Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f593deebabe26b07920644c33e033b11bebb3b97e4eef2d277cac0963b46c03
+oid sha256:308c66cf7cc561844c3244027b3bf1bbb588f7334df0ceecf7d9a1fe9689b263
 size 56662456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:519008bcef9fe26a18c59433b9d8090882006d79388b21b45d28ac5ad1360950
+oid sha256:60d5207d10f1e0668b2a8da0b117651f6a8451f91f88cafc573e175238d87b76
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f69ad638511de7174129f7b93b8fe2b9d387a61c53e182f12cb6d9b43daab6fa
+oid sha256:9781620c6144bfb1c850cc1e721289002e55e16ee2b70edace362e5c7a144e30
 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": 1.23676335811615,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.03148366784730421,
+  "best_metric": 1.227588176727295,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.047225501770956316,
   "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": 10.134,
       "eval_steps_per_second": 2.538,
       "step": 20
+    },
+    {
+      "epoch": 0.03305785123966942,
+      "grad_norm": 0.36481747031211853,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 3.863,
+      "step": 21
+    },
+    {
+      "epoch": 0.03778040141676505,
+      "grad_norm": 0.3830651640892029,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 3.8907,
+      "step": 24
+    },
+    {
+      "epoch": 0.03935458480913026,
+      "eval_loss": 1.2320196628570557,
+      "eval_runtime": 53.365,
+      "eval_samples_per_second": 10.025,
+      "eval_steps_per_second": 2.511,
+      "step": 25
+    },
+    {
+      "epoch": 0.04250295159386069,
+      "grad_norm": 0.6799097657203674,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 5.2746,
+      "step": 27
+    },
+    {
+      "epoch": 0.047225501770956316,
+      "grad_norm": 0.48981112241744995,
+      "learning_rate": 0.0,
+      "loss": 4.2177,
+      "step": 30
+    },
+    {
+      "epoch": 0.047225501770956316,
+      "eval_loss": 1.227588176727295,
+      "eval_runtime": 52.7638,
+      "eval_samples_per_second": 10.14,
+      "eval_steps_per_second": 2.54,
+      "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": 4807501849559040.0,
+  "total_flos": 7000924568420352.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null