Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4db332fd692eecebff30bb8c9b537f415280397f56b3f811fd098e995e328ffb
+oid sha256:fa7f4c140e0a9b39eeaffc7a1e059cd78cef04b00f4bfee8a0f71514b264c6a9
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a2f2eb2e24a56d7d5eaf5521899e1fdeb193391df054fc4fc05957e390facde
+oid sha256:9a05301d92fe47da545a4a20f7bea86b27a9160f047c5ef4b2ba90f3dfd24d6d
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df8e58994fbfb265c03f4dde71af06ed5e6d6648055cc85eea0d8767265600f4
+oid sha256:7b10a95fbb58ac93569219ce9d1af718f81e5e7c7129aedc857bba9ef24f2c7e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.035404496371039124,
+  "epoch": 0.07080899274207825,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 3.902,
       "eval_steps_per_second": 1.954,
       "step": 25
+    },
+    {
+      "epoch": 0.036820676225880686,
+      "grad_norm": 2.2406327724456787,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.1696,
+      "step": 26
+    },
+    {
+      "epoch": 0.038236856080722255,
+      "grad_norm": 0.21706989407539368,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.1207,
+      "step": 27
+    },
+    {
+      "epoch": 0.03965303593556382,
+      "grad_norm": 0.6819403767585754,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.1059,
+      "step": 28
+    },
+    {
+      "epoch": 0.04106921579040538,
+      "grad_norm": 1.85183584690094,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.1389,
+      "step": 29
+    },
+    {
+      "epoch": 0.04248539564524695,
+      "grad_norm": 0.6912545561790466,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.1074,
+      "step": 30
+    },
+    {
+      "epoch": 0.04390157550008851,
+      "grad_norm": 0.2985907196998596,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.1139,
+      "step": 31
+    },
+    {
+      "epoch": 0.04531775535493007,
+      "grad_norm": 0.9557470083236694,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.1193,
+      "step": 32
+    },
+    {
+      "epoch": 0.04673393520977164,
+      "grad_norm": 0.38003310561180115,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.112,
+      "step": 33
+    },
+    {
+      "epoch": 0.048150115064613204,
+      "grad_norm": 0.3061525523662567,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.107,
+      "step": 34
+    },
+    {
+      "epoch": 0.04956629491945477,
+      "grad_norm": 0.29527008533477783,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.1145,
+      "step": 35
+    },
+    {
+      "epoch": 0.050982474774296335,
+      "grad_norm": 0.4223112463951111,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.0935,
+      "step": 36
+    },
+    {
+      "epoch": 0.0523986546291379,
+      "grad_norm": 0.8453797101974487,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.0726,
+      "step": 37
+    },
+    {
+      "epoch": 0.053814834483979467,
+      "grad_norm": 0.26757749915122986,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.0648,
+      "step": 38
+    },
+    {
+      "epoch": 0.05523101433882103,
+      "grad_norm": 1.951507806777954,
+      "learning_rate": 5e-05,
+      "loss": 0.145,
+      "step": 39
+    },
+    {
+      "epoch": 0.0566471941936626,
+      "grad_norm": 2.7410080432891846,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.206,
+      "step": 40
+    },
+    {
+      "epoch": 0.05806337404850416,
+      "grad_norm": 0.6865355968475342,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.0908,
+      "step": 41
+    },
+    {
+      "epoch": 0.05947955390334572,
+      "grad_norm": 0.949466347694397,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0796,
+      "step": 42
+    },
+    {
+      "epoch": 0.06089573375818729,
+      "grad_norm": 0.7530195713043213,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0922,
+      "step": 43
+    },
+    {
+      "epoch": 0.06231191361302885,
+      "grad_norm": 1.2768175601959229,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.0763,
+      "step": 44
+    },
+    {
+      "epoch": 0.06372809346787042,
+      "grad_norm": 0.44944190979003906,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0563,
+      "step": 45
+    },
+    {
+      "epoch": 0.06514427332271198,
+      "grad_norm": 1.1507816314697266,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.1047,
+      "step": 46
+    },
+    {
+      "epoch": 0.06656045317755355,
+      "grad_norm": 0.27491295337677,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0581,
+      "step": 47
+    },
+    {
+      "epoch": 0.06797663303239511,
+      "grad_norm": 0.8990926742553711,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.1178,
+      "step": 48
+    },
+    {
+      "epoch": 0.06939281288723669,
+      "grad_norm": 0.36759093403816223,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.0581,
+      "step": 49
+    },
+    {
+      "epoch": 0.07080899274207825,
+      "grad_norm": 0.25813916325569153,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.0469,
+      "step": 50
+    },
+    {
+      "epoch": 0.07080899274207825,
+      "eval_loss": 0.10698376595973969,
+      "eval_runtime": 153.0381,
+      "eval_samples_per_second": 3.888,
+      "eval_steps_per_second": 1.947,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.786003044735386e+16,
+  "total_flos": 7.516055305558426e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null