Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6404ec9b70cbd50657e9e21b373ec0536680a0fc4dc5a47eea0fb01a20f0cb77
+oid sha256:44ad15e64db001e1a1f2c3056046232d62594514e98766859f1e00c65346e429
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fdabda8d5485c694cb6287c50dd3f9b2aa7f28cf6e5bf7cf8f56e1086ef88d3
+oid sha256:633a9737c4ab3dd787211a3bbea56f9f4645571126fe5926f072bc2d33c9f275
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18e8f087554efef961013d2e8937b5a79d0403657e07d679f4e18d12e80c3b05
+oid sha256:ac5f70442b6e4fba1c726ef7a3d9603c39539e88c7ff2a6e3c8918cc4259c51a
 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": 0.023820867079561697,
+  "epoch": 0.04764173415912339,
   "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": 4.653,
       "eval_steps_per_second": 2.327,
       "step": 25
+    },
+    {
+      "epoch": 0.024773701762744165,
+      "grad_norm": 1.4650429487228394,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 2.453,
+      "step": 26
+    },
+    {
+      "epoch": 0.02572653644592663,
+      "grad_norm": 1.5379657745361328,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.4569,
+      "step": 27
+    },
+    {
+      "epoch": 0.0266793711291091,
+      "grad_norm": 1.4416159391403198,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 2.0689,
+      "step": 28
+    },
+    {
+      "epoch": 0.027632205812291567,
+      "grad_norm": 1.9543250799179077,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 2.7355,
+      "step": 29
+    },
+    {
+      "epoch": 0.028585040495474036,
+      "grad_norm": 4.280240058898926,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.3589,
+      "step": 30
+    },
+    {
+      "epoch": 0.029537875178656504,
+      "grad_norm": 2.5730347633361816,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.5142,
+      "step": 31
+    },
+    {
+      "epoch": 0.03049070986183897,
+      "grad_norm": 1.9060622453689575,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 2.4468,
+      "step": 32
+    },
+    {
+      "epoch": 0.03144354454502144,
+      "grad_norm": 2.6304562091827393,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 2.5699,
+      "step": 33
+    },
+    {
+      "epoch": 0.03239637922820391,
+      "grad_norm": 2.1982674598693848,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 2.5823,
+      "step": 34
+    },
+    {
+      "epoch": 0.03334921391138637,
+      "grad_norm": 1.9779804944992065,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 2.0681,
+      "step": 35
+    },
+    {
+      "epoch": 0.03430204859456884,
+      "grad_norm": 2.2652299404144287,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 2.5656,
+      "step": 36
+    },
+    {
+      "epoch": 0.03525488327775131,
+      "grad_norm": 2.288848400115967,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 2.442,
+      "step": 37
+    },
+    {
+      "epoch": 0.03620771796093378,
+      "grad_norm": 2.1887640953063965,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 2.4672,
+      "step": 38
+    },
+    {
+      "epoch": 0.037160552644116246,
+      "grad_norm": 2.69694185256958,
+      "learning_rate": 5e-05,
+      "loss": 2.8142,
+      "step": 39
+    },
+    {
+      "epoch": 0.038113387327298714,
+      "grad_norm": 2.768056869506836,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 2.7236,
+      "step": 40
+    },
+    {
+      "epoch": 0.03906622201048118,
+      "grad_norm": 4.088725566864014,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 2.5499,
+      "step": 41
+    },
+    {
+      "epoch": 0.04001905669366365,
+      "grad_norm": 3.419790744781494,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.9799,
+      "step": 42
+    },
+    {
+      "epoch": 0.04097189137684612,
+      "grad_norm": 6.255226135253906,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.883,
+      "step": 43
+    },
+    {
+      "epoch": 0.04192472606002858,
+      "grad_norm": 0.0,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.04287756074321105,
+      "grad_norm": 0.0,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.04383039542639352,
+      "grad_norm": 0.0,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.04478323010957599,
+      "grad_norm": 0.0,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.045736064792758456,
+      "grad_norm": 8.734387397766113,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.4118,
+      "step": 48
+    },
+    {
+      "epoch": 0.046688899475940925,
+      "grad_norm": 3.778465509414673,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 2.7381,
+      "step": 49
+    },
+    {
+      "epoch": 0.04764173415912339,
+      "grad_norm": 2.9656107425689697,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 2.6656,
+      "step": 50
+    },
+    {
+      "epoch": 0.04764173415912339,
+      "eval_loss": NaN,
+      "eval_runtime": 190.1935,
+      "eval_samples_per_second": 4.648,
+      "eval_steps_per_second": 2.324,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.46010452164608e+16,
+  "total_flos": 1.3782543103741133e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null