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:d8cc44a1282136c3fc49d58e2b03de72f5daeaf8cef6fce1d5642a7641f79ef9
+oid sha256:1adfc6515b1e67ae439537859c9465f29dc8628bab6a94caf80a88046880fa87
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0309bc971930d54a8beb2a07f535d85f0dd8c8336c530f70c6ca0ca48a5b41c0
+oid sha256:97291eda5ca6f3cb63e5be95416d00d6c51f61b9a8913fa4b66b2362b58c68b3
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dda92d25f1cd844c47237a59d93afe6104deb8d34274403f432b7801160f3a4
+oid sha256:38220ad448edaad4525c57c063299252bbf6f342fd28b6412a1850b27989a0da
 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": 1.9224990606307983,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.09302325581395349,
+  "best_metric": 1.7479033470153809,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.18604651162790697,
   "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": 4.235,
       "eval_steps_per_second": 1.07,
       "step": 10
+    },
+    {
+      "epoch": 0.11162790697674418,
+      "grad_norm": 0.5291640758514404,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.9079,
+      "step": 12
+    },
+    {
+      "epoch": 0.13953488372093023,
+      "grad_norm": 0.4846174418926239,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.7631,
+      "step": 15
+    },
+    {
+      "epoch": 0.13953488372093023,
+      "eval_loss": 1.8105331659317017,
+      "eval_runtime": 21.5003,
+      "eval_samples_per_second": 4.232,
+      "eval_steps_per_second": 1.07,
+      "step": 15
+    },
+    {
+      "epoch": 0.16744186046511628,
+      "grad_norm": 0.5171637535095215,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.7568,
+      "step": 18
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "eval_loss": 1.7479033470153809,
+      "eval_runtime": 21.5065,
+      "eval_samples_per_second": 4.231,
+      "eval_steps_per_second": 1.069,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.26648217239552e+16,
+  "total_flos": 2.53296434479104e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null