Training in progress, step 28, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d76418ff259d6b95ca3894a200164cb00ea783d60345b1fb1ae03590905f50
+oid sha256:3e9420f6f3fc29633a07c26c966bcb335bdc2f001c1272653d3ea778f90fe75f
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87819adfca79781ff1481332dd3e62a860f819af78a0041bf061284c45717743
+oid sha256:ab31d15ea1ba2d4d7bad408ca02f40a4d59f928df01a5b0221084a9a06c0d6c6
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50fdde2e6e9bce9221776c4ef7a09f6ed036b172161ee458bcdbf277b8f7af76
+oid sha256:d0917413fef43bed6cecb7db8c5e42249c1e10cc03c1d8a741dc0fb77bd55f91
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc7a5e0a3f6e8213978b91efc94b2e3f0ccc2e6d341d3af403f1b3a2f8391987
+oid sha256:ba0330846ae5b1cd29ac03ff9027753080e9429c5277168703ffd1f37aa0ea76
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47bc08790b49b64dc7821549f6ecd30dc1169ce9ea88bc8a9d0c66b37b3de198
+oid sha256:f8d42e9dafcdb6df44230a1a7cae754a92b3595499a99211109c3eca67a76e1e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73a118e681fa814e101b0fd54b5f7d177ef6c83e0e721bb9177ce578ce9b71a7
+oid sha256:b5d68508636586630def15adada56bacf5564430dadc7cdc60a1b731c838c499
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.7491408934707904,
+  "epoch": 3.0790378006872854,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 28,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,27 @@
       "eval_samples_per_second": 15.312,
       "eval_steps_per_second": 3.981,
       "step": 25
+    },
+    {
+      "epoch": 2.859106529209622,
+      "grad_norm": NaN,
+      "learning_rate": 1.130761821582766e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 2.9690721649484537,
+      "grad_norm": NaN,
+      "learning_rate": 1.0328100665587574e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 3.0790378006872854,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 28
     }
   ],
   "logging_steps": 1,
@@ -221,12 +242,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.984041808658432e+17,
+  "total_flos": 3.342126825697444e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null