Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:973b317c499569fc3a634a5daf57f900be93f95a3b9ea7a2715567fa25ceb740
+oid sha256:cbf5d94cce3b45e1ab7b2c8dbea2246c8742fab79f1a17b5c626d10dd266cb45
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be5c5d51a63e0cb37ff1ba25afb3da4b225954ece5f1bb97b0727c600738227e
+oid sha256:80bf3fc1413a7f1d4712f24107188644eeaa65cc0ab1cc9369b6470db8e00a2d
 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": 0.024366471734892786,
+  "epoch": 0.04873294346978557,
   "eval_steps": 4,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -238,6 +238,229 @@
       "learning_rate": 6.91341716182545e-05,
       "loss": 0.0,
       "step": 25
+    },
+    {
+      "epoch": 0.025341130604288498,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": NaN,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.02729044834307992,
+      "grad_norm": NaN,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.02729044834307992,
+      "eval_loss": NaN,
+      "eval_runtime": 573.2103,
+      "eval_samples_per_second": 2.263,
+      "eval_steps_per_second": 0.567,
+      "step": 28
+    },
+    {
+      "epoch": 0.028265107212475632,
+      "grad_norm": NaN,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.029239766081871343,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.030214424951267055,
+      "grad_norm": NaN,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.031189083820662766,
+      "grad_norm": NaN,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.031189083820662766,
+      "eval_loss": NaN,
+      "eval_runtime": 572.9542,
+      "eval_samples_per_second": 2.264,
+      "eval_steps_per_second": 0.567,
+      "step": 32
+    },
+    {
+      "epoch": 0.03216374269005848,
+      "grad_norm": NaN,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.03313840155945419,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.0341130604288499,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.03508771929824561,
+      "grad_norm": NaN,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.03508771929824561,
+      "eval_loss": NaN,
+      "eval_runtime": 572.9072,
+      "eval_samples_per_second": 2.264,
+      "eval_steps_per_second": 0.567,
+      "step": 36
+    },
+    {
+      "epoch": 0.036062378167641324,
+      "grad_norm": NaN,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.037037037037037035,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.038011695906432746,
+      "grad_norm": NaN,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.03898635477582846,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.03898635477582846,
+      "eval_loss": NaN,
+      "eval_runtime": 572.7858,
+      "eval_samples_per_second": 2.264,
+      "eval_steps_per_second": 0.567,
+      "step": 40
+    },
+    {
+      "epoch": 0.03996101364522417,
+      "grad_norm": NaN,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.04093567251461988,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.04191033138401559,
+      "grad_norm": NaN,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.042884990253411304,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.042884990253411304,
+      "eval_loss": NaN,
+      "eval_runtime": 573.1049,
+      "eval_samples_per_second": 2.263,
+      "eval_steps_per_second": 0.567,
+      "step": 44
+    },
+    {
+      "epoch": 0.043859649122807015,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.04483430799220273,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.04580896686159844,
+      "grad_norm": NaN,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.04678362573099415,
+      "grad_norm": NaN,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.04678362573099415,
+      "eval_loss": NaN,
+      "eval_runtime": 572.8438,
+      "eval_samples_per_second": 2.264,
+      "eval_steps_per_second": 0.567,
+      "step": 48
+    },
+    {
+      "epoch": 0.04775828460038986,
+      "grad_norm": NaN,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.04873294346978557,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -252,12 +475,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.86091809144832e+16,
+  "total_flos": 1.972183618289664e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null