Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:059ce4ed2c9d66aae9a5b1d9259d0ad457f758d584c4c70839d2a88bd425c643
+oid sha256:c289e30570510bbc1fe85e9dddf1124d4d9d27faf279d8190146f74366c8b651
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d732afaad48d5e6aed85060472dfc79db03082b1d3265ec383946dcd1bea7407
+oid sha256:cba8757a8d8e46bfe8b5b599de3592a77eeada7a89782a524299c979ff1f6817
 size 71077780

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cd65248abd8d21605297ae218ac1c829d4870b341ac910ec1aa8438f48d86cc
+oid sha256:bc606b024f32950624832b549d8d615f8cbd0bf20ab17b21abbd312c0d57f4ca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4ffe1cc6011db9bcd26d2a5ee9a2f60bf90f43b3c6aed165ee32997fe344b31
+oid sha256:c41568ec8d15c28a2145796b65c5977bed142a18699c02f8db4b41d7a5440c4c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8461153507232666,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.00440257110152329,
+  "best_metric": 1.8115742206573486,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.005870094802031053,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 67.686,
       "eval_steps_per_second": 16.924,
       "step": 150
+    },
+    {
+      "epoch": 0.004696075841624842,
+      "grad_norm": 0.48622700572013855,
+      "learning_rate": 0.00018740803823691298,
+      "loss": 1.7917,
+      "step": 160
+    },
+    {
+      "epoch": 0.004989580581726395,
+      "grad_norm": 0.49764740467071533,
+      "learning_rate": 0.00018193523609311556,
+      "loss": 1.8452,
+      "step": 170
+    },
+    {
+      "epoch": 0.005283085321827948,
+      "grad_norm": 0.5556671619415283,
+      "learning_rate": 0.00017610710081049675,
+      "loss": 1.8311,
+      "step": 180
+    },
+    {
+      "epoch": 0.0055765900619295,
+      "grad_norm": 0.5455553531646729,
+      "learning_rate": 0.00016995202647831142,
+      "loss": 1.8376,
+      "step": 190
+    },
+    {
+      "epoch": 0.005870094802031053,
+      "grad_norm": 0.49670788645744324,
+      "learning_rate": 0.00016350000000000002,
+      "loss": 1.5889,
+      "step": 200
+    },
+    {
+      "epoch": 0.005870094802031053,
+      "eval_loss": 1.8115742206573486,
+      "eval_runtime": 210.7647,
+      "eval_samples_per_second": 68.066,
+      "eval_steps_per_second": 17.019,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2412693938503680.0,
+  "total_flos": 3219787284480000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null