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:a3f2cddb8f6c16e14506f61398315e8e8559ddacc3052958c6153f0540be94b8
+oid sha256:79b3a8adb495844460687cdda7393b7f6882253643fe5c3e502ba09e9e9a7eae
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5b6bb58c5fa8610d53560451fd5fa4ff03ef54b31d2072db966f8cb587e4ede
+oid sha256:5e15cbd9c4290d97da5f63770a17d342607e37354129ed5e894a1cf2ba85fde7
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d33f40e184a7f09f8d6e363ab40199a15752564119d3f3f5ab0b52f362e665
+oid sha256:2402ffa6243bb683b0930892d69f33711f15bf87d32f7c393ad127e2ae07522e
 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": 10.363765716552734,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0005955482766321745,
+  "best_metric": 10.345518112182617,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.001191096553264349,
   "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": 76.165,
       "eval_steps_per_second": 38.082,
       "step": 10
+    },
+    {
+      "epoch": 0.0007146579319586094,
+      "grad_norm": 0.5134620666503906,
+      "learning_rate": 0.000163742398974869,
+      "loss": 10.3646,
+      "step": 12
+    },
+    {
+      "epoch": 0.0008933224149482617,
+      "grad_norm": 0.5371794104576111,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.358,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008933224149482617,
+      "eval_loss": 10.353273391723633,
+      "eval_runtime": 92.7021,
+      "eval_samples_per_second": 76.266,
+      "eval_steps_per_second": 38.133,
+      "step": 15
+    },
+    {
+      "epoch": 0.0010719868979379142,
+      "grad_norm": 0.5245136022567749,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 10.3507,
+      "step": 18
+    },
+    {
+      "epoch": 0.001191096553264349,
+      "eval_loss": 10.345518112182617,
+      "eval_runtime": 92.4325,
+      "eval_samples_per_second": 76.488,
+      "eval_steps_per_second": 38.244,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 523024465920.0,
+  "total_flos": 1046048931840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null