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:f2a328f7538ed62618a15944f2ff9ac9bf0b1fdc35d78baa986f39e6c831fdda
+oid sha256:b263c0419ed83039a46b26b8f9d793ea2712fb7865c3f12ecd1b7f1e38fde191
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee0985c5c720d8e4373ad41439497a0f36acbdd939c199a6db5167f2be6b22f3
+oid sha256:04462b3e544232972eda8a566be5dbb0d9c037762956d0cde88f7ddc55f8c36f
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a850cc6eda316843b981d8bd2fc891e4769877ed1461a31c08af31fbf0c075d3
+oid sha256:e31e0fdb3869a241061ca27b64da9fbd0a58f71586f852b6544558cc627e89db
 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": 2.6880009174346924,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.001732051615138131,
+  "best_metric": 2.4166297912597656,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.003464103230276262,
   "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": 6.812,
       "eval_steps_per_second": 3.408,
       "step": 10
+    },
+    {
+      "epoch": 0.0020784619381657575,
+      "grad_norm": 4.757950305938721,
+      "learning_rate": 0.000163742398974869,
+      "loss": 2.4351,
+      "step": 12
+    },
+    {
+      "epoch": 0.002598077422707197,
+      "grad_norm": 3.0368690490722656,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.4886,
+      "step": 15
+    },
+    {
+      "epoch": 0.002598077422707197,
+      "eval_loss": 2.514369249343872,
+      "eval_runtime": 356.622,
+      "eval_samples_per_second": 6.817,
+      "eval_steps_per_second": 3.41,
+      "step": 15
+    },
+    {
+      "epoch": 0.003117692907248636,
+      "grad_norm": 3.3173792362213135,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.5876,
+      "step": 18
+    },
+    {
+      "epoch": 0.003464103230276262,
+      "eval_loss": 2.4166297912597656,
+      "eval_runtime": 356.3483,
+      "eval_samples_per_second": 6.822,
+      "eval_steps_per_second": 3.412,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3834471807713280.0,
+  "total_flos": 7668943615426560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null