Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8628d545bbf88b72ffd297291e5bf5c57e3b6f190df37ce68bdb82cdb66ee048
+oid sha256:8d347c168ef39bb2a80d8c292860d11c8a2d253e4cf7af29b0ec1462c2f602f8
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7267023a0c268d9c768d3b4d2d3a88ed45e86170e7647724f4242483df2b318
+oid sha256:bc57d0a624437e59d00dce4e4812a759d76d9f2289d4d0e6a2ca6807d1e2ad09
 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": 0.00020472505425213938,
+  "epoch": 0.00040945010850427875,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 3.661,
       "eval_steps_per_second": 3.661,
       "step": 25
+    },
+    {
+      "epoch": 0.00024567006510256724,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.00028661507595299513,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.000327560086803423,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.00036850509765385086,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.00040945010850427875,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.00040945010850427875,
+      "eval_loss": NaN,
+      "eval_runtime": 3698.3758,
+      "eval_samples_per_second": 3.669,
+      "eval_steps_per_second": 3.669,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -72,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2184495916646400.0,
+  "total_flos": 4368991833292800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null