Training in progress, step 189, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70ea86d51a9634bf92e8e76a85f96ec6ab8e9992c9a760df14bd2431d4bf14de
+oid sha256:9b632180e937ab1fa5d61d48b8652b6eb3d9d4cef91094e5cc90d3cee65676b3
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:536a10198983821af10e2dddfe73906facff151d67d87c597a610ff5276198bc
+oid sha256:0074a94e7be8f39393e7be3ece5718fa75893cad9596eb6bcf3dfb395e3ed98a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fde2add4ac526f9d88b4a85a5e304b22d4aa9bf06cf799f89fbf1fa68e0bf83
+oid sha256:65558e26afbfb87dd1928966282919939bdee4084add607d42e008ed52d680cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005318250886375148,
+  "epoch": 0.007977376329562722,
   "eval_steps": 63,
-  "global_step": 126,
+  "global_step": 189,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -115,6 +115,56 @@
       "eval_samples_per_second": 11.708,
       "eval_steps_per_second": 5.854,
       "step": 126
+    },
+    {
+      "epoch": 0.005487084247847374,
+      "grad_norm": NaN,
+      "learning_rate": 9.679484224283449e-05,
+      "loss": 0.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.005909167651527942,
+      "grad_norm": NaN,
+      "learning_rate": 8.404001049666211e-05,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.006331251055208509,
+      "grad_norm": NaN,
+      "learning_rate": 7.154724133689677e-05,
+      "loss": 0.8831,
+      "step": 150
+    },
+    {
+      "epoch": 0.006753334458889077,
+      "grad_norm": NaN,
+      "learning_rate": 5.952166568776062e-05,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.007175417862569644,
+      "grad_norm": NaN,
+      "learning_rate": 4.8160743168947496e-05,
+      "loss": 0.0689,
+      "step": 170
+    },
+    {
+      "epoch": 0.007597501266250211,
+      "grad_norm": NaN,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 0.0793,
+      "step": 180
+    },
+    {
+      "epoch": 0.007977376329562722,
+      "eval_loss": NaN,
+      "eval_runtime": 853.2017,
+      "eval_samples_per_second": 11.692,
+      "eval_steps_per_second": 5.846,
+      "step": 189
     }
   ],
   "logging_steps": 10,
@@ -134,7 +184,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.6158980849664e+16,
+  "total_flos": 1.13841809915904e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null