Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c69f123166e2ca90eda74e8a3d51b014325d7c1ae47a595f87fa00df5bb932f
+oid sha256:e4e815def6fbeceab5aff7ab1d26b01db2a4e1c8fd90120acde47e1ae44b4d43
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c43d2761b50091cf4baa0d57859022fae0a545b911b5942a4baee7a2cfd830dd
+oid sha256:e7c417bae043f02a3f34251fe73a936c4b76dade1d46eebf4f2c109099aad84a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddaa639affba9b89222fee046caf8a7f8b52a142c3b2d35ccd1f461973cfdc78
+oid sha256:b5b325ea4e14a510f9eb0108f2923753e246a5ec70e919cdd84a9afd64b95afd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00030320717388173404,
+  "epoch": 0.00045481076082260104,
   "eval_steps": 4,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -195,6 +195,92 @@
       "eval_samples_per_second": 31.376,
       "eval_steps_per_second": 7.844,
       "step": 20
+    },
+    {
+      "epoch": 0.00031836753257582075,
+      "grad_norm": NaN,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.00033352789126990745,
+      "grad_norm": NaN,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.00034868824996399416,
+      "grad_norm": NaN,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.00036384860865808086,
+      "grad_norm": NaN,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.00036384860865808086,
+      "eval_loss": NaN,
+      "eval_runtime": 885.7638,
+      "eval_samples_per_second": 31.356,
+      "eval_steps_per_second": 7.84,
+      "step": 24
+    },
+    {
+      "epoch": 0.00037900896735216757,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.00039416932604625427,
+      "grad_norm": NaN,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.000409329684740341,
+      "grad_norm": NaN,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0004244900434344277,
+      "grad_norm": NaN,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.0004244900434344277,
+      "eval_loss": NaN,
+      "eval_runtime": 886.2482,
+      "eval_samples_per_second": 31.339,
+      "eval_steps_per_second": 7.835,
+      "step": 28
+    },
+    {
+      "epoch": 0.0004396504021285144,
+      "grad_norm": NaN,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.00045481076082260104,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -209,12 +295,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1029368772034560.0,
+  "total_flos": 1544053158051840.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null