Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:626a90ee15c300b8170c43b8fdd94992639b4c13087eeeb4d9b1f2beec7a9ff9
+oid sha256:aef52bb299e989df98e293355641ff56dc3a3e43a68926d02328af9171900eec
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79797b2edf02da384d5b52f0397cab41e83685e79b0ee2160290a3a39ed6a854
+oid sha256:b2929a1f5926125f075599864651f213cb0ffd692b2f4fe9b76cd41ba35562cc
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7fb540bf1098f3fafd2ed3f5530d3aedc9e2282c29efa7e1a0eb379d600df5e
+oid sha256:f84c0dab2299268ee9a680624db586d3e2841d6716a98e1cfe7418659efd4637
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8132a70e2c906264f66a9a972096ea0ea0e8f6ed5761ec4dff184c03a94047f0
+oid sha256:50be61d909f587455365584b393b87dd8622c8e62afb45a0896539b949481051
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cc524578aece9db639622bd82bf0d1b1989813f74386e1d5c6d48ba44286a29
+oid sha256:f62d2d7fbdbcf21a71afc7305b03d21c03157d469d6b4bb2e802fdb1e8bc9fc1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c7027a1fee7d6ccfca069071c4dc789a5def1d8b8eb31339fab088adea4107f
+oid sha256:50358e6ae175bd80bfe3762f58f91387f2ddf0abb474b86adfe6e0bd5fd6b2c6
 size 15024

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": 0.007979253939756632,
+  "epoch": 0.015958507879513265,
   "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": 36.776,
       "eval_steps_per_second": 4.6,
       "step": 25
+    },
+    {
+      "epoch": 0.008298424097346898,
+      "grad_norm": 1.4494647979736328,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.0816,
+      "step": 26
+    },
+    {
+      "epoch": 0.008617594254937163,
+      "grad_norm": 0.7066687941551208,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0262,
+      "step": 27
+    },
+    {
+      "epoch": 0.008936764412527429,
+      "grad_norm": 0.8260243535041809,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.0334,
+      "step": 28
+    },
+    {
+      "epoch": 0.009255934570117695,
+      "grad_norm": 0.5964095592498779,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.0204,
+      "step": 29
+    },
+    {
+      "epoch": 0.009575104727707959,
+      "grad_norm": 0.4692519009113312,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0194,
+      "step": 30
+    },
+    {
+      "epoch": 0.009894274885298225,
+      "grad_norm": 1.4883151054382324,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.06,
+      "step": 31
+    },
+    {
+      "epoch": 0.01021344504288849,
+      "grad_norm": 0.21536561846733093,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.005,
+      "step": 32
+    },
+    {
+      "epoch": 0.010532615200478756,
+      "grad_norm": 1.1327840089797974,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.0278,
+      "step": 33
+    },
+    {
+      "epoch": 0.01085178535806902,
+      "grad_norm": 0.9777172207832336,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.0202,
+      "step": 34
+    },
+    {
+      "epoch": 0.011170955515659286,
+      "grad_norm": 1.0507439374923706,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0252,
+      "step": 35
+    },
+    {
+      "epoch": 0.011490125673249552,
+      "grad_norm": 0.8614091277122498,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.0152,
+      "step": 36
+    },
+    {
+      "epoch": 0.011809295830839816,
+      "grad_norm": 0.41616290807724,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.005,
+      "step": 37
+    },
+    {
+      "epoch": 0.012128465988430082,
+      "grad_norm": 1.297167420387268,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.0125,
+      "step": 38
+    },
+    {
+      "epoch": 0.012447636146020347,
+      "grad_norm": 1.1140822172164917,
+      "learning_rate": 5e-05,
+      "loss": 0.0137,
+      "step": 39
+    },
+    {
+      "epoch": 0.012766806303610613,
+      "grad_norm": 1.8954771757125854,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.0162,
+      "step": 40
+    },
+    {
+      "epoch": 0.013085976461200877,
+      "grad_norm": 1.8588792085647583,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.0407,
+      "step": 41
+    },
+    {
+      "epoch": 0.013405146618791143,
+      "grad_norm": 1.1832501888275146,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0177,
+      "step": 42
+    },
+    {
+      "epoch": 0.013724316776381409,
+      "grad_norm": 0.1914079785346985,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.002,
+      "step": 43
+    },
+    {
+      "epoch": 0.014043486933971673,
+      "grad_norm": 0.8026562333106995,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.006,
+      "step": 44
+    },
+    {
+      "epoch": 0.01436265709156194,
+      "grad_norm": 0.1954847127199173,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0016,
+      "step": 45
+    },
+    {
+      "epoch": 0.014681827249152204,
+      "grad_norm": 0.0970122441649437,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.0009,
+      "step": 46
+    },
+    {
+      "epoch": 0.01500099740674247,
+      "grad_norm": 2.05657696723938,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0471,
+      "step": 47
+    },
+    {
+      "epoch": 0.015320167564332734,
+      "grad_norm": 0.10873958468437195,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0012,
+      "step": 48
+    },
+    {
+      "epoch": 0.015639337721923,
+      "grad_norm": 2.274010419845581,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.0141,
+      "step": 49
+    },
+    {
+      "epoch": 0.015958507879513265,
+      "grad_norm": 0.029483182355761528,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.0006,
+      "step": 50
+    },
+    {
+      "epoch": 0.015958507879513265,
+      "eval_loss": 0.030417734757065773,
+      "eval_runtime": 286.7279,
+      "eval_samples_per_second": 36.808,
+      "eval_steps_per_second": 4.604,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.492020904329216e+17,
+  "total_flos": 2.984041808658432e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null