Training in progress, step 80, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04866f19224e3c6c707b48a084793f67427a2ceb7d472a6a60dfe7279f936357
+oid sha256:5252b2d702ec4e4b7629e26fe3a70c426d1c12a5b12acd3ae606f3a9754efaae
 size 662430992

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d05bf854ec5530dc19213111fa317517d4f95ecbdc1f9b16cddf88cdfc4cc9fd
+oid sha256:242746371cb73d68846b644343062826e77803c4164e9556ac463d01ae95069f
 size 674384884

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3918916686970543d4efb3f1e180491d463d9768b77aeff4079700a44921b20
+oid sha256:a50d87badb0708be06ac367c54fb94d34320d2eb8407fd57285a16c8da09911d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:994eed7336e125de256b9888e810844dc1d9039754f553de4f39d5f3f96a0fa1
+oid sha256:8a55ac2f13f8b0b0932cc32ea158ca78aa103ef94c5e5ed92bad08a2b3d35ea4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f120d428b54302d9d44f77cb171c5498cd2043508404c77f22a5704748b80184
+oid sha256:4d244a3e1f8a0833f09ba072f66200d74bfe752b03372f6d7e2933c7d7641ba2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a12141330df9b37337d67f7e1b465ad25083268c3227fc1f7a7726159c2fbd0b
+oid sha256:14926bd6988ebc984f858596410fe698400001fdebd5c125a448743474bdadad
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f299ab56b5f200cab03608b3ac75cf1761ca29c2207c1dfe5ab919b66f8dbd88
+oid sha256:c420644371984c0c279fff13e73e1c3067315dc564ce90ee02e2ca237d8a9e35
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.571428571428571,
+  "epoch": 11.428571428571429,
   "eval_steps": 20,
-  "global_step": 60,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -81,6 +81,28 @@
       "eval_samples_per_second": 304.43,
       "eval_steps_per_second": 3.245,
       "step": 60
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.828125,
+      "learning_rate": 4.530518418775733e-05,
+      "loss": 3.7931,
+      "step": 70
+    },
+    {
+      "epoch": 11.428571428571429,
+      "grad_norm": 1.5625,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 3.7326,
+      "step": 80
+    },
+    {
+      "epoch": 11.428571428571429,
+      "eval_loss": 3.0470147132873535,
+      "eval_runtime": 4.9222,
+      "eval_samples_per_second": 304.944,
+      "eval_steps_per_second": 3.251,
+      "step": 80
     }
   ],
   "logging_steps": 10,
@@ -100,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.147133608165376e+16,
+  "total_flos": 2.862844810887168e+16,
   "train_batch_size": 24,
   "trial_name": null,
   "trial_params": null