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:e576b9403b0280ea633f40cc360e0f62f787d8613dea811cfd6c6a418cc3ac0c
+oid sha256:e830957ac14db3a9074c9d4201c9207500b7bc106f894e3e93d3ff83b141254e
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8b043334135c082c25cf6c629200e4f170f3a5a6d0880e726c4c35930144452
+oid sha256:095ef47cee3fe623a1cab782aabc0865174f6863144a23ad426d06bea2581852
 size 127788180

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb7c4f26e392579293b6421ef5f149945ac0f9d888c22e3a6dbba00d44cbd66f
+oid sha256:c146388a3e375aff2b63de7d9a527540be61e69f806a75222257789592fb97ff
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:517d172c0957a5d0a87e85d64f047aa4020d33d97084cce4e3f00b119f19b7ae
+oid sha256:41a785ff17fa78518f56867cd303b6ba59257cf76b3fcae729747c3054010b8f
 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": 0.23757852655625358,
+  "epoch": 0.47515705311250717,
   "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": 5.576,
       "eval_steps_per_second": 1.405,
       "step": 13
+    },
+    {
+      "epoch": 0.25585379782981155,
+      "grad_norm": 2.663853168487549,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.6116,
+      "step": 14
+    },
+    {
+      "epoch": 0.2741290691033695,
+      "grad_norm": 2.392077922821045,
+      "learning_rate": 8.296729075500344e-05,
+      "loss": 0.3944,
+      "step": 15
+    },
+    {
+      "epoch": 0.2924043403769275,
+      "grad_norm": 2.333585262298584,
+      "learning_rate": 8.043807145043604e-05,
+      "loss": 0.2627,
+      "step": 16
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 0.5413778424263,
+      "learning_rate": 7.777851165098012e-05,
+      "loss": 0.1026,
+      "step": 17
+    },
+    {
+      "epoch": 0.3289548829240434,
+      "grad_norm": 1.2651410102844238,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.2252,
+      "step": 18
+    },
+    {
+      "epoch": 0.3472301541976014,
+      "grad_norm": 0.9693997502326965,
+      "learning_rate": 7.211443451095007e-05,
+      "loss": 0.0994,
+      "step": 19
+    },
+    {
+      "epoch": 0.36550542547115933,
+      "grad_norm": 1.002900242805481,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.1058,
+      "step": 20
+    },
+    {
+      "epoch": 0.3837806967447173,
+      "grad_norm": 0.8303418755531311,
+      "learning_rate": 6.607197326515808e-05,
+      "loss": 0.0462,
+      "step": 21
+    },
+    {
+      "epoch": 0.40205596801827526,
+      "grad_norm": 0.6390141248703003,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.0405,
+      "step": 22
+    },
+    {
+      "epoch": 0.42033123929183325,
+      "grad_norm": 0.6512762308120728,
+      "learning_rate": 5.9754516100806423e-05,
+      "loss": 0.0238,
+      "step": 23
+    },
+    {
+      "epoch": 0.4386065105653912,
+      "grad_norm": 0.7656252980232239,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.0375,
+      "step": 24
+    },
+    {
+      "epoch": 0.4568817818389492,
+      "grad_norm": 0.46867817640304565,
+      "learning_rate": 5.327015646150716e-05,
+      "loss": 0.016,
+      "step": 25
+    },
+    {
+      "epoch": 0.47515705311250717,
+      "grad_norm": 0.22703154385089874,
+      "learning_rate": 5e-05,
+      "loss": 0.0108,
+      "step": 26
+    },
+    {
+      "epoch": 0.47515705311250717,
+      "eval_loss": 0.011774315498769283,
+      "eval_runtime": 66.1555,
+      "eval_samples_per_second": 5.578,
+      "eval_steps_per_second": 1.406,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.281361167510405e+17,
+  "total_flos": 1.056272233502081e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null