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:b74016ba80c25894450882f5a0a23d523f3443696ce07255e925de217368e15e
+oid sha256:9b6ba47ca793a092b064c76745563191dbfb6c58f36927c5f5224f9d646b384c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20477e35f2b74f1e37b41a7da8b10ea5d4c11abe4f0497d580e9910e6663805a
+oid sha256:c93347fbdb52ec5c1b8e7207dacd486b8dd5ad5716a4a4ac0d23d4112e09c57e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f601e5723b7977940291127d4234689f9b9aaaff2705528d580c2f361e9ecdd
+oid sha256:4b4c4414b1477b88dd28545796fac3625b92c8d58dc69e8be9393c4668fcf60b
 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": 1.247101902961731,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.012292562999385371,
+  "best_metric": 1.2206299304962158,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.01843884449907806,
   "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": 15.402,
       "eval_steps_per_second": 7.712,
       "step": 20
+    },
+    {
+      "epoch": 0.01290719114935464,
+      "grad_norm": 0.596222996711731,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.1096,
+      "step": 21
+    },
+    {
+      "epoch": 0.014751075599262446,
+      "grad_norm": 0.5047256946563721,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.1311,
+      "step": 24
+    },
+    {
+      "epoch": 0.015365703749231715,
+      "eval_loss": 1.2259085178375244,
+      "eval_runtime": 44.5912,
+      "eval_samples_per_second": 15.362,
+      "eval_steps_per_second": 7.692,
+      "step": 25
+    },
+    {
+      "epoch": 0.016594960049170254,
+      "grad_norm": 0.8928716778755188,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.8738,
+      "step": 27
+    },
+    {
+      "epoch": 0.01843884449907806,
+      "grad_norm": 0.6247184872627258,
+      "learning_rate": 0.0,
+      "loss": 1.3205,
+      "step": 30
+    },
+    {
+      "epoch": 0.01843884449907806,
+      "eval_loss": 1.2206299304962158,
+      "eval_runtime": 44.5161,
+      "eval_samples_per_second": 15.388,
+      "eval_steps_per_second": 7.705,
+      "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": 8531703760945152.0,
+  "total_flos": 1.2426611999637504e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null