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:af0f7d6aef412434d9c9bf24cee05afaf6dc3a065e13be194c9c4f23814f1529
+oid sha256:823b060951cee39ab5e4119ad8ddede538a326033a84a669847251755e24ca5f
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49fb815279be831637421139660adb055ade028b0547401696d1094a245ffe8c
+oid sha256:c45e2b976154527203598cb4deffca1de6101e6d25b0c56bb4492b2ce7900d84
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:055fc4e3f439badff3bfb0dcc78d2c4ad7e062217a4c357b3bdb340474e67d2c
+oid sha256:8cd8a31ef8ab595f5e259f41cd65e0c690a67b5797731dd7b7754a8fa1b2a5c8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87bb1aa192c7f9c0516bbbf45e738ece50573944baeb2415a4a135a1ac346045
+oid sha256:5220d0af0ff98b2d6e04334f1c29842da7230747bf3383cf1f883a4d2eb6d4f2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9036096930503845,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.2178649237472767,
+  "best_metric": 0.8491891622543335,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.32679738562091504,
   "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": 12.868,
       "eval_steps_per_second": 3.283,
       "step": 100
+    },
+    {
+      "epoch": 0.23965141612200436,
+      "grad_norm": 7.476004123687744,
+      "learning_rate": 5.095e-06,
+      "loss": 1.0529,
+      "step": 110
+    },
+    {
+      "epoch": 0.26143790849673204,
+      "grad_norm": 7.453296184539795,
+      "learning_rate": 4.5288888888888885e-06,
+      "loss": 0.9474,
+      "step": 120
+    },
+    {
+      "epoch": 0.28322440087145967,
+      "grad_norm": 8.616524696350098,
+      "learning_rate": 3.9627777777777784e-06,
+      "loss": 0.7555,
+      "step": 130
+    },
+    {
+      "epoch": 0.30501089324618735,
+      "grad_norm": 9.001409530639648,
+      "learning_rate": 3.3966666666666666e-06,
+      "loss": 0.8331,
+      "step": 140
+    },
+    {
+      "epoch": 0.32679738562091504,
+      "grad_norm": 9.718732833862305,
+      "learning_rate": 2.830555555555556e-06,
+      "loss": 0.7389,
+      "step": 150
+    },
+    {
+      "epoch": 0.32679738562091504,
+      "eval_loss": 0.8491891622543335,
+      "eval_runtime": 11.2774,
+      "eval_samples_per_second": 12.858,
+      "eval_steps_per_second": 3.281,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.678722527441715e+16,
+  "total_flos": 4.004822788551475e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null