Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:911475c792ca6672cbde6bbeba218c752761cdecb9ee0167b0dbc6da1ed628c1
+oid sha256:234b1d5c01d29c1839967d8b18af236339a3d667efeb276feb222738d4348424
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4c7b5d94e13675aa9dec3ae0c8c42b15704e86e2fb9fb52a77a135205529389
+oid sha256:5475096bc4406baf8f948f663a50d0793d2d5ade166f537d50ac7b7161329ba6
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b46e47288282fbea002eed6cbf060850ca36a435d8694c93bebae6076d14cd3
+oid sha256:c56088c033bb948005186a85403f9f53a67e87ceb9bf29f30351f95a6f5bc69f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e79d8c81c28cccecf62c97d7dd656ff3c70055cc3d5608fb5051fff0516dc264
+oid sha256:6230a4f38a0ea478447f5ea0afea90b5855d705f677280e45e7e6abb464194a3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3272861838340759,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.26258205689277897,
+  "best_metric": 0.31218644976615906,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.3063457330415755,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,49 @@
       "eval_samples_per_second": 10.032,
       "eval_steps_per_second": 2.524,
       "step": 300
+    },
+    {
+      "epoch": 0.2713347921225383,
+      "grad_norm": 0.4647512137889862,
+      "learning_rate": 7.694492759663374e-05,
+      "loss": 0.7352,
+      "step": 310
+    },
+    {
+      "epoch": 0.2800875273522976,
+      "grad_norm": 0.23608016967773438,
+      "learning_rate": 7.013477507094284e-05,
+      "loss": 0.5446,
+      "step": 320
+    },
+    {
+      "epoch": 0.2888402625820569,
+      "grad_norm": 0.011121237650513649,
+      "learning_rate": 6.347743076828492e-05,
+      "loss": 0.1594,
+      "step": 330
+    },
+    {
+      "epoch": 0.2975929978118162,
+      "grad_norm": 0.03790149837732315,
+      "learning_rate": 5.700532860090863e-05,
+      "loss": 0.0004,
+      "step": 340
+    },
+    {
+      "epoch": 0.3063457330415755,
+      "grad_norm": 0.17843233048915863,
+      "learning_rate": 5.075000000000002e-05,
+      "loss": 0.0016,
+      "step": 350
+    },
+    {
+      "epoch": 0.3063457330415755,
+      "eval_loss": 0.31218644976615906,
+      "eval_runtime": 47.9567,
+      "eval_samples_per_second": 10.03,
+      "eval_steps_per_second": 2.523,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.81991873314816e+16,
+  "total_flos": 1.1455090721292288e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null