Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5479e3fb1429f6f1432a3f9cbbf5788e5a6ebdf6b2766bbe5c723ea6589a5ead
+oid sha256:93272d9cd36da9660f618f0d4170893e231b805f453f258319f489193a929e61
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02790c5ffa334edf2879f8bd8513d07be98c168dc224ba8eadd8818b78205bf
+oid sha256:834b3e2741cdc3ed93fbe48c07e9651dc3691bdd8c3f26a8de51dbcc2d77f03f
 size 61926

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359d0ddb346e1a051d153b9361e52227f5a93bfd11d7d59f8d34fe81bcaff9e5
+oid sha256:6279e2d6d30b2ce7f2189e648e383ab146d51fb0fecf44d1e16d05504562e6f8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.054945054945054944,
+  "epoch": 0.08241758241758242,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 33.677,
       "eval_steps_per_second": 16.839,
       "step": 10
+    },
+    {
+      "epoch": 0.06043956043956044,
+      "grad_norm": 0.02739313431084156,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 11.9323,
+      "step": 11
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 0.024653950706124306,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 11.9318,
+      "step": 12
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 0.027017774060368538,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 11.931,
+      "step": 13
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 0.028646156191825867,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.9311,
+      "step": 14
+    },
+    {
+      "epoch": 0.08241758241758242,
+      "grad_norm": 0.028420699760317802,
+      "learning_rate": 5e-05,
+      "loss": 11.9325,
+      "step": 15
+    },
+    {
+      "epoch": 0.08241758241758242,
+      "eval_loss": 11.931500434875488,
+      "eval_runtime": 18.4245,
+      "eval_samples_per_second": 33.325,
+      "eval_steps_per_second": 16.663,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 119915151360.0,
+  "total_flos": 179872727040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null