Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c41c205df1f52f97b5247e30d999b8f0f65b3b0d781e26412f52afc1376941
+oid sha256:bc09b6d832460f6125f2db8055c6f9f537d1ea3414f1f8a8a8e22b7efa3fa616
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23760c172a79ee1de058ab769f0f369bf7d5c56d7e7443ddcd35a24664a8ff3d
+oid sha256:157cd5c27e1bbfa5f91dac42e11035af12e5b2d92b54551902af11acc1b94a7c
 size 81730196

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfcdef8a8b916b711480982f753423d6133b7c4e35e662651b9da32ca0cd379f
+oid sha256:e79f6ba8fb7ffd48989487f6e68f93db591e92af3a69e568722794c031540f83
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea18bc07366a2f238e1591e2c8ffd4355de51a0adee25da04857a678c39dc63a
+oid sha256:ecf7ec282beb1f61e959b9e912d5b9b4c3128e903769f4f35493243fd1bdc61b
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18285714285714286,
+  "epoch": 0.3657142857142857,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 11.599,
       "eval_steps_per_second": 2.906,
       "step": 13
+    },
+    {
+      "epoch": 0.19692307692307692,
+      "grad_norm": 0.2747080326080322,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.8738,
+      "step": 14
+    },
+    {
+      "epoch": 0.210989010989011,
+      "grad_norm": 0.2343476116657257,
+      "learning_rate": 8.296729075500344e-05,
+      "loss": 0.8745,
+      "step": 15
+    },
+    {
+      "epoch": 0.22505494505494505,
+      "grad_norm": 0.2237587720155716,
+      "learning_rate": 8.043807145043604e-05,
+      "loss": 0.8282,
+      "step": 16
+    },
+    {
+      "epoch": 0.23912087912087912,
+      "grad_norm": 0.19825835525989532,
+      "learning_rate": 7.777851165098012e-05,
+      "loss": 0.842,
+      "step": 17
+    },
+    {
+      "epoch": 0.2531868131868132,
+      "grad_norm": 0.16660410165786743,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.8453,
+      "step": 18
+    },
+    {
+      "epoch": 0.2672527472527473,
+      "grad_norm": 0.1577339917421341,
+      "learning_rate": 7.211443451095007e-05,
+      "loss": 0.844,
+      "step": 19
+    },
+    {
+      "epoch": 0.2813186813186813,
+      "grad_norm": 0.1596086323261261,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.8101,
+      "step": 20
+    },
+    {
+      "epoch": 0.2953846153846154,
+      "grad_norm": 0.1533115953207016,
+      "learning_rate": 6.607197326515808e-05,
+      "loss": 0.8229,
+      "step": 21
+    },
+    {
+      "epoch": 0.30945054945054945,
+      "grad_norm": 0.1380361020565033,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.8142,
+      "step": 22
+    },
+    {
+      "epoch": 0.32351648351648354,
+      "grad_norm": 0.12135830521583557,
+      "learning_rate": 5.9754516100806423e-05,
+      "loss": 0.7935,
+      "step": 23
+    },
+    {
+      "epoch": 0.3375824175824176,
+      "grad_norm": 0.12721355259418488,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.8114,
+      "step": 24
+    },
+    {
+      "epoch": 0.3516483516483517,
+      "grad_norm": 0.12719641625881195,
+      "learning_rate": 5.327015646150716e-05,
+      "loss": 0.8137,
+      "step": 25
+    },
+    {
+      "epoch": 0.3657142857142857,
+      "grad_norm": 0.12431051582098007,
+      "learning_rate": 5e-05,
+      "loss": 0.8016,
+      "step": 26
+    },
+    {
+      "epoch": 0.3657142857142857,
+      "eval_loss": 0.7906247973442078,
+      "eval_runtime": 41.3118,
+      "eval_samples_per_second": 11.595,
+      "eval_steps_per_second": 2.905,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7423994538675405e+17,
+  "total_flos": 5.484798907735081e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null