Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2b7fab8e5c707684dd7dcf2acfeef02dc66a45c810d37881d6d35ab0138813e
+oid sha256:b9ac74b39f72854d193986d03bc840a1c04412975226a003ddf6f9712ea85a29
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cadb54f5b4b7cf6e5570f8b8aa5d66a30d9e31f2de3c6b5c891900bdb9053acc
+oid sha256:543b0438259af00bb05f335870bb7e86c3bf831f69c1ab4c7de1da70e4df1a1a
 size 418030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:039fcb416f3a29717abd0881d31fed0ae41a339ceb603e8a0d9a2989535c8efc
+oid sha256:a0fa569ae9431ecec1ad250d458bd97a0680dbd03fc69e453a6363003309127e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:921ab0de3764126581ec39378879cb5b5f7b00db4d38a319c5350418d3b5b284
+oid sha256:25f5be5717b8cedfd0ed40abce613b5b748b90320bdb20c1f1ab3a4f8a9f9654
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.850296497344971,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 1.4527845036319613,
+  "best_metric": 6.843703746795654,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 1.937046004842615,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,21 @@
       "eval_samples_per_second": 1326.165,
       "eval_steps_per_second": 41.979,
       "step": 150
+    },
+    {
+      "epoch": 1.937046004842615,
+      "grad_norm": 0.13267219066619873,
+      "learning_rate": 0.000202,
+      "loss": 6.8475,
+      "step": 200
+    },
+    {
+      "epoch": 1.937046004842615,
+      "eval_loss": 6.843703746795654,
+      "eval_runtime": 0.7287,
+      "eval_samples_per_second": 953.768,
+      "eval_steps_per_second": 30.191,
+      "step": 200
     }
   ],
   "logging_steps": 50,
@@ -88,7 +103,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6325423902720.0,
+  "total_flos": 8430294306816.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null