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:c475a2aa9f9ca8c2da2346395e14ccc2810683d54702dfe2b1b0bba1141cf0fc
+oid sha256:26f5ce926d12ae5566b4582e76cd8795850ebbd48aeaa3fe8afcd9e1c3149ab1
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39c7f751c7505f2b7d5c8c28c15a506d7ff4fdf7190c5115f3ee555e5513005c
+oid sha256:07a0e50545b540b367f16bb13d496f2e4b62954e1efd357f82ac1d32d5dfe453
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:114f02ccdf376179787d9b9a595e5a6ee234fa37f65747584aeac8e390b85d72
+oid sha256:7d143b857efe9b2f5e9e5f3317722527032a2ebf78aea15c1a29bea382f3d58b
 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": 0.678810179233551,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.038834951456310676,
+  "best_metric": 0.5158158540725708,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.07766990291262135,
   "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": 12.619,
       "eval_steps_per_second": 3.198,
       "step": 10
+    },
+    {
+      "epoch": 0.04660194174757282,
+      "grad_norm": 2.3093507289886475,
+      "learning_rate": 0.000163742398974869,
+      "loss": 2.4677,
+      "step": 12
+    },
+    {
+      "epoch": 0.05825242718446602,
+      "grad_norm": 1.2664294242858887,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.2427,
+      "step": 15
+    },
+    {
+      "epoch": 0.05825242718446602,
+      "eval_loss": 0.5657013654708862,
+      "eval_runtime": 17.2405,
+      "eval_samples_per_second": 12.587,
+      "eval_steps_per_second": 3.19,
+      "step": 15
+    },
+    {
+      "epoch": 0.06990291262135923,
+      "grad_norm": 1.203683853149414,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.3629,
+      "step": 18
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "eval_loss": 0.5158158540725708,
+      "eval_runtime": 17.1662,
+      "eval_samples_per_second": 12.641,
+      "eval_steps_per_second": 3.204,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.26956599246848e+16,
+  "total_flos": 2.53913198493696e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null