Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9894f4e130ceba8e360f75920d312b51e983d2f01a2cd31d0cd1b331577f06ce
+oid sha256:d97b6b62ead56b86ec17fa83afaf62b79ed1939d43859f4ba0398908dba4dca8
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:183195870a6827892ba1e7e0f681ac6e54431d35097d3ada59699d70826c5b08
+oid sha256:eeecebb300ade4a384deba2ac136a84a850d99aa7e089cef62903fbdb8c1857f
 size 51418196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c46d4aa8a39b760feb2ece556f0543b4b9f6c3fd4315fd4ddccefb37d238482f
+oid sha256:d1916266e5d8c733d88e89ea7c6174486a4c857e0f94cd7c34aefcb7617bed5a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d10d0fa96665f6b4af4824faec3d1d9f4e8b4343723a14d86cab932da6ce3225
+oid sha256:e7e4a8d9505ab5e0891e71b89f41010a5997ec96d8f1c5ec4c12ce973f5bf2fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7979318499565125,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.23536334215945867,
+  "best_metric": 0.7788119912147522,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.29420417769932333,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 22.071,
       "eval_steps_per_second": 5.518,
       "step": 200
+    },
+    {
+      "epoch": 0.2471315092674316,
+      "grad_norm": 0.7978292107582092,
+      "learning_rate": 0.00014845508703326504,
+      "loss": 5.7924,
+      "step": 210
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "grad_norm": 0.9069154858589172,
+      "learning_rate": 0.00014373073204588556,
+      "loss": 4.7768,
+      "step": 220
+    },
+    {
+      "epoch": 0.27066784348337747,
+      "grad_norm": 0.7871260643005371,
+      "learning_rate": 0.00013888241754733208,
+      "loss": 2.6733,
+      "step": 230
+    },
+    {
+      "epoch": 0.2824360105913504,
+      "grad_norm": 0.7734578847885132,
+      "learning_rate": 0.00013392388661180303,
+      "loss": 1.2857,
+      "step": 240
+    },
+    {
+      "epoch": 0.29420417769932333,
+      "grad_norm": 1.4109017848968506,
+      "learning_rate": 0.0001288691947339621,
+      "loss": 1.3427,
+      "step": 250
+    },
+    {
+      "epoch": 0.29420417769932333,
+      "eval_loss": 0.7788119912147522,
+      "eval_runtime": 65.0714,
+      "eval_samples_per_second": 22.007,
+      "eval_steps_per_second": 5.502,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3447268011081728e+17,
+  "total_flos": 1.6845926844019507e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null