Training in progress, step 112, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5696b0909841c30ce657da7fef89d416fda37a2d1d0a8e66831a5ea7676d6e4
+oid sha256:e47b82aa2abc24774e65bf3c840b73254af400c018b54a4b74076c10b7aa50f1
 size 4969539560

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a7223ea8f99f7b799b24686be78454f9f72e8d03fef9f83c56d83584086be14
+oid sha256:3948e1712d66e4846b20e1f82e841d2b592341e95b95f7284d25901e27823131
 size 1912795688

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.0,
+  "epoch": 28.0,
   "eval_steps": 16,
-  "global_step": 80,
+  "global_step": 112,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -608,6 +608,246 @@
       "eval_samples_per_second": 17.305,
       "eval_steps_per_second": 17.305,
       "step": 80
+    },
+    {
+      "epoch": 20.29090909090909,
+      "grad_norm": 9.43545913696289,
+      "learning_rate": 9.728616793536587e-08,
+      "loss": 0.726,
+      "step": 81
+    },
+    {
+      "epoch": 20.581818181818182,
+      "grad_norm": 8.36042308807373,
+      "learning_rate": 9.715024851617789e-08,
+      "loss": 0.7908,
+      "step": 82
+    },
+    {
+      "epoch": 20.87272727272727,
+      "grad_norm": 9.46149730682373,
+      "learning_rate": 9.701111919237408e-08,
+      "loss": 0.8219,
+      "step": 83
+    },
+    {
+      "epoch": 21.0,
+      "grad_norm": 9.277331352233887,
+      "learning_rate": 9.68687905591911e-08,
+      "loss": 0.7955,
+      "step": 84
+    },
+    {
+      "epoch": 21.29090909090909,
+      "grad_norm": 9.980899810791016,
+      "learning_rate": 9.672327345550542e-08,
+      "loss": 0.8459,
+      "step": 85
+    },
+    {
+      "epoch": 21.581818181818182,
+      "grad_norm": 8.734892845153809,
+      "learning_rate": 9.65745789630079e-08,
+      "loss": 0.7952,
+      "step": 86
+    },
+    {
+      "epoch": 21.87272727272727,
+      "grad_norm": 7.979213714599609,
+      "learning_rate": 9.642271840535982e-08,
+      "loss": 0.6928,
+      "step": 87
+    },
+    {
+      "epoch": 22.0,
+      "grad_norm": 9.570889472961426,
+      "learning_rate": 9.626770334733058e-08,
+      "loss": 0.7813,
+      "step": 88
+    },
+    {
+      "epoch": 22.29090909090909,
+      "grad_norm": 9.478497505187988,
+      "learning_rate": 9.610954559391703e-08,
+      "loss": 0.783,
+      "step": 89
+    },
+    {
+      "epoch": 22.581818181818182,
+      "grad_norm": 8.57199478149414,
+      "learning_rate": 9.594825718944444e-08,
+      "loss": 0.7859,
+      "step": 90
+    },
+    {
+      "epoch": 22.87272727272727,
+      "grad_norm": 8.782203674316406,
+      "learning_rate": 9.578385041664925e-08,
+      "loss": 0.7784,
+      "step": 91
+    },
+    {
+      "epoch": 23.0,
+      "grad_norm": 9.160470008850098,
+      "learning_rate": 9.561633779574373e-08,
+      "loss": 0.7613,
+      "step": 92
+    },
+    {
+      "epoch": 23.29090909090909,
+      "grad_norm": 8.80034065246582,
+      "learning_rate": 9.544573208346251e-08,
+      "loss": 0.7708,
+      "step": 93
+    },
+    {
+      "epoch": 23.581818181818182,
+      "grad_norm": 9.001204490661621,
+      "learning_rate": 9.527204627209113e-08,
+      "loss": 0.7975,
+      "step": 94
+    },
+    {
+      "epoch": 23.87272727272727,
+      "grad_norm": 8.64294147491455,
+      "learning_rate": 9.509529358847655e-08,
+      "loss": 0.7533,
+      "step": 95
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 9.539164543151855,
+      "learning_rate": 9.491548749301997e-08,
