Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9443cd312403bd6cee6454d772721cef1f1c00c7329593f6cbf2bffaac7d46da
+oid sha256:ef1e0c2d4d0e4c8f5744dd8107a834c14bfcc16504b5f0b49f329d9010f786ce
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27df454959078a16d81e98cdba31298cedee4983a27c893750c7c31c6fbb6ee7
+oid sha256:15c4a5fcad2aabea14041f5e2313de084470e56a4fd1bdb0cfcda3d85b013644
 size 313998650

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0be8316416cbabc3eab3bdab30f2fd93ceee720eb73ace3a6c8a77b1ea2b7c3
+oid sha256:00fccdd1cc68d38e5b4f4fdcf2197a99508e0c8651b6b1f96069edf35d9c190c
 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": 0.041911148365465216,
+  "epoch": 0.08382229673093043,
   "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": 19.503,
       "eval_steps_per_second": 9.771,
       "step": 25
+    },
+    {
+      "epoch": 0.04358759430008382,
+      "grad_norm": 10.980728149414062,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.2975,
+      "step": 26
+    },
+    {
+      "epoch": 0.04526404023470243,
+      "grad_norm": 8.236481666564941,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.2102,
+      "step": 27
+    },
+    {
+      "epoch": 0.04694048616932104,
+      "grad_norm": 7.4617767333984375,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.2197,
+      "step": 28
+    },
+    {
+      "epoch": 0.04861693210393965,
+      "grad_norm": 10.079323768615723,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.3974,
+      "step": 29
+    },
+    {
+      "epoch": 0.050293378038558254,
+      "grad_norm": 6.351953983306885,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.242,
+      "step": 30
+    },
+    {
+      "epoch": 0.051969823973176864,
+      "grad_norm": 8.568976402282715,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.2159,
+      "step": 31
+    },
+    {
+      "epoch": 0.053646269907795474,
+      "grad_norm": 3.9171841144561768,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.1036,
+      "step": 32
+    },
+    {
+      "epoch": 0.055322715842414084,
+      "grad_norm": 1.558870553970337,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.0284,
+      "step": 33
+    },
+    {
+      "epoch": 0.05699916177703269,
+      "grad_norm": 2.970895767211914,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.0734,
+      "step": 34
+    },
+    {
+      "epoch": 0.0586756077116513,
+      "grad_norm": 5.282650470733643,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0669,
+      "step": 35
+    },
+    {
+      "epoch": 0.06035205364626991,
+      "grad_norm": 4.935418605804443,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.1214,
+      "step": 36
+    },
+    {
+      "epoch": 0.06202849958088852,
+      "grad_norm": 4.224859714508057,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.1697,
+      "step": 37
+    },
+    {
+      "epoch": 0.06370494551550712,
+      "grad_norm": 8.419668197631836,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.245,
+      "step": 38
+    },
+    {
+      "epoch": 0.06538139145012574,
+      "grad_norm": 4.401646137237549,
+      "learning_rate": 5e-05,
+      "loss": 0.0996,
+      "step": 39
+    },
+    {
+      "epoch": 0.06705783738474434,
+      "grad_norm": 1.9046088457107544,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.0401,
+      "step": 40
+    },
+    {
+      "epoch": 0.06873428331936295,
+      "grad_norm": 7.665452003479004,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.1484,
+      "step": 41
+    },
+    {
+      "epoch": 0.07041072925398156,
+      "grad_norm": 3.5041327476501465,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0514,
+      "step": 42
+    },
+    {
+      "epoch": 0.07208717518860017,
+      "grad_norm": 8.407772064208984,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.1707,
+      "step": 43
+    },
+    {
+      "epoch": 0.07376362112321877,
+      "grad_norm": 8.42634105682373,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.0916,
+      "step": 44
+    },
+    {
+      "epoch": 0.07544006705783739,
+      "grad_norm": 4.17021369934082,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0612,
+      "step": 45
+    },
+    {
+      "epoch": 0.07711651299245599,
+      "grad_norm": 9.347469329833984,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.2845,
+      "step": 46
+    },
+    {
+      "epoch": 0.07879295892707461,
+      "grad_norm": 8.287640571594238,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.1242,
+      "step": 47
+    },
+    {
+      "epoch": 0.08046940486169321,
+      "grad_norm": 9.394111633300781,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0785,
+      "step": 48
+    },
+    {
+      "epoch": 0.08214585079631181,
+      "grad_norm": 2.0844478607177734,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.0241,
+      "step": 49
+    },
+    {
+      "epoch": 0.08382229673093043,
+      "grad_norm": 3.97900128364563,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.187,
+      "step": 50
+    },
+    {
+      "epoch": 0.08382229673093043,
+      "eval_loss": 0.13281704485416412,
+      "eval_runtime": 25.9404,
+      "eval_samples_per_second": 19.391,
+      "eval_steps_per_second": 9.715,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9934148626022400.0,
+  "total_flos": 1.98682972520448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null