Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93be91f4cf957702a4cb1858c221a93dda1a8855bd774418a2ae58f4ae636977
+oid sha256:a49dc400cad83dc717924664f79db036cd194e098668790cd71458644692a923
 size 646253418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:405b3c05fdddddd30a9319bbc0fd78700bd1cd7545671fcb8fdba5eea3568078
+oid sha256:558012041b538fdaaeeebca6abf29097f009eaf3fb3d7d8fa15728c41bd53d0f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:559fc41b1666bf9d08bbf36782e6c7ecd5d9cb035c707b8454088fa01b378aaa
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08163265306122448,
+  "epoch": 0.16326530612244897,
   "eval_steps": 10,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -93,6 +93,84 @@
       "eval_samples_per_second": 5.386,
       "eval_steps_per_second": 2.693,
       "step": 10
+    },
+    {
+      "epoch": 0.08979591836734693,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.09795918367346938,
+      "grad_norm": NaN,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.10612244897959183,
+      "grad_norm": NaN,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.11428571428571428,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.12244897959183673,
+      "grad_norm": NaN,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.1306122448979592,
+      "grad_norm": NaN,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.13877551020408163,
+      "grad_norm": NaN,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.1469387755102041,
+      "grad_norm": NaN,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.15510204081632653,
+      "grad_norm": NaN,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "eval_loss": NaN,
+      "eval_runtime": 19.6287,
+      "eval_samples_per_second": 5.298,
+      "eval_steps_per_second": 2.649,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -107,12 +185,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.530826075190067e+16,
+  "total_flos": 3.936840561406771e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null