+      "loss": 0.8112,
+      "step": 96
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 0.7388671040534973,
+      "eval_runtime": 0.7379,
+      "eval_samples_per_second": 17.617,
+      "eval_steps_per_second": 17.617,
+      "step": 96
+    },
+    {
+      "epoch": 24.29090909090909,
+      "grad_norm": 8.564647674560547,
+      "learning_rate": 9.473264167865172e-08,
+      "loss": 0.779,
+      "step": 97
+    },
+    {
+      "epoch": 24.581818181818182,
+      "grad_norm": 8.466269493103027,
+      "learning_rate": 9.454677006978843e-08,
+      "loss": 0.7427,
+      "step": 98
+    },
+    {
+      "epoch": 24.87272727272727,
+      "grad_norm": 9.549156188964844,
+      "learning_rate": 9.435788682127281e-08,
+      "loss": 0.7749,
+      "step": 99
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 8.791007041931152,
+      "learning_rate": 9.416600631729548e-08,
+      "loss": 0.8413,
+      "step": 100
+    },
+    {
+      "epoch": 25.29090909090909,
+      "grad_norm": 8.481273651123047,
+      "learning_rate": 9.397114317029974e-08,
+      "loss": 0.7987,
+      "step": 101
+    },
+    {
+      "epoch": 25.581818181818182,
+      "grad_norm": 7.957334518432617,
+      "learning_rate": 9.377331221986867e-08,
+      "loss": 0.7579,
+      "step": 102
+    },
+    {
+      "epoch": 25.87272727272727,
+      "grad_norm": 7.695952415466309,
+      "learning_rate": 9.357252853159505e-08,
+      "loss": 0.7138,
+      "step": 103
+    },
+    {
+      "epoch": 26.0,
+      "grad_norm": 8.535294532775879,
+      "learning_rate": 9.336880739593415e-08,
+      "loss": 0.8143,
+      "step": 104
+    },
+    {
+      "epoch": 26.29090909090909,
+      "grad_norm": 7.785234451293945,
+      "learning_rate": 9.316216432703917e-08,
+      "loss": 0.7595,
+      "step": 105
+    },
+    {
+      "epoch": 26.581818181818182,
+      "grad_norm": 7.210692882537842,
+      "learning_rate": 9.295261506157986e-08,
+      "loss": 0.6892,
+      "step": 106
+    },
+    {
+      "epoch": 26.87272727272727,
+      "grad_norm": 7.439105033874512,
+      "learning_rate": 9.274017555754408e-08,
+      "loss": 0.7828,
+      "step": 107
+    },
+    {
+      "epoch": 27.0,
+      "grad_norm": 8.5601167678833,
+      "learning_rate": 9.252486199302256e-08,
+      "loss": 0.8267,
+      "step": 108
+    },
+    {
+      "epoch": 27.29090909090909,
+      "grad_norm": 7.751751899719238,
+      "learning_rate": 9.230669076497686e-08,
+      "loss": 0.7837,
+      "step": 109
+    },
+    {
+      "epoch": 27.581818181818182,
+      "grad_norm": 7.58750057220459,
+      "learning_rate": 9.20856784879907e-08,
+      "loss": 0.7629,
+      "step": 110
+    },
+    {
+      "epoch": 27.87272727272727,
+      "grad_norm": 7.078155040740967,
+      "learning_rate": 9.186184199300463e-08,
+      "loss": 0.732,
+      "step": 111
+    },
+    {
+      "epoch": 28.0,
+      "grad_norm": 7.075254440307617,
+      "learning_rate": 9.163519832603437e-08,
+      "loss": 0.708,
+      "step": 112
+    },
+    {
+      "epoch": 28.0,
+      "eval_loss": 0.7153984904289246,
+      "eval_runtime": 0.7384,
+      "eval_samples_per_second": 17.605,
+      "eval_steps_per_second": 17.605,
+      "step": 112
     }
   ],
   "logging_steps": 1,
@@ -627,7 +867,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.68306572017664e+16,
+  "total_flos": 3.756292008247296e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null