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:e38e44965978ec6b2b4f8ccdc9b4e4b5d1198ea5ae4ad87ad16bb2707f6bac2c
+oid sha256:6b989deff64bff1ab48f749e4d9aad73c28b9fd0930af8dd5dc634f2f0dc9d7a
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19a6cb3454e2a78122ac6f3ed6b42f5e75a2e4c0906f4f46df2c082138e9db9b
+oid sha256:f4c7eebb841a84c219700a7d3aa08c43f3257bd8f123515754cb9966c17f4a83
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fefb6e94bb0231985ecc91a7ebfca6a935aa50d07909109f8818c4c8c1e8853e
+oid sha256:5d9a134a1ce091ac0ff97a5168971b89697f184ed91d6285b7d0fa9d1ea72cc5
 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": 0.3763931095600128,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.009149130832570906,
+  "best_metric": 0.3640096187591553,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.013723696248856358,
   "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": 11.335,
       "eval_steps_per_second": 2.838,
       "step": 20
+    },
+    {
+      "epoch": 0.00960658737419945,
+      "grad_norm": 0.35927730798721313,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.3669,
+      "step": 21
+    },
+    {
+      "epoch": 0.010978956999085087,
+      "grad_norm": 0.31829825043678284,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.3661,
+      "step": 24
+    },
+    {
+      "epoch": 0.011436413540713633,
+      "eval_loss": 0.36795511841773987,
+      "eval_runtime": 162.5768,
+      "eval_samples_per_second": 11.324,
+      "eval_steps_per_second": 2.836,
+      "step": 25
+    },
+    {
+      "epoch": 0.012351326623970723,
+      "grad_norm": 0.40827932953834534,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.3549,
+      "step": 27
+    },
+    {
+      "epoch": 0.013723696248856358,
+      "grad_norm": 0.34633514285087585,
+      "learning_rate": 0.0,
+      "loss": 0.3407,
+      "step": 30
+    },
+    {
+      "epoch": 0.013723696248856358,
+      "eval_loss": 0.3640096187591553,
+      "eval_runtime": 162.3702,
+      "eval_samples_per_second": 11.338,
+      "eval_steps_per_second": 2.839,
+      "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": 1.647225084051456e+16,
+  "total_flos": 2.470837626077184e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null