Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16b1cf3cafa2eda7c232bc6cc3fca122b83a32b7a53e2f9972e5491f69d8095d
+oid sha256:f74e32c80a27b88d895bdb1f4578e05687337736870720b59fe44dba58c489ce
 size 5962860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a0678dd5e4508551da8571ee0e0d183132c1ea9c4504670473da5c6692e57d
+oid sha256:7e272e9d7e493c9b11d52af458cc392aea6cce8c014e1d7b5cb2cc292f76675e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002911914583838874,
+  "epoch": 0.005823829167677748,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 45.183,
       "eval_steps_per_second": 22.592,
       "step": 3
+    },
+    {
+      "epoch": 0.003882552778451832,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.0048531909730647905,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.005823829167677748,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.005823829167677748,
+      "eval_loss": NaN,
+      "eval_runtime": 9.7144,
+      "eval_samples_per_second": 44.676,
+      "eval_steps_per_second": 22.338,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 11347825655808.0,
+  "total_flos": 23363170467840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null