Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17467b2787fa0b6c45330338966e03dde30efa4376dcca84a3e82b047387689b
+oid sha256:aa894ee32425518a3ee9a468ac21c436055bb2433a014cb978e6085c5ba57aa9
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dc47276b078476fe94c154d86f218a1df46b0d9967e7455a47caa49723df650
+oid sha256:d249d02bd710b3b3de8f049e739adeb5e7a445f7d5ee9527135bf24c656c0761
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1a68088fe2a09b17969078c90ec4e6c0082b31cb5cef241b0d3930254d8f326
+oid sha256:cb5474b8229a1c766aba0c2731c5d108f3b3249228ece3b9cf0d9dbaba3e98a6
 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": 1.9791643619537354,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0010375865736297373,
+  "best_metric": 1.9425504207611084,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0020751731472594746,
   "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": 18.633,
       "eval_steps_per_second": 9.317,
       "step": 10
+    },
+    {
+      "epoch": 0.0012451038883556846,
+      "grad_norm": 0.7417125105857849,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 1.9186,
+      "step": 12
+    },
+    {
+      "epoch": 0.0015563798604446059,
+      "grad_norm": 0.8706774711608887,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.9334,
+      "step": 15
+    },
+    {
+      "epoch": 0.0015563798604446059,
+      "eval_loss": 1.9557490348815918,
+      "eval_runtime": 219.1222,
+      "eval_samples_per_second": 18.519,
+      "eval_steps_per_second": 9.26,
+      "step": 15
+    },
+    {
+      "epoch": 0.0018676558325335271,
+      "grad_norm": 0.9030641317367554,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 1.9011,
+      "step": 18
+    },
+    {
+      "epoch": 0.0020751731472594746,
+      "eval_loss": 1.9425504207611084,
+      "eval_runtime": 218.7571,
+      "eval_samples_per_second": 18.55,
+      "eval_steps_per_second": 9.275,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 360477150412800.0,
+  "total_flos": 720954300825600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null