Training in progress, step 75, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2880a860a8a9a8a83cb675582b84bc00e59d8bcecb7238684a1922055bc45222
+oid sha256:8c6ad1120358e3c5604b58973b91bea18507f0208c706c0423cb2ed7072eab44
 size 389352298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:046804697d0eafa330e3396617725dfb4a16483375a565a71f7a654c9fd8cfee
+oid sha256:485c8ff181ca5b08119a0a161260da7716165cd17d4acaccca9fa88bc1cd415d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08592910848549946,
+  "epoch": 0.1288936627282492,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 7.696,
       "eval_steps_per_second": 3.848,
       "step": 50
+    },
+    {
+      "epoch": 0.08764769065520946,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.08936627282491943,
+      "grad_norm": NaN,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.09108485499462943,
+      "grad_norm": NaN,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.09280343716433942,
+      "grad_norm": NaN,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.09452201933404941,
+      "grad_norm": NaN,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.0962406015037594,
+      "grad_norm": NaN,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.09795918367346938,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.09967776584317938,
+      "grad_norm": NaN,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.10139634801288937,
+      "grad_norm": NaN,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.10311493018259936,
+      "grad_norm": NaN,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.10483351235230934,
+      "grad_norm": NaN,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.10655209452201933,
+      "grad_norm": NaN,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.10827067669172932,
+      "grad_norm": NaN,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.10998925886143932,
+      "grad_norm": NaN,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.11170784103114931,
+      "grad_norm": NaN,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.11342642320085929,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.11514500537056928,
+      "grad_norm": NaN,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.11686358754027927,
+      "grad_norm": NaN,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.11858216970998926,
+      "grad_norm": NaN,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.12030075187969924,
+      "grad_norm": NaN,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.12201933404940923,
+      "grad_norm": NaN,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.12373791621911923,
+      "grad_norm": NaN,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.12545649838882922,
+      "grad_norm": NaN,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.1271750805585392,
+      "grad_norm": NaN,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.1288936627282492,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.1288936627282492,
+      "eval_loss": NaN,
+      "eval_runtime": 63.6652,
+      "eval_samples_per_second": 7.697,
+      "eval_steps_per_second": 3.848,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.81874442223616e+16,
+  "total_flos": 4.22811663335424e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null