Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83f8e5b81adfe0802874e054bb4141a6c9ca444260cac8658f2063c912d777cf
+oid sha256:db5f037f706d096dab2869a45bdd57d4c2ddff45143b18908a35b676d48c860c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb8c9f39c808444ba356b8259f1b381d5be6bc7bd1669874f3e2266294c7fc6b
+oid sha256:86e647a82cc157a8b55765dc994ce7fc2966651162d01a2a2cb063c7b9a4d0f7
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4da5d8e17ffed708017fed0aa9bb08ecfbc345b142c22b42e93feb3a81596202
+oid sha256:dff5630883cddec4cfc7052bca1183759e6e57eda67ba131fc8be70f276d16da
 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": 2.391322612762451,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.003518648838845883,
+  "best_metric": 2.0442113876342773,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.007037297677691766,
   "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": 6.455,
       "eval_steps_per_second": 1.615,
       "step": 10
+    },
+    {
+      "epoch": 0.00422237860661506,
+      "grad_norm": 0.7181974053382874,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.9543,
+      "step": 12
+    },
+    {
+      "epoch": 0.005277973258268825,
+      "grad_norm": 1.226182222366333,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.9358,
+      "step": 15
+    },
+    {
+      "epoch": 0.005277973258268825,
+      "eval_loss": 2.124796152114868,
+      "eval_runtime": 370.5255,
+      "eval_samples_per_second": 6.461,
+      "eval_steps_per_second": 1.617,
+      "step": 15
+    },
+    {
+      "epoch": 0.0063335679099225895,
+      "grad_norm": 0.8600994348526001,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.9038,
+      "step": 18
+    },
+    {
+      "epoch": 0.007037297677691766,
+      "eval_loss": 2.0442113876342773,
+      "eval_runtime": 369.8902,
+      "eval_samples_per_second": 6.472,
+      "eval_steps_per_second": 1.619,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7604344656494592.0,
+  "total_flos": 1.5023217492099072e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null