Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bb0bcb5b27d66cb7df592bad8abc64f9720572260b76dfa6957fdfb66160c24
+oid sha256:e554fe0576476e10d81b30240b7ebb6bf7e11918985a67e48c7c8cc9837e79c1
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ace909af57d97d3f3a923620da76d0bb662d6a64a800ff2bcc099d13eec6e1a5
+oid sha256:50288d58a8d08bd24d1f68eacae08eea637c1d00944122fd1caf838d65343bb7
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96d390a5a03bf54a286ea419b3804b61d765f6a45256de035d98c9791a0ea9b2
+oid sha256:e7398c4730b443a556b0f3765250cdc5b60e639de3117d0b5766017dd403aff5
 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": 2.960925817489624,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.011560693641618497,
+  "best_metric": 2.750244379043579,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.023121387283236993,
   "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": 37.518,
       "eval_steps_per_second": 18.811,
       "step": 10
+    },
+    {
+      "epoch": 0.013872832369942197,
+      "grad_norm": 7.719348907470703,
+      "learning_rate": 0.000163742398974869,
+      "loss": 2.4484,
+      "step": 12
+    },
+    {
+      "epoch": 0.017341040462427744,
+      "grad_norm": 9.678977012634277,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.8573,
+      "step": 15
+    },
+    {
+      "epoch": 0.017341040462427744,
+      "eval_loss": 2.837536096572876,
+      "eval_runtime": 10.103,
+      "eval_samples_per_second": 36.128,
+      "eval_steps_per_second": 18.113,
+      "step": 15
+    },
+    {
+      "epoch": 0.020809248554913295,
+      "grad_norm": 5.845253944396973,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.6995,
+      "step": 18
+    },
+    {
+      "epoch": 0.023121387283236993,
+      "eval_loss": 2.750244379043579,
+      "eval_runtime": 9.6981,
+      "eval_samples_per_second": 37.636,
+      "eval_steps_per_second": 18.87,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 180238575206400.0,
+  "total_flos": 360477150412800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null