Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94d030682298f0c7920bc0539dc26b725522de512a46022b1cfd864e8183da8b
+oid sha256:2880a860a8a9a8a83cb675582b84bc00e59d8bcecb7238684a1922055bc45222
 size 389352298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae293c02ba3fb5a300883da5091c5c217ded2630da707c5de22f52ea7a82b7f7
+oid sha256:046804697d0eafa330e3396617725dfb4a16483375a565a71f7a654c9fd8cfee
 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": 0.04296455424274973,
+  "epoch": 0.08592910848549946,
   "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": 7.697,
       "eval_steps_per_second": 3.849,
       "step": 25
+    },
+    {
+      "epoch": 0.04468313641245972,
+      "grad_norm": NaN,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.04640171858216971,
+      "grad_norm": NaN,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0481203007518797,
+      "grad_norm": NaN,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.04983888292158969,
+      "grad_norm": NaN,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.05155746509129968,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.053276047261009665,
+      "grad_norm": NaN,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.05499462943071966,
+      "grad_norm": NaN,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.05671321160042964,
+      "grad_norm": NaN,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.058431793770139635,
+      "grad_norm": NaN,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.06015037593984962,
+      "grad_norm": NaN,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.06186895810955961,
+      "grad_norm": NaN,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.0635875402792696,
+      "grad_norm": NaN,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.0653061224489796,
+      "grad_norm": NaN,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.06702470461868958,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.06874328678839957,
+      "grad_norm": NaN,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07046186895810956,
+      "grad_norm": NaN,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.07218045112781955,
+      "grad_norm": NaN,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.07389903329752953,
+      "grad_norm": NaN,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.07561761546723952,
+      "grad_norm": NaN,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.07733619763694952,
+      "grad_norm": NaN,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.07905477980665951,
+      "grad_norm": NaN,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.0807733619763695,
+      "grad_norm": NaN,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.08249194414607948,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": NaN,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.08592910848549946,
+      "grad_norm": NaN,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.08592910848549946,
+      "eval_loss": NaN,
+      "eval_runtime": 63.6685,
+      "eval_samples_per_second": 7.696,
+      "eval_steps_per_second": 3.848,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.40937221111808e+16,
+  "total_flos": 2.81874442223616e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null