Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae0121c7556edf5c3d39dc68a36ad1e58f74a3050f3cd6875ea40059b7c76d3
+oid sha256:3ac6d465212671f645f0c5c05ebf728f1d70d12d7ce543038e72cf8f653cb838
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0504a82b9d1462df6794f44fbb8431046ed9c46b7286f7ec8247a50fe9724974
+oid sha256:923793c3226af58b708818fdf54ec6644050e5ff369f5d3e7bf667b6fd94bb04
 size 51418452

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d26b6ca5513429ee6f5da17a80a0dec8462857d45a6714cbe5fe4f29d713d2c9
+oid sha256:436e3f26d21c67fae4787bf3356ab50f12b0bd9b8481bf84f7755722eb0ab42a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c9b643e87499abdfb160399a4a6e4965274897c037cf91e4cd5d5d65b2b404
+oid sha256:fe0a47cc675a5d4ba5fe8c0d42564476e1fe842799977ab67bf2a8317adef53f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7572553157806396,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.41188584877905265,
+  "best_metric": 0.7500874400138855,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.47072668431891734,
   "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": 22.038,
       "eval_steps_per_second": 5.51,
       "step": 350
+    },
+    {
+      "epoch": 0.4236540158870256,
+      "grad_norm": 0.696776270866394,
+      "learning_rate": 7.113080526603792e-05,
+      "loss": 5.7138,
+      "step": 360
+    },
+    {
+      "epoch": 0.4354221829949985,
+      "grad_norm": 0.9223313331604004,
+      "learning_rate": 6.607611338819697e-05,
+      "loss": 4.5998,
+      "step": 370
+    },
+    {
+      "epoch": 0.4471903501029715,
+      "grad_norm": 0.7238697409629822,
+      "learning_rate": 6.111758245266794e-05,
+      "loss": 2.5621,
+      "step": 380
+    },
+    {
+      "epoch": 0.4589585172109444,
+      "grad_norm": 0.9471986889839172,
+      "learning_rate": 5.626926795411447e-05,
+      "loss": 1.2488,
+      "step": 390
+    },
+    {
+      "epoch": 0.47072668431891734,
+      "grad_norm": 1.4697206020355225,
+      "learning_rate": 5.1544912966734994e-05,
+      "loss": 1.3135,
+      "step": 400
+    },
+    {
+      "epoch": 0.47072668431891734,
+      "eval_loss": 0.7500874400138855,
+      "eval_runtime": 64.8413,
+      "eval_samples_per_second": 22.085,
+      "eval_steps_per_second": 5.521,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.3560350392018534e+17,
+  "total_flos": 2.6931377852330803e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null