Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9581f7821f4e70b6ef8beb0cef1bd44196502f6b3112cab1ec0d9fd8bac0fc10
+oid sha256:403460df9e4fccfcc3b90e4b521d977cbf4b6b1144a3c27109527524806fde0c
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:005c6bb8843c16d8be143cea2828dcb4a053cd2e34b13f5ed5bbb11504b5c95c
+oid sha256:2ffe54f95c6e2293f18a1b75be9154c7981e3c6e291d7f37dcc66429c5ed61eb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040b95482c646935022d148ebc91f462fbf2195cfa3365adbbe3bd6ca1f35a74
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07507507507507508,
+  "epoch": 0.15015015015015015,
   "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": 4.514,
       "eval_steps_per_second": 2.265,
       "step": 25
+    },
+    {
+      "epoch": 0.07807807807807808,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.08108108108108109,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.08408408408408409,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.08708708708708708,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.09009009009009009,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.09009009009009009,
+      "eval_loss": NaN,
+      "eval_runtime": 62.4266,
+      "eval_samples_per_second": 4.501,
+      "eval_steps_per_second": 2.259,
+      "step": 30
+    },
+    {
+      "epoch": 0.09309309309309309,
+      "grad_norm": NaN,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.0960960960960961,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.0990990990990991,
+      "grad_norm": NaN,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.1021021021021021,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.10510510510510511,
+      "grad_norm": NaN,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.10510510510510511,
+      "eval_loss": NaN,
+      "eval_runtime": 62.2539,
+      "eval_samples_per_second": 4.514,
+      "eval_steps_per_second": 2.265,
+      "step": 35
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": NaN,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": NaN,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.11411411411411411,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.11711711711711711,
+      "grad_norm": NaN,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.12012012012012012,
+      "grad_norm": NaN,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.12012012012012012,
+      "eval_loss": NaN,
+      "eval_runtime": 62.1587,
+      "eval_samples_per_second": 4.521,
+      "eval_steps_per_second": 2.268,
+      "step": 40
+    },
+    {
+      "epoch": 0.12312312312312312,
+      "grad_norm": NaN,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.12612612612612611,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.12912912912912913,
+      "grad_norm": NaN,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.13213213213213212,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": NaN,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "eval_loss": NaN,
+      "eval_runtime": 62.3494,
+      "eval_samples_per_second": 4.507,
+      "eval_steps_per_second": 2.261,
+      "step": 45
+    },
+    {
+      "epoch": 0.13813813813813813,
+      "grad_norm": NaN,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.14114114114114115,
+      "grad_norm": NaN,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.14414414414414414,
+      "grad_norm": NaN,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.14714714714714713,
+      "grad_norm": NaN,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.15015015015015015,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.15015015015015015,
+      "eval_loss": NaN,
+      "eval_runtime": 62.1854,
+      "eval_samples_per_second": 4.519,
+      "eval_steps_per_second": 2.267,
+      "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": 3.51719368163328e+16,
+  "total_flos": 7.03438736326656e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null