Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27df161324c0ea0b9ee539c341e4dcb5f50e2dd7215a01e4ed2a248e90ca9eb0
+oid sha256:a2b49238da4c41404dd097adc65d8a182b42c0457858cf70f7b84c156bc0a315
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53a3d590d4a9e9126b678d07989e2074d293cf88743ecd44ec26f400946c8033
+oid sha256:374abdf38288bae20534803eebd1640c3c5f26125d1a555a4ed5f0f6b0d34376
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba94e5f2576dd89fac4159f7c106e2d89fcd72be877ca4132e34fb56c60f73e
+oid sha256:c3ca9c86f4e1e8136456f71fa3c0684780b4398a9136b4c1725c36b538b5bfbb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2989118099212646,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0016909744240118367,
+  "best_metric": 1.249632477760315,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0033819488480236735,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 14.15,
       "eval_steps_per_second": 7.075,
       "step": 10
+    },
+    {
+      "epoch": 0.002029169308814204,
+      "grad_norm": 0.4550609588623047,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.3542,
+      "step": 12
+    },
+    {
+      "epoch": 0.0025364616360177552,
+      "grad_norm": 0.4199211299419403,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.3569,
+      "step": 15
+    },
+    {
+      "epoch": 0.0025364616360177552,
+      "eval_loss": 1.263357162475586,
+      "eval_runtime": 175.9689,
+      "eval_samples_per_second": 14.15,
+      "eval_steps_per_second": 7.075,
+      "step": 15
+    },
+    {
+      "epoch": 0.0030437539632213063,
+      "grad_norm": 0.40665045380592346,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.1759,
+      "step": 18
+    },
+    {
+      "epoch": 0.0033819488480236735,
+      "eval_loss": 1.249632477760315,
+      "eval_runtime": 175.9054,
+      "eval_samples_per_second": 14.155,
+      "eval_steps_per_second": 7.078,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4358587790917632.0,
+  "total_flos": 9088119223615488.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null