Training in progress, step 46, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3161d89e2ad1b44a18bf418bfb17aa903d17835c252c09465b64747372bac3f
+oid sha256:71f9ad67d7da082ffc7e6bcb5da67c989ae4179d2e6742fcb02dcddde436b548
 size 70667778

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06ab5129ab155330a39a9371aacd2f73f3677218096c1c34b3766d995f841a91
+oid sha256:380920090fa298dc1c0b364af9064413da5ecdbe3aeb596471d663387915393e
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81435bd0a6a3789b553c69a79f8c384151f9688d0cd7d745e20e5aadeece4761
+oid sha256:9c7c9e22c75a13a9902d17f3192f927c82d7333c0b4d285610b63194d12e2883
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:844a9e8b65ea1c19a7e6553433121a4f8c699c309e7900990529efa7ada6321b
+oid sha256:ca03a7964455ac25dc387068890b645c2e3e0fcd3245a993a5c6b7145edfe622
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.768,
+  "epoch": 0.9813333333333333,
   "eval_steps": 12,
-  "global_step": 36,
+  "global_step": 46,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -291,6 +291,76 @@
       "eval_samples_per_second": 21.637,
       "eval_steps_per_second": 5.478,
       "step": 36
+    },
+    {
+      "epoch": 0.7893333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 7.4e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.8106666666666666,
+      "grad_norm": NaN,
+      "learning_rate": 7.6e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": NaN,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.8746666666666667,
+      "grad_norm": NaN,
+      "learning_rate": 8.2e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": NaN,
+      "learning_rate": 8.4e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.9173333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 8.6e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.9386666666666666,
+      "grad_norm": NaN,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.9813333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.0,
+      "step": 46
     }
   ],
   "logging_steps": 1,
@@ -305,12 +375,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5190870965944320.0,
+  "total_flos": 6632779567595520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null