Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75a93e45c1f01388d9539e48222ef23f466237ddadc885bb927717da0d88fc24
+oid sha256:2e60d5a23036bb878f2cf414a1a49695b751ae35f90e679de534badfd25c475c
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:646d30f08586a0139e83faf69d63be0f7b3e569c0d4c88edbd577762ea49f153
+oid sha256:54b27a1e9ccf6d03bf55747bdeebd28cdbb88b96eb97dfc7b1b53e6cc7278a99
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9074ae6aafc288ba48f3235cf837ad0748ddbeb4ecc5d9e672928c3244deb8e8
+oid sha256:9b59dc21d3c08f7c0f871508eb3bdbfe87460e84a04c7ce907d9b4f7b519baa1
 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": 1.2044516801834106,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.013689253935660506,
+  "best_metric": 1.1420856714248657,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.02737850787132101,
   "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": 30.722,
       "eval_steps_per_second": 7.693,
       "step": 10
+    },
+    {
+      "epoch": 0.01642710472279261,
+      "grad_norm": 0.4068310856819153,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.9677,
+      "step": 12
+    },
+    {
+      "epoch": 0.02053388090349076,
+      "grad_norm": 0.44693639874458313,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.0655,
+      "step": 15
+    },
+    {
+      "epoch": 0.02053388090349076,
+      "eval_loss": 1.1659916639328003,
+      "eval_runtime": 20.3609,
+      "eval_samples_per_second": 30.205,
+      "eval_steps_per_second": 7.564,
+      "step": 15
+    },
+    {
+      "epoch": 0.024640657084188913,
+      "grad_norm": 0.48836642503738403,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.1105,
+      "step": 18
+    },
+    {
+      "epoch": 0.02737850787132101,
+      "eval_loss": 1.1420856714248657,
+      "eval_runtime": 20.2233,
+      "eval_samples_per_second": 30.41,
+      "eval_steps_per_second": 7.615,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1040301762281472.0,
+  "total_flos": 2008024331845632.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null