27f0f3d2f6e201039abcc50fe9c69747f98360b11e440474
+oid sha256:5672e7460ec4bb20926333b87c1de2eb753f75f0449ae9dd507ee1cf812c0bce
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a497315615827dbfe07ef4ef54afba40b23c55667dfa82ac40626574a432d00
+oid sha256:cefa1feb46fb134136cae0514a9b4d7f5ee7c548f72ebedcd52cca0c9d5a1399
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f62de7b3720d73b36506a2be2c357e852a008b86421c13562a927e573a51594
+oid sha256:811c50c92fcf0d94c6c776ed6e8ceff3da691c7f85fb718fb2430787c3ac61c5
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b65baacae1e9b6120b362e0290a5ce659aa309c6bbced410beb869eaf2627764
-size 14439
+oid sha256:4bbf02a4081ed4b267df817f2c1eebe3e21fb0c27efa334683d9878792c81135
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e52a6dd6fc2ba6933bc667fca14386a68b07572a9b1700ef8ab0b34bba18efa7
+oid sha256:fbbaa3fc76ce5e36303621f0b3c2a3411cdf79310693a1e151a2d13a1eef02ee
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2216165040389695,
-  "global_step": 80000,
+  "epoch": 1.3743185670438407,
+  "global_step": 90000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -598,11 +598,85 @@
       "eval_samples_per_second": 922.521,
       "eval_steps_per_second": 14.76,
       "step": 80000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00014963249471630944,
+      "loss": 0.3906,
+      "step": 81000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.000149608424764662,
+      "loss": 0.391,
+      "step": 82000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0001495835935864336,
+      "loss": 0.3875,
+      "step": 83000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00014955800145317397,
+      "loss": 0.3861,
+      "step": 84000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00014953164864475466,
+      "loss": 0.3844,
+      "step": 85000
+    },
+    {
+      "epoch": 1.3,
+      "eval_runtime": 1.0992,
+      "eval_samples_per_second": 909.734,
+      "eval_steps_per_second": 14.556,
+      "step": 85000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0001495045354493657,
+      "loss": 0.3829,
+      "step": 86000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00014947666216351272,
+      "loss": 0.3815,
+      "step": 87000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00014944802909201344,
+      "loss": 0.38,
+      "step": 88000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00014941863654799456,
+      "loss": 0.3789,
+      "step": 89000
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00014938848485288825,
+      "loss": 0.3785,
+      "step": 90000
+    },
+    {
+      "epoch": 1.37,
+      "eval_runtime": 0.9266,
+      "eval_samples_per_second": 1079.167,
+      "eval_steps_per_second": 17.267,
+      "step": 90000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 5.608014311746284e+21,
+  "total_flos": 6.309016922049755e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1666258a1f724f902b9aa295ec67f13a120dd77f80fd4e6bc4d68349a651a63
+oid sha256:f633f40ddd88931a1bcbba40dbb7908be8ffc1f11ca88c044ce2b036b207de26
 size 449471589