Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3149a50f1b0489e2e25715d7093edd9164841faaf349365d3af101e4d2de76ff
+oid sha256:6e02cdfc7b8fc4880b42b8ff60be321dacd0a8ff78df092d3ed9e52862423e16
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:492f0761d4ce0c878039ad15d8dead5c8bed2d8af0a44e502b1a606a4080da2c
+oid sha256:7fb7e9078af9812f92989f4557b21957498f3f10e74175d72f32a1b306258348
 size 111412180

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97ef3ea628ad95cd3d2536a964c5bfdfbeafda4219a7ff983d32d1405c407f79
+oid sha256:f44f8535e242739088c844171d04d95514925895ac23749b1a2bf84bc76bccfa
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4bd93cff19b8ec76eb5beeaec7111e757ccdd9cbffd342b1cf9aec141c9554e
+oid sha256:d94e3c2c501d5df9361a581f9e3f0d0b765f815dc284faaddce0a0aff0524cd1
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:2b7c6b205e1552be0830a6d7bc56be5230d8f9d9a142f3205ff3e7dff8c8730a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5850091407678245,
+  "epoch": 0.8775137111517367,
   "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": 7.093,
       "eval_steps_per_second": 1.773,
       "step": 10
+    },
+    {
+      "epoch": 0.643510054844607,
+      "grad_norm": 6.990315914154053,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 6.2191,
+      "step": 11
+    },
+    {
+      "epoch": 0.7020109689213894,
+      "grad_norm": 6.611320495605469,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 4.9522,
+      "step": 12
+    },
+    {
+      "epoch": 0.7605118829981719,
+      "grad_norm": 8.069223403930664,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 4.3585,
+      "step": 13
+    },
+    {
+      "epoch": 0.8190127970749543,
+      "grad_norm": 7.039530277252197,
+      "learning_rate": 5e-05,
+      "loss": 3.7174,
+      "step": 14
+    },
+    {
+      "epoch": 0.8775137111517367,
+      "grad_norm": 9.83570384979248,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.8227,
+      "step": 15
+    },
+    {
+      "epoch": 0.8775137111517367,
+      "eval_loss": 4.3420915603637695,
+      "eval_runtime": 16.3441,
+      "eval_samples_per_second": 7.097,
+      "eval_steps_per_second": 1.774,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7121597487775744e+17,
+  "total_flos": 4.0682396231663616e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null