Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c9a621f88f72c3bcbcaedd9a4406110d9faa23700e775868b6941da1d9680b7
+oid sha256:109f85a8a6aae19a8283d64bbbd499c660468d93c34c505eaeed2472374c6c79
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0d4a4ea1a2152cc922f7e7a6fce560f771c9c83a4efecc0fd24c536d0d4d57
+oid sha256:859739c467e69200ac256415c2558cbaaa82138cbfaeb2bb61fc6744dab58596
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e858221bc1c52bb92b57bd79de8d7f60bcb9ada7c362a506059572563943da5d
+oid sha256:2d21aa072b3bf17a29e473aa0967bf113e0eabd6990ff76f63b1925aca7670d7
 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": 2.438471555709839,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.043149946062567425,
+  "best_metric": 1.959831714630127,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.08629989212513485,
   "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": 10.273,
       "eval_steps_per_second": 2.581,
       "step": 10
+    },
+    {
+      "epoch": 0.05177993527508091,
+      "grad_norm": 3.322448492050171,
+      "learning_rate": 0.000163742398974869,
+      "loss": 9.0185,
+      "step": 12
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": 3.0929150581359863,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 8.532,
+      "step": 15
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "eval_loss": 2.1120529174804688,
+      "eval_runtime": 18.9051,
+      "eval_samples_per_second": 10.315,
+      "eval_steps_per_second": 2.592,
+      "step": 15
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 3.2946879863739014,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 8.1404,
+      "step": 18
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "eval_loss": 1.959831714630127,
+      "eval_runtime": 18.9926,
+      "eval_samples_per_second": 10.267,
+      "eval_steps_per_second": 2.58,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3684183016734720.0,
+  "total_flos": 7368366033469440.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null