Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e77cf09633e3bda1cee312fafc1063497a8fe3974ec29222db5358a1033149d
+oid sha256:2384c0aaf94d8aa52dbe4a83303cac3cff37f50a40703c88d74abfc82b479907
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88e9f7f39886cb0d6f8b5465fc0733183e1b98b72232dabaa4b3aad0199cfd47
+oid sha256:d8b9427e187c9ffc1df90f97f3d161c037369b501aa3c0979ccf45b6510bade9
 size 68874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
+oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d46ef0f8a7945706ef65ae5e8be31402361869b6b4c8ecb8ef0263696377404
+oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.934170722961426,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0029614274080106613,
+  "best_metric": 11.933917999267578,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0059228548160213225,
   "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": 88.976,
       "eval_steps_per_second": 44.488,
       "step": 10
+    },
+    {
+      "epoch": 0.0035537128896127933,
+      "grad_norm": 0.05989011749625206,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 11.932,
+      "step": 12
+    },
+    {
+      "epoch": 0.004442141112015992,
+      "grad_norm": 0.037861209362745285,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.9359,
+      "step": 15
+    },
+    {
+      "epoch": 0.004442141112015992,
+      "eval_loss": 11.934015274047852,
+      "eval_runtime": 16.0398,
+      "eval_samples_per_second": 88.654,
+      "eval_steps_per_second": 44.327,
+      "step": 15
+    },
+    {
+      "epoch": 0.00533056933441919,
+      "grad_norm": 0.033359162509441376,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 11.9323,
+      "step": 18
+    },
+    {
+      "epoch": 0.0059228548160213225,
+      "eval_loss": 11.933917999267578,
+      "eval_runtime": 15.97,
+      "eval_samples_per_second": 89.042,
+      "eval_steps_per_second": 44.521,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3747348480.0,
+  "total_flos": 7494696960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null