Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cef4af1edda012b7fcb920ed54feed977ce6ecdbb6f3855feb80788316f9f08
+oid sha256:87c2c748fdea6e4df30285253615c6ccb0507867ecbddc48169d23d2153e8006
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e03db4552dd322bc2876e8b6d4e6a93c186e8af38a1bc9ddcd1884ba36996a0b
+oid sha256:a3ae4bde86c456959a43743df1f1f49fe179e837dd05854969e8cfc13dac3e3e
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1f88534a8da60de527d1cc9e43227c3c25cc07e3ddf35c45886e34daf212955
+oid sha256:b4ec1d5634f6b9d660db2162626d3c8d3b414e73462d77c6a227ef7e8165e111
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7410375475883484,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.08368200836820083,
+  "best_metric": 0.7117478847503662,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.12552301255230125,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 9.753,
       "eval_steps_per_second": 2.462,
       "step": 20
+    },
+    {
+      "epoch": 0.08786610878661087,
+      "grad_norm": 2.102637529373169,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.7635,
+      "step": 21
+    },
+    {
+      "epoch": 0.100418410041841,
+      "grad_norm": 2.4638094902038574,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.8203,
+      "step": 24
+    },
+    {
+      "epoch": 0.10460251046025104,
+      "eval_loss": 0.7162254452705383,
+      "eval_runtime": 20.8849,
+      "eval_samples_per_second": 9.672,
+      "eval_steps_per_second": 2.442,
+      "step": 25
+    },
+    {
+      "epoch": 0.11297071129707113,
+      "grad_norm": 2.498424530029297,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.7622,
+      "step": 27
+    },
+    {
+      "epoch": 0.12552301255230125,
+      "grad_norm": 2.2009360790252686,
+      "learning_rate": 0.0,
+      "loss": 2.752,
+      "step": 30
+    },
+    {
+      "epoch": 0.12552301255230125,
+      "eval_loss": 0.7117478847503662,
+      "eval_runtime": 20.7757,
+      "eval_samples_per_second": 9.723,
+      "eval_steps_per_second": 2.455,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.306916403806208e+16,
+  "total_flos": 1.960374605709312e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null