Training in progress, step 100, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf89c1b940b623fcdbcb83b7136878229f26e9586367c4ee64255df5455db34
+oid sha256:5d10e39ec38647d94aec21b8f23c5f0f70a12a986aca178ddc2f4d9f85ebe37f
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408e56684290fc2d4d62af6818d9eed799690d481ec8a8ead29730102632763f
+oid sha256:faac1656e758e8dc521d5b3ce272931901186027e782eb031f8a28a6467d6ac1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5535055350553506,
+  "epoch": 0.7380073800738007,
   "eval_steps": 9,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,205 @@
       "learning_rate": 1.7860619515673033e-05,
       "loss": 0.0,
       "step": 75
+    },
+    {
+      "epoch": 0.5608856088560885,
+      "grad_norm": NaN,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0,
+      "step": 76
+    },
+    {
+      "epoch": 0.5682656826568265,
+      "grad_norm": NaN,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0,
+      "step": 77
+    },
+    {
+      "epoch": 0.5756457564575646,
+      "grad_norm": NaN,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.5830258302583026,
+      "grad_norm": NaN,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0,
+      "step": 79
+    },
+    {
+      "epoch": 0.5904059040590406,
+      "grad_norm": NaN,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.5977859778597786,
+      "grad_norm": NaN,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.5977859778597786,
+      "eval_loss": NaN,
+      "eval_runtime": 11.2994,
+      "eval_samples_per_second": 10.089,
+      "eval_steps_per_second": 1.328,
+      "step": 81
+    },
+    {
+      "epoch": 0.6051660516605166,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 82
+    },
+    {
+      "epoch": 0.6125461254612546,
+      "grad_norm": NaN,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0,
+      "step": 83
+    },
+    {
+      "epoch": 0.6199261992619927,
+      "grad_norm": NaN,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.6273062730627307,
+      "grad_norm": NaN,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.6346863468634686,
+      "grad_norm": NaN,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0,
+      "step": 86
+    },
+    {
+      "epoch": 0.6420664206642066,
+      "grad_norm": NaN,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.6494464944649446,
+      "grad_norm": NaN,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0,
+      "step": 88
+    },
+    {
+      "epoch": 0.6568265682656826,
+      "grad_norm": NaN,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.6642066420664207,
+      "grad_norm": NaN,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.6642066420664207,
+      "eval_loss": NaN,
+      "eval_runtime": 11.2902,
+      "eval_samples_per_second": 10.097,
+      "eval_steps_per_second": 1.329,
+      "step": 90
+    },
+    {
+      "epoch": 0.6715867158671587,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.6789667896678967,
+      "grad_norm": NaN,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0,
+      "step": 92
+    },
+    {
+      "epoch": 0.6863468634686347,
+      "grad_norm": NaN,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.6937269372693727,
+      "grad_norm": NaN,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0,
+      "step": 94
+    },
+    {
+      "epoch": 0.7011070110701108,
+      "grad_norm": NaN,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.7084870848708487,
+      "grad_norm": NaN,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.7158671586715867,
+      "grad_norm": NaN,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0,
+      "step": 97
+    },
+    {
+      "epoch": 0.7232472324723247,
+      "grad_norm": NaN,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0,
+      "step": 98
+    },
+    {
+      "epoch": 0.7306273062730627,
+      "grad_norm": NaN,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.7306273062730627,
+      "eval_loss": NaN,
+      "eval_runtime": 11.2895,
+      "eval_samples_per_second": 10.098,
+      "eval_steps_per_second": 1.329,
+      "step": 99
+    },
+    {
+      "epoch": 0.7380073800738007,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -618,12 +817,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.90098483265536e+16,
+  "total_flos": 6.53464644354048e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null