Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c9de87c920816ee805ad6f0dcc048fe47192a63dee5a90180ea68ad0ee3ce96
+oid sha256:5d24b0397b84515fd5c8658413acbf5679ee218e370af53374322a5e02dad939
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81529912341fabc5dfb9e803b11f514589f1bbb9a589b89e52e8f8e7b1e0973d
+oid sha256:ccaa10718baaf5bd64601309ed15285ab5d78611ccf0666d7ebf10ed6f211462
 size 18810356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5a59fb166c95ba4ca8df491eb4ff9d8576a87883e8e6c47c6166836bd7eda3a
+oid sha256:ef41991dbb561d3a2f5aceab35c3651f4204f14eaf4c97c7bbc11367b613fe59
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c4651949407010a02df1b68ceaab868428ade8f98ceca4a68f2ae05b6e6aa52
+oid sha256:f5f1cac8669e836e149701a48af17007b43f815a942690ea0b80d521bdf222a6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.758694648742676,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.015803138051698837,
+  "best_metric": 2.735464572906494,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.018060729201941527,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 49.573,
       "eval_steps_per_second": 12.396,
       "step": 350
+    },
+    {
+      "epoch": 0.016254656281747375,
+      "grad_norm": 3.1886544227600098,
+      "learning_rate": 4.518272739424847e-05,
+      "loss": 2.5843,
+      "step": 360
+    },
+    {
+      "epoch": 0.016706174511795915,
+      "grad_norm": 4.394619941711426,
+      "learning_rate": 3.9394698779120026e-05,
+      "loss": 2.6041,
+      "step": 370
+    },
+    {
+      "epoch": 0.017157692741844453,
+      "grad_norm": 3.7810781002044678,
+      "learning_rate": 3.3914112848217066e-05,
+      "loss": 2.6417,
+      "step": 380
+    },
+    {
+      "epoch": 0.01760921097189299,
+      "grad_norm": 4.610939979553223,
+      "learning_rate": 2.8767670465288276e-05,
+      "loss": 2.6743,
+      "step": 390
+    },
+    {
+      "epoch": 0.018060729201941527,
+      "grad_norm": 5.860191345214844,
+      "learning_rate": 2.3980444580304764e-05,
+      "loss": 3.1479,
+      "step": 400
+    },
+    {
+      "epoch": 0.018060729201941527,
+      "eval_loss": 2.735464572906494,
+      "eval_runtime": 185.0743,
+      "eval_samples_per_second": 50.391,
+      "eval_steps_per_second": 12.6,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3158681030492160.0,
+  "total_flos": 3609277468508160.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null