Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cc11a708f3fd42f74bab82cbfcc569b31df94372c8fc095298c6abed55563e0
+oid sha256:d08c29a581b7495b98db6669e8b0eb0a2e11cbf0df40c0f771ca78647e8894d4
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cacdaa0771f2e960635a3c20dcc870763e627a7cf795fe81d2c1466373d434cc
+oid sha256:8341503acd91b0398a249a6b1ca19c925bba5279ad8f0ee3e23b108a5e4a1a05
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:911d88406a5628edb0f5bfb3cf2e86ec85008521b75615ca6b5996d3f37e81b8
+oid sha256:d5e017601a85b1ad744d7bf8dc4ff27aac026cd55e1155e549fe88ac679a9134
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba316ec96e6c10e041a852d2cc4f3336f45d4c5889e07910766cddeb5a8ea440
+oid sha256:90450db20f965e5463684029a88340d224d3fb2689f6532511f6579867f35119
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.0686392784118652,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.004515182300485382,
+  "best_metric": 2.9804024696350098,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.006772773450728073,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 50.395,
       "eval_steps_per_second": 12.602,
       "step": 100
+    },
+    {
+      "epoch": 0.004966700530533921,
+      "grad_norm": 6.514296531677246,
+      "learning_rate": 0.00019613840940836658,
+      "loss": 2.8477,
+      "step": 110
+    },
+    {
+      "epoch": 0.005418218760582459,
+      "grad_norm": 4.205728054046631,
+      "learning_rate": 0.00019300212826804002,
+      "loss": 2.9135,
+      "step": 120
+    },
+    {
+      "epoch": 0.005869736990630997,
+      "grad_norm": 3.894537925720215,
+      "learning_rate": 0.00018942492985603364,
+      "loss": 2.8827,
+      "step": 130
+    },
+    {
+      "epoch": 0.006321255220679535,
+      "grad_norm": 5.284046173095703,
+      "learning_rate": 0.0001854242419234321,
+      "loss": 3.052,
+      "step": 140
+    },
+    {
+      "epoch": 0.006772773450728073,
+      "grad_norm": 5.975098609924316,
+      "learning_rate": 0.00018101955541969522,
+      "loss": 3.3612,
+      "step": 150
+    },
+    {
+      "epoch": 0.006772773450728073,
+      "eval_loss": 2.9804024696350098,
+      "eval_runtime": 183.7514,
+      "eval_samples_per_second": 50.753,
+      "eval_steps_per_second": 12.691,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 905698840412160.0,
+  "total_flos": 1356295278428160.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null