Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45a70cdf51aeee0d766b3b03e1524e8f498f476968b059507ed321a0f7700bab
+oid sha256:0a3951f5840f31a861a33d68471f23dfb88a87a21c43033fdcd2244da312f0cb
 size 144985666

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ceaa0ce3aacbb4bd4c5b17de2cb7f2963770c234a2f2a775d3b761fd64b67ff
+oid sha256:042e47f179f7e1927208bdf7d6f0265118f04766e96bfb269ebb1ddbf810e28c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008151287903488751,
+  "epoch": 0.016302575806977502,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,221 @@
       "eval_samples_per_second": 14.405,
       "eval_steps_per_second": 1.801,
       "step": 25
+    },
+    {
+      "epoch": 0.008477339419628301,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.008803390935767852,
+      "grad_norm": NaN,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.009129442451907402,
+      "grad_norm": NaN,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.009455493968046952,
+      "grad_norm": NaN,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.0097815454841865,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0097815454841865,
+      "eval_loss": NaN,
+      "eval_runtime": 179.2782,
+      "eval_samples_per_second": 14.408,
+      "eval_steps_per_second": 1.802,
+      "step": 30
+    },
+    {
+      "epoch": 0.010107597000326051,
+      "grad_norm": NaN,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.010433648516465601,
+      "grad_norm": NaN,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.010759700032605152,
+      "grad_norm": NaN,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.011085751548744702,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.011411803064884252,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.011411803064884252,
+      "eval_loss": NaN,
+      "eval_runtime": 179.3952,
+      "eval_samples_per_second": 14.398,
+      "eval_steps_per_second": 1.8,
+      "step": 35
+    },
+    {
+      "epoch": 0.011737854581023801,
+      "grad_norm": NaN,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.012063906097163351,
+      "grad_norm": NaN,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.012389957613302902,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.012716009129442452,
+      "grad_norm": NaN,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.013042060645582002,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.013042060645582002,
+      "eval_loss": NaN,
+      "eval_runtime": 179.2959,
+      "eval_samples_per_second": 14.406,
+      "eval_steps_per_second": 1.801,
+      "step": 40
+    },
+    {
+      "epoch": 0.013368112161721553,
+      "grad_norm": NaN,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.013694163677861103,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.014020215194000651,
+      "grad_norm": NaN,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.014346266710140202,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.014672318226279752,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.014672318226279752,
+      "eval_loss": NaN,
+      "eval_runtime": 179.3378,
+      "eval_samples_per_second": 14.403,
+      "eval_steps_per_second": 1.801,
+      "step": 45
+    },
+    {
+      "epoch": 0.014998369742419302,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.015324421258558853,
+      "grad_norm": NaN,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.0156504727746984,
+      "grad_norm": NaN,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.015976524290837953,
+      "grad_norm": NaN,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.016302575806977502,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.016302575806977502,
+      "eval_loss": NaN,
+      "eval_runtime": 179.2331,
+      "eval_samples_per_second": 14.411,
+      "eval_steps_per_second": 1.802,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -244,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6404706234531840.0,
+  "total_flos": 1.2729353641132032e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null