Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5497596bcd22b39c1bf928c7239767a077489606c8c9fc0b7c847306e09b5e77
+oid sha256:ef448f02bfa0874d8b984dd7fea8948ca11655f23b7bd607cb738ceee5453c02
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c0de391ceae72081a6683fb1b208be4e710e93e6a248697c9e2f20e9d1b8c94
+oid sha256:cef699405e3f3ff010fa2459093c116515d0495548b42175b88ce72dcea444c5
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0a6d4a64d930a838765c3c927de04161f7a5a3ea45622b2da6484471022a666
+oid sha256:895c063d601a85133104ef08e5880ca891f08de28269ee26dd5ffc2f63690c87
 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": 2.3986308574676514,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.005295908910366741,
+  "best_metric": 1.8730665445327759,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.010591817820733483,
   "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": 6.856,
       "eval_steps_per_second": 1.716,
       "step": 10
+    },
+    {
+      "epoch": 0.00635509069244009,
+      "grad_norm": 1.8081384897232056,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.8778,
+      "step": 12
+    },
+    {
+      "epoch": 0.007943863365550112,
+      "grad_norm": 3.0349438190460205,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.0174,
+      "step": 15
+    },
+    {
+      "epoch": 0.007943863365550112,
+      "eval_loss": 2.0816292762756348,
+      "eval_runtime": 230.1286,
+      "eval_samples_per_second": 6.909,
+      "eval_steps_per_second": 1.729,
+      "step": 15
+    },
+    {
+      "epoch": 0.009532636038660135,
+      "grad_norm": 2.317234754562378,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.0729,
+      "step": 18
+    },
+    {
+      "epoch": 0.010591817820733483,
+      "eval_loss": 1.8730665445327759,
+      "eval_runtime": 229.2172,
+      "eval_samples_per_second": 6.937,
+      "eval_steps_per_second": 1.736,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3280194659942400.0,
+  "total_flos": 6560389319884800.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null