Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d93fa27471e7db3dd77b5dca46152b3487dd03aa0d14ace2d6f399b7a221777
+oid sha256:9aecab4f272140ec8fdad7a220fd8b4d304014e7982eeb0051bdaf9e2d613213
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98dba1aa2a4f9fa7903bbc584a97a93e96110ab8dfa437edf844ff85b9490681
+oid sha256:a4e8bd30af80d1463679537e237f509f9d9d3d4b822979217e028dc7c9bbf3e7
 size 157104826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2d935ae5b025dfbff004bc579868ff2ea858dae72a4e1d8ad957d608afdd06d
+oid sha256:cd4b1b81f4a3e9a9201480c036410a11ecf8e3912d634679b6b7af0f1279bd91
 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": 0.01531745423910546,
+  "epoch": 0.03063490847821092,
   "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": 19.674,
       "eval_steps_per_second": 9.844,
       "step": 25
+    },
+    {
+      "epoch": 0.015930152408669677,
+      "grad_norm": 4.93162202835083,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 1.8622,
+      "step": 26
+    },
+    {
+      "epoch": 0.016542850578233896,
+      "grad_norm": 4.746114730834961,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.6622,
+      "step": 27
+    },
+    {
+      "epoch": 0.017155548747798115,
+      "grad_norm": 4.882776260375977,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 1.8984,
+      "step": 28
+    },
+    {
+      "epoch": 0.017768246917362333,
+      "grad_norm": 3.9814393520355225,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 1.3697,
+      "step": 29
+    },
+    {
+      "epoch": 0.018380945086926552,
+      "grad_norm": 7.2121992111206055,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.1676,
+      "step": 30
+    },
+    {
+      "epoch": 0.01899364325649077,
+      "grad_norm": 5.58474588394165,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.6876,
+      "step": 31
+    },
+    {
+      "epoch": 0.01960634142605499,
+      "grad_norm": 4.772983551025391,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 1.7231,
+      "step": 32
+    },
+    {
+      "epoch": 0.020219039595619208,
+      "grad_norm": 3.946286678314209,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 1.2223,
+      "step": 33
+    },
+    {
+      "epoch": 0.020831737765183427,
+      "grad_norm": 4.936631679534912,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 1.6819,
+      "step": 34
+    },
+    {
+      "epoch": 0.021444435934747645,
+      "grad_norm": 4.5297956466674805,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.824,
+      "step": 35
+    },
+    {
+      "epoch": 0.022057134104311864,
+      "grad_norm": 5.4143524169921875,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 2.5458,
+      "step": 36
+    },
+    {
+      "epoch": 0.022669832273876082,
+      "grad_norm": 4.592708110809326,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 1.6016,
+      "step": 37
+    },
+    {
+      "epoch": 0.0232825304434403,
+      "grad_norm": 5.789618492126465,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 2.0341,
+      "step": 38
+    },
+    {
+      "epoch": 0.02389522861300452,
+      "grad_norm": 6.866486549377441,
+      "learning_rate": 5e-05,
+      "loss": 1.9014,
+      "step": 39
+    },
+    {
+      "epoch": 0.02450792678256874,
+      "grad_norm": 3.9232795238494873,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 1.5297,
+      "step": 40
+    },
+    {
+      "epoch": 0.025120624952132957,
+      "grad_norm": 5.109820365905762,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 1.4501,
+      "step": 41
+    },
+    {
+      "epoch": 0.025733323121697176,
+      "grad_norm": 4.550601959228516,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.8131,
+      "step": 42
+    },
+    {
+      "epoch": 0.02634602129126139,
+      "grad_norm": 4.237565994262695,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.4321,
+      "step": 43
+    },
+    {
+      "epoch": 0.02695871946082561,
+      "grad_norm": 4.74612283706665,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 1.7617,
+      "step": 44
+    },
+    {
+      "epoch": 0.027571417630389828,
+      "grad_norm": 4.633487224578857,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.5634,
+      "step": 45
+    },
+    {
+      "epoch": 0.028184115799954047,
+      "grad_norm": 5.383734703063965,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 1.2762,
+      "step": 46
+    },
+    {
+      "epoch": 0.028796813969518265,
+      "grad_norm": 4.597635746002197,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.6126,
+      "step": 47
+    },
+    {
+      "epoch": 0.029409512139082484,
+      "grad_norm": 5.0467939376831055,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.8275,
+      "step": 48
+    },
+    {
+      "epoch": 0.030022210308646703,
+      "grad_norm": 4.837862968444824,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 1.354,
+      "step": 49
+    },
+    {
+      "epoch": 0.03063490847821092,
+      "grad_norm": 5.544301509857178,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 2.0362,
+      "step": 50
+    },
+    {
+      "epoch": 0.03063490847821092,
+      "eval_loss": 1.6958106756210327,
+      "eval_runtime": 69.8654,
+      "eval_samples_per_second": 19.681,
+      "eval_steps_per_second": 9.848,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9837753453772800.0,
+  "total_flos": 1.96755069075456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null