Training in progress, step 75, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e91c0292a7b218673a4e653f0c4c3fdef2df69978a29536b9b8daf2f57c2d2
+oid sha256:096cfba531387f71314995b8010660c3e68db2c55e85f309800d875b9500ad14
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddb74d0aebd163de2638af63f54646bf43755b394f9ad316a8887160f29e36ba
+oid sha256:2c7f198cc6c8f8f5472018d8873e54f6d94d5526d60f0b6d8bea53f2a9274a41
 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": 0.0018123904070175756,
+  "epoch": 0.0027185856105263633,
   "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": 4.592,
       "eval_steps_per_second": 2.296,
       "step": 50
+    },
+    {
+      "epoch": 0.0018486382151579272,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.0018848860232982788,
+      "grad_norm": NaN,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.0019211338314386302,
+      "grad_norm": NaN,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.0019573816395789816,
+      "grad_norm": NaN,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.001993629447719333,
+      "grad_norm": NaN,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.002029877255859685,
+      "grad_norm": NaN,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.0020661250640000364,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.0021023728721403876,
+      "grad_norm": NaN,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.0021386206802807392,
+      "grad_norm": NaN,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.002174868488421091,
+      "grad_norm": NaN,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.0022111162965614425,
+      "grad_norm": NaN,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.0022473641047017936,
+      "grad_norm": NaN,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.0022836119128421453,
+      "grad_norm": NaN,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.002319859720982497,
+      "grad_norm": NaN,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.0023561075291228485,
+      "grad_norm": NaN,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.0023923553372631997,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.0024286031454035513,
+      "grad_norm": NaN,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.002464850953543903,
+      "grad_norm": NaN,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.0025010987616842545,
+      "grad_norm": NaN,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.002537346569824606,
+      "grad_norm": NaN,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.0025735943779649573,
+      "grad_norm": NaN,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.002609842186105309,
+      "grad_norm": NaN,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.0026460899942456605,
+      "grad_norm": NaN,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.002682337802386012,
+      "grad_norm": NaN,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.0027185856105263633,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.0027185856105263633,
+      "eval_loss": NaN,
+      "eval_runtime": 5062.3485,
+      "eval_samples_per_second": 4.589,
+      "eval_steps_per_second": 2.295,
+      "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": 6.616329524084736e+16,
+  "total_flos": 9.899989361963827e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null