Training in progress, step 65000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aed51e0509bb804385dd26ac7efc0a9e47a56e347156f29e3530e79f493ac7f3
+oid sha256:0245292760b62513586c26ecff5192e7b5ad83e4daf7f643ddd61d6aad92d500
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a31c1c501f73be8d8a7f16e11d37411e3c712923b4a21ad6ffb33847450b9a
+oid sha256:91a835f354ab09525c33e280985ebd252ba93511526376509b024f45deb2f1ce
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84403784a2e4bb85790fc8f78c7002661d073ba9542c895bc847b8a1bf1ca7ae
+oid sha256:0b21161fe5b062917103c130cb71a421351140e37488dc23aeb32719319cb94c
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07abcb633a1c3c4eb53fd4703a59c8c41655d2c68e08d0e8e61edbd1a57b1690
+oid sha256:e3871d161af5dbcdf99fa548f2814e73dcf94f0ccbb13b2f6c2217e93008fee6
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8324a5d497c15c28556ce4fc72c170ad143b9c0359a73895cbbd954cdf4285ab
+oid sha256:3d89e9311da168e5510e65cc996f92e058a83847391982c385da0d08e788c7ea
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.482500435312555,
-  "global_step": 60000,
+  "epoch": 4.917812989726624,
+  "global_step": 65000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -822,11 +822,79 @@
       "eval_samples_per_second": 53.313,
       "eval_steps_per_second": 0.842,
       "step": 60000
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 4.0717494800280484e-05,
+      "loss": 0.414,
+      "step": 60500
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 4.0044619833152034e-05,
+      "loss": 0.4127,
+      "step": 61000
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 3.937553126317129e-05,
+      "loss": 0.4129,
+      "step": 61500
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 3.871039417793112e-05,
+      "loss": 0.4125,
+      "step": 62000
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 3.804937269005464e-05,
+      "loss": 0.4121,
+      "step": 62500
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 3.7392629896702916e-05,
+      "loss": 0.4121,
+      "step": 63000
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 3.674032783933316e-05,
+      "loss": 0.4119,
+      "step": 63500
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 3.609262746371739e-05,
+      "loss": 0.4116,
+      "step": 64000
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 3.544968858023156e-05,
+      "loss": 0.4107,
+      "step": 64500
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 3.481294084680979e-05,
+      "loss": 0.412,
+      "step": 65000
+    },
+    {
+      "epoch": 4.92,
+      "eval_loss": 0.38968759775161743,
+      "eval_runtime": 78.1248,
+      "eval_samples_per_second": 64.0,
+      "eval_steps_per_second": 1.011,
+      "step": 65000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 2.8258565659645575e+21,
+  "total_flos": 3.061349633329319e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a31c1c501f73be8d8a7f16e11d37411e3c712923b4a21ad6ffb33847450b9a
+oid sha256:91a835f354ab09525c33e280985ebd252ba93511526376509b024f45deb2f1ce
 size 449471589