Training in progress, step 230000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:693acb404bd716024339c392e2525a222d512799f307cbc3c627cc06cc273d0a
+oid sha256:a06ef5c009b6a3d34b61b8e9435e48bd8704c1092e28f5d3a8a0669a2a565c45
 size 893441530

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9716372fe65b419e7c80eb8977da754b2b98eb5f76ef3a580319f2fed92f0540
+oid sha256:95f9300ed2f42668d1280e1852bf99100220c183e1a5aa40fe963881c2f1f15c
 size 454197066

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f790e3c44cecb3ef71e873c48e467d4d611b47cfee4cb2ead4b7c85d77cdf919
-size 14244
+oid sha256:da60bc481c5e8dde4e51a48ffefd72b80167a866448e54613b2b81fb34be2af3
+size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:824fa47ba659f4ce2f56c6bbe2607cad986b97216c333c1aa067688c46dbd745
+oid sha256:fa1786a2f6edec81fd73665bbfadc34243a09e187302f15861e7ba28d522bf54
 size 1064

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.22,
-  "global_step": 220000,
+  "epoch": 0.23,
+  "global_step": 230000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1634,11 +1634,85 @@
       "eval_samples_per_second": 106.201,
       "eval_steps_per_second": 13.275,
       "step": 220000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8068934674071315e-05,
+      "loss": 0.3679,
+      "step": 221000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8061162222523262e-05,
+      "loss": 0.3655,
+      "step": 222000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8053349459695724e-05,
+      "loss": 0.3657,
+      "step": 223000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8045496471027813e-05,
+      "loss": 0.3655,
+      "step": 224000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.803760334239856e-05,
+      "loss": 0.3667,
+      "step": 225000
+    },
+    {
+      "epoch": 0.23,
+      "eval_runtime": 3366.2132,
+      "eval_samples_per_second": 100.9,
+      "eval_steps_per_second": 12.613,
+      "step": 225000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.802967016012596e-05,
+      "loss": 0.3668,
+      "step": 226000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8021697010966016e-05,
+      "loss": 0.3669,
+      "step": 227000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8013683982111812e-05,
+      "loss": 0.366,
+      "step": 228000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8005631161192552e-05,
+      "loss": 0.3692,
+      "step": 229000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7997538636272585e-05,
+      "loss": 0.3683,
+      "step": 230000
+    },
+    {
+      "epoch": 0.23,
+      "eval_runtime": 3198.8818,
+      "eval_samples_per_second": 106.178,
+      "eval_steps_per_second": 13.272,
+      "step": 230000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 1.948014238110843e+21,
+  "total_flos": 2.036560339843154e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9716372fe65b419e7c80eb8977da754b2b98eb5f76ef3a580319f2fed92f0540
+oid sha256:95f9300ed2f42668d1280e1852bf99100220c183e1a5aa40fe963881c2f1f15c
 size 454197066