Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a5c54e2f7522ee5d8c6f1208ae01e98415a7325d1cb3f07758bfb5c816a934
+oid sha256:e2507b89bf6ea0762c34e95ada362bbaa2e8e33e231b10d368dfa83fe6ea8566
 size 194840426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4e1a0151c8c40dc8d2f192af52091353f02d69a323aa5d7ac30ab6bf4931d7
+oid sha256:52d6d09c0b5cbd2545f4852d9a26ec8f99bc796dd25a1e396645a6cedd79e107
 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": 0.12618296529968454,
+  "epoch": 0.1892744479495268,
   "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": 14.514,
       "eval_steps_per_second": 3.683,
       "step": 20
+    },
+    {
+      "epoch": 0.13249211356466878,
+      "grad_norm": NaN,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.138801261829653,
+      "grad_norm": NaN,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.14511041009463724,
+      "grad_norm": NaN,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.15141955835962145,
+      "grad_norm": NaN,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.15141955835962145,
+      "eval_loss": NaN,
+      "eval_runtime": 4.6246,
+      "eval_samples_per_second": 14.488,
+      "eval_steps_per_second": 3.676,
+      "step": 24
+    },
+    {
+      "epoch": 0.15772870662460567,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.1640378548895899,
+      "grad_norm": NaN,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.17034700315457413,
+      "grad_norm": NaN,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.17665615141955837,
+      "grad_norm": NaN,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.17665615141955837,
+      "eval_loss": NaN,
+      "eval_runtime": 4.6139,
+      "eval_samples_per_second": 14.521,
+      "eval_steps_per_second": 3.684,
+      "step": 28
+    },
+    {
+      "epoch": 0.1829652996845426,
+      "grad_norm": NaN,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.1892744479495268,
+      "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": 2794842929233920.0,
+  "total_flos": 4192264393850880.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null