Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20d80a7e2a4a5ff16db0855f0a03950b1d5d9a6b83c296181e1be52f79cfc1da
+oid sha256:2cc11a708f3fd42f74bab82cbfcc569b31df94372c8fc095298c6abed55563e0
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792e6747813b3c9512bf77221dec092119a62f7f4dbeacea2b647f0c31efb374
+oid sha256:cacdaa0771f2e960635a3c20dcc870763e627a7cf795fe81d2c1466373d434cc
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a89dcb167b99d28b2e9bbc7f35db8cd35eadc2cc0b39b76c7a5083937d27592
+oid sha256:911d88406a5628edb0f5bfb3cf2e86ec85008521b75615ca6b5996d3f37e81b8
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27e650fa00c2750be5e3ef893e2145c3f44fe2add3bc0ce842bd38e59c89f1ec
+oid sha256:ba316ec96e6c10e041a852d2cc4f3336f45d4c5889e07910766cddeb5a8ea440
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.3135757446289062,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.002257591150242691,
+  "best_metric": 3.0686392784118652,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.004515182300485382,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 50.198,
       "eval_steps_per_second": 12.552,
       "step": 50
+    },
+    {
+      "epoch": 0.0027091093802912294,
+      "grad_norm": 4.627725601196289,
+      "learning_rate": 0.00020475031515163197,
+      "loss": 3.1244,
+      "step": 60
+    },
+    {
+      "epoch": 0.0031606276103397675,
+      "grad_norm": 4.629662990570068,
+      "learning_rate": 0.00020400247704601096,
+      "loss": 3.0593,
+      "step": 70
+    },
+    {
+      "epoch": 0.0036121458403883056,
+      "grad_norm": 4.690089225769043,
+      "learning_rate": 0.00020276012907521508,
+      "loss": 2.9041,
+      "step": 80
+    },
+    {
+      "epoch": 0.004063664070436844,
+      "grad_norm": 5.650446891784668,
+      "learning_rate": 0.00020102932383367768,
+      "loss": 2.7957,
+      "step": 90
+    },
+    {
+      "epoch": 0.004515182300485382,
+      "grad_norm": 6.984936237335205,
+      "learning_rate": 0.00019881849363055561,
+      "loss": 3.173,
+      "step": 100
+    },
+    {
+      "epoch": 0.004515182300485382,
+      "eval_loss": 3.0686392784118652,
+      "eval_runtime": 185.0562,
+      "eval_samples_per_second": 50.395,
+      "eval_steps_per_second": 12.602,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 455102402396160.0,
+  "total_flos": 905698840412160.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null