Training in progress, step 93, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31c49463f3821582d9d78755f5eb97a42b46bfdd8f9601d6971f4f497316456e
+oid sha256:caeddd11e4b9cc9d83e11d9ec3987e94c5436376e83a9998ce3068e458397d51
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:255c08b2f79fe4bae4226d36f7cf03b9c43f1a10cbb716e63d3c74250abc8ff2
+oid sha256:705b00d71daa4142253c16c1bebea91dabaa93d2b6338a801dde26f42519f2dc
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:149f5934ccd723cc5ecad7bf2a9242c754be0eb33e2819fc4e2d0c12aedee181
+oid sha256:67ac7f1c5347e279b4947122f9a4f1ea87fde404d3dbf35cb5a047b4265298f9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d1b8a36fcf0317e6a9c8738d638639c228d4b5886701e2af2c36b54e118f8ba
+oid sha256:96bfc2360018b511a262b59e99fcddde6a9bd8f019814a20e26529e523d531e5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5030425963488844,
+  "epoch": 0.7545638945233266,
   "eval_steps": 31,
-  "global_step": 62,
+  "global_step": 93,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -171,6 +171,91 @@
       "eval_samples_per_second": 15.504,
       "eval_steps_per_second": 1.938,
       "step": 62
+    },
+    {
+      "epoch": 0.5111561866125761,
+      "grad_norm": 3.9001667499542236,
+      "learning_rate": 9.474671808010126e-05,
+      "loss": 2.3843,
+      "step": 63
+    },
+    {
+      "epoch": 0.5354969574036511,
+      "grad_norm": 6.379414081573486,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 2.2963,
+      "step": 66
+    },
+    {
+      "epoch": 0.5598377281947262,
+      "grad_norm": 4.97390079498291,
+      "learning_rate": 9.351778479699499e-05,
+      "loss": 2.2517,
+      "step": 69
+    },
+    {
+      "epoch": 0.5841784989858012,
+      "grad_norm": 4.063937187194824,
+      "learning_rate": 9.285836503510562e-05,
+      "loss": 2.2437,
+      "step": 72
+    },
+    {
+      "epoch": 0.6085192697768763,
+      "grad_norm": 3.602717161178589,
+      "learning_rate": 9.21695722906443e-05,
+      "loss": 2.1695,
+      "step": 75
+    },
+    {
+      "epoch": 0.6328600405679513,
+      "grad_norm": 4.555128574371338,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 2.1648,
+      "step": 78
+    },
+    {
+      "epoch": 0.6572008113590264,
+      "grad_norm": 5.0544867515563965,
+      "learning_rate": 9.070577591781597e-05,
+      "loss": 2.0922,
+      "step": 81
+    },
+    {
+      "epoch": 0.6815415821501014,
+      "grad_norm": 4.92878532409668,
+      "learning_rate": 8.993177550236464e-05,
+      "loss": 2.141,
+      "step": 84
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 3.6681647300720215,
+      "learning_rate": 8.91304078426207e-05,
+      "loss": 2.1638,
+      "step": 87
+    },
+    {
+      "epoch": 0.7302231237322515,
+      "grad_norm": 4.451002597808838,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 2.1766,
+      "step": 90
+    },
+    {
+      "epoch": 0.7545638945233266,
+      "grad_norm": 5.902685165405273,
+      "learning_rate": 8.744778603945011e-05,
+      "loss": 2.1005,
+      "step": 93
+    },
+    {
+      "epoch": 0.7545638945233266,
+      "eval_loss": 0.5568718314170837,
+      "eval_runtime": 13.4611,
+      "eval_samples_per_second": 15.452,
+      "eval_steps_per_second": 1.931,
+      "step": 93
     }
   ],
   "logging_steps": 3,
@@ -190,7 +275,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.249073800419738e+16,
+  "total_flos": 1.2373610700629606e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null