Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:410721344149590e3dbef766b359b19f084bcbbb5a45ca2ad0af4e0f2fdd2d0b
+oid sha256:232eb6e26b9220a64dee770e820589de447f302022658509e1452c6fbb83162f
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:366ebacae284a6d823c9968467be5b71c3dee311f37ba7150c59d87f75195881
+oid sha256:fb47a58ee93b9adbc4730dd1ab4ad5160feafa440132993984b7d38f1b184591
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.018105849582172703,
+  "epoch": 0.02321262766945218,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 77.007,
       "eval_steps_per_second": 38.546,
       "step": 39
+    },
+    {
+      "epoch": 0.018570102135561744,
+      "grad_norm": NaN,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.01903435468895079,
+      "grad_norm": NaN,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.019498607242339833,
+      "grad_norm": NaN,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.019962859795728878,
+      "grad_norm": NaN,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 1.0726,
+      "step": 43
+    },
+    {
+      "epoch": 0.02042711234911792,
+      "grad_norm": NaN,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.020891364902506964,
+      "grad_norm": NaN,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.02135561745589601,
+      "grad_norm": NaN,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.02181987000928505,
+      "grad_norm": NaN,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.022284122562674095,
+      "grad_norm": NaN,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.02274837511606314,
+      "grad_norm": NaN,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.02321262766945218,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 950154785980416.0,
+  "total_flos": 1214754852962304.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null