Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1adfc6515b1e67ae439537859c9465f29dc8628bab6a94caf80a88046880fa87
+oid sha256:020301653818ae9e211d55c234742b3ad590976e2dad3c9e05796a487046de6c
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97291eda5ca6f3cb63e5be95416d00d6c51f61b9a8913fa4b66b2362b58c68b3
+oid sha256:539795c9355054ab742451d4fbe052e9d1a90cd3a7f8b418bda15556ece4daf6
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38220ad448edaad4525c57c063299252bbf6f342fd28b6412a1850b27989a0da
+oid sha256:73b2095a313b289a00bf1d1ea616b14aa22b6faaef548d1b355d9729c289662b
 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": 1.7479033470153809,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.18604651162790697,
+  "best_metric": 1.71920645236969,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.27906976744186046,
   "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": 4.231,
       "eval_steps_per_second": 1.069,
       "step": 20
+    },
+    {
+      "epoch": 0.19534883720930232,
+      "grad_norm": 0.5440554022789001,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.8117,
+      "step": 21
+    },
+    {
+      "epoch": 0.22325581395348837,
+      "grad_norm": 0.6222204566001892,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.8081,
+      "step": 24
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "eval_loss": 1.7246214151382446,
+      "eval_runtime": 21.4867,
+      "eval_samples_per_second": 4.235,
+      "eval_steps_per_second": 1.07,
+      "step": 25
+    },
+    {
+      "epoch": 0.25116279069767444,
+      "grad_norm": 0.3558702766895294,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.8349,
+      "step": 27
+    },
+    {
+      "epoch": 0.27906976744186046,
+      "grad_norm": 0.42415860295295715,
+      "learning_rate": 0.0,
+      "loss": 1.6276,
+      "step": 30
+    },
+    {
+      "epoch": 0.27906976744186046,
+      "eval_loss": 1.71920645236969,
+      "eval_runtime": 21.4466,
+      "eval_samples_per_second": 4.243,
+      "eval_steps_per_second": 1.072,
+      "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": 2.53296434479104e+16,
+  "total_flos": 3.79944651718656e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null