Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:568754026574ce90d36a0f8cbd351a43364c1685abb143b7528937a03bc25ab8
+oid sha256:f426b0494820fe7c4e3846c8d736186b42e9fb6aa8767ceade086ac571743760
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bf241f5231f2fc977b7400c083f7763d747483945b80e23f074f013551821d3
+oid sha256:bb1011b2a4c32f863edb40e28e651f582f2c16f5365504b2a43e42389839eb50
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4132ae1b4a033f8644b59f8a23837ea26bb7e9719a3bfb3f318121b42a8e381
+oid sha256:3682b8eea806d5bf68e4d42abb8d07090a7034f42dbb560fe9267880cf5e1882
 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": 0.02955519432540269,
+  "epoch": 0.05911038865080538,
   "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": 63.694,
       "eval_steps_per_second": 31.892,
       "step": 25
+    },
+    {
+      "epoch": 0.030737402098418798,
+      "grad_norm": 0.5218274593353271,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 10.3256,
+      "step": 26
+    },
+    {
+      "epoch": 0.031919609871434905,
+      "grad_norm": 0.4940618574619293,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.3235,
+      "step": 27
+    },
+    {
+      "epoch": 0.03310181764445101,
+      "grad_norm": 0.5238776206970215,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 10.3201,
+      "step": 28
+    },
+    {
+      "epoch": 0.03428402541746712,
+      "grad_norm": 0.5208531618118286,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 10.3259,
+      "step": 29
+    },
+    {
+      "epoch": 0.035466233190483226,
+      "grad_norm": 0.4884912371635437,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 10.322,
+      "step": 30
+    },
+    {
+      "epoch": 0.03664844096349933,
+      "grad_norm": 0.502714991569519,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.3168,
+      "step": 31
+    },
+    {
+      "epoch": 0.03783064873651544,
+      "grad_norm": 0.4994688928127289,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 10.3133,
+      "step": 32
+    },
+    {
+      "epoch": 0.03901285650953155,
+      "grad_norm": 0.48997777700424194,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 10.3152,
+      "step": 33
+    },
+    {
+      "epoch": 0.040195064282547655,
+      "grad_norm": 0.47123217582702637,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 10.3165,
+      "step": 34
+    },
+    {
+      "epoch": 0.04137727205556377,
+      "grad_norm": 0.4655868113040924,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 10.3137,
+      "step": 35
+    },
+    {
+      "epoch": 0.042559479828579876,
+      "grad_norm": 0.47290700674057007,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 10.3092,
+      "step": 36
+    },
+    {
+      "epoch": 0.04374168760159598,
+      "grad_norm": 0.45041579008102417,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 10.313,
+      "step": 37
+    },
+    {
+      "epoch": 0.04492389537461209,
+      "grad_norm": 0.4488605260848999,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 10.3097,
+      "step": 38
+    },
+    {
+      "epoch": 0.0461061031476282,
+      "grad_norm": 0.4443797469139099,
+      "learning_rate": 5e-05,
+      "loss": 10.3127,
+      "step": 39
+    },
+    {
+      "epoch": 0.047288310920644304,
+      "grad_norm": 0.43257617950439453,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 10.3075,
+      "step": 40
+    },
+    {
+      "epoch": 0.04847051869366041,
+      "grad_norm": 0.4261913001537323,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 10.3078,
+      "step": 41
+    },
+    {
+      "epoch": 0.04965272646667652,
+      "grad_norm": 0.4139930307865143,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3092,
+      "step": 42
+    },
+    {
+      "epoch": 0.050834934239692625,
+      "grad_norm": 0.4107111692428589,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.3064,
+      "step": 43
+    },
+    {
+      "epoch": 0.05201714201270873,
+      "grad_norm": 0.4274075925350189,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 10.3095,
+      "step": 44
+    },
+    {
+      "epoch": 0.05319934978572484,
+      "grad_norm": 0.36746472120285034,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3076,
+      "step": 45
+    },
+    {
+      "epoch": 0.054381557558740946,
+      "grad_norm": 0.3831612765789032,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 10.305,
+      "step": 46
+    },
+    {
+      "epoch": 0.05556376533175705,
+      "grad_norm": 0.39060816168785095,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.3008,
+      "step": 47
+    },
+    {
+      "epoch": 0.05674597310477316,
+      "grad_norm": 0.36450064182281494,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.306,
+      "step": 48
+    },
+    {
+      "epoch": 0.057928180877789275,
+      "grad_norm": 0.37881675362586975,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 10.3028,
+      "step": 49
+    },
+    {
+      "epoch": 0.05911038865080538,
+      "grad_norm": 0.34583741426467896,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 10.3086,
+      "step": 50
+    },
+    {
+      "epoch": 0.05911038865080538,
+      "eval_loss": 10.30260944366455,
+      "eval_runtime": 11.0633,
+      "eval_samples_per_second": 64.448,
+      "eval_steps_per_second": 32.269,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5346007449600.0,
+  "total_flos": 10692014899200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null