Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b218bfb01580e03be44ca48b3a7796be0d9cc23fde2adf54d7ca840c442a90e9
+oid sha256:911475c792ca6672cbde6bbeba218c752761cdecb9ee0167b0dbc6da1ed628c1
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89338a1e7e3c931a3f388f9d7f975a3c55792f6048c00706fc44cb172274658a
-size 328468404
+oid sha256:b4c7b5d94e13675aa9dec3ae0c8c42b15704e86e2fb9fb52a77a135205529389
+size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95226b9443ed4e38c27bbb8187789d508a89cfc90744595951e5068e3128acf8
+oid sha256:6b46e47288282fbea002eed6cbf060850ca36a435d8694c93bebae6076d14cd3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9b2510d4f3300d86de2c5b705a4b3113b18ea2234bf5e3432bd4dee5175a4db
+oid sha256:e79d8c81c28cccecf62c97d7dd656ff3c70055cc3d5608fb5051fff0516dc264
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3523136377334595,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.2188183807439825,
+  "best_metric": 0.3272861838340759,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.26258205689277897,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 9.986,
       "eval_steps_per_second": 2.512,
       "step": 250
+    },
+    {
+      "epoch": 0.2275711159737418,
+      "grad_norm": 0.5447108149528503,
+      "learning_rate": 0.00011210963902166683,
+      "loss": 0.8402,
+      "step": 260
+    },
+    {
+      "epoch": 0.2363238512035011,
+      "grad_norm": 0.32077598571777344,
+      "learning_rate": 0.00010504229891530386,
+      "loss": 0.6314,
+      "step": 270
+    },
+    {
+      "epoch": 0.24507658643326038,
+      "grad_norm": 0.22313565015792847,
+      "learning_rate": 9.795770108469618e-05,
+      "loss": 0.2108,
+      "step": 280
+    },
+    {
+      "epoch": 0.2538293216630197,
+      "grad_norm": 0.03895167261362076,
+      "learning_rate": 9.08903609783332e-05,
+      "loss": 0.0013,
+      "step": 290
+    },
+    {
+      "epoch": 0.26258205689277897,
+      "grad_norm": 0.004272861871868372,
+      "learning_rate": 8.387470996680658e-05,
+      "loss": 0.0024,
+      "step": 300
+    },
+    {
+      "epoch": 0.26258205689277897,
+      "eval_loss": 0.3272861838340759,
+      "eval_runtime": 47.9479,
+      "eval_samples_per_second": 10.032,
+      "eval_steps_per_second": 2.524,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.17585994072064e+16,
+  "total_flos": 9.81991873314816e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null