Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d19d120d98eca14e37e0e3ca76e2f6d519d7e4f15121dca0b99b8670f261a18
+oid sha256:27a7e48288fb7e98130effc09a443086aeda45a1543b20413a9a14e8463e2a6b
 size 828526568

last-checkpoint/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4bd858814182c1ca78928662dd2808b6dcdbd7f8e48eeb70d84e22b864e4e9b
+oid sha256:7a5e2465a21776f6b11aaad5ae5e73e5299188394a8b13ec35feaf5b3e9e22e7
 size 1657755122

last-checkpoint/pytorch_model_fsdp.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27949875f15d00e1d30a0397cf66ef7673a3d4f28b8e22e08493d06d96ca2236
+oid sha256:33d567a1ce8013f3d1353502f65107776932e5bf44bc8ca8d1700e44afd824f4
 size 828793718

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b49fe64ae4bbd6f86acbecce3d62122b689972d76f90380c5655675dfe34a584
+oid sha256:e1c721dc9e7a128695aa757659b455b66eed608e12fb70ec3e7da6ee4fe17684
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c632e20b21fd813e860b78543c966a0c9853161e6dab3d38079f8d1c1140468
+oid sha256:4f79d01ac59109f9fb23deb4e3fb4d5a3ceb1f25a06de4a1189f362027e8b273
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f324260c3b2e9138c79111fd584443eda8073ed4aace9b2b56df5dbf8b9c5d3
+oid sha256:f82b0d1cefd4f4436ae808681102171b3999df3c7fc173bd2452a3218ed3ea3a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 6,
-  "best_metric": 0.3095230758190155,
-  "best_model_checkpoint": "miner_id_24/checkpoint-6",
-  "epoch": 0.021636240703177823,
+  "best_global_step": 9,
+  "best_metric": 0.2719385325908661,
+  "best_model_checkpoint": "miner_id_24/checkpoint-9",
+  "epoch": 0.032454361054766734,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,35 @@
       "eval_samples_per_second": 6.295,
       "eval_steps_per_second": 0.789,
       "step": 6
+    },
+    {
+      "epoch": 0.025242280820374125,
+      "grad_norm": 0.11893875896930695,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.2486,
+      "step": 7
+    },
+    {
+      "epoch": 0.02884832093757043,
+      "grad_norm": 0.18706969916820526,
+      "learning_rate": 0.0001,
+      "loss": 0.2442,
+      "step": 8
+    },
+    {
+      "epoch": 0.032454361054766734,
+      "grad_norm": 0.11945672333240509,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.2259,
+      "step": 9
+    },
+    {
+      "epoch": 0.032454361054766734,
+      "eval_loss": 0.2719385325908661,
+      "eval_runtime": 296.4826,
+      "eval_samples_per_second": 6.301,
+      "eval_steps_per_second": 0.789,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -102,7 +131,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6475484454282854e+17,
+  "total_flos": 2.2563477975046554e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null