Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e15be16ca9a8b7e10973501ae21366c6ea679cb13dcbebdbc0c5cce6b138bd8
+oid sha256:fd3c1da81c14a0db55be0c24ecd79049b791440c9aa7efb2574a0640ec52a35c
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5e1fc06fd6e7ae4d7d978213db8b9b94d9313116ef2d1740129d25af8e9644f
+oid sha256:2ff858ec7126944f018edd4f087d64e9b28884c9feda06ffc5fb381681f173fb
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e0a757ffe6c9fcd3b1bf3120b902f92c3aa5d6542e79c5ea824ded072ba2b1f
+oid sha256:aa0de0c32bf94efe74fce56eafc87e41e69cc5016d5c33867cf1c8934b8875ce
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cd62d399a2450f21c7bec0f65f92f467b6df40bae3ff61b19e25062ffc80260
+oid sha256:292f236c37f22c287cc737dd1428bf82b9a9008a84eb2f517544aab166f8a97f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2346261739730835,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.10474860335195531,
+  "best_metric": 1.2006936073303223,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.13966480446927373,
   "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": 11.637,
       "eval_steps_per_second": 2.914,
       "step": 150
+    },
+    {
+      "epoch": 0.11173184357541899,
+      "grad_norm": 0.4873850345611572,
+      "learning_rate": 0.00018654836833674362,
+      "loss": 0.9312,
+      "step": 160
+    },
+    {
+      "epoch": 0.11871508379888268,
+      "grad_norm": 0.4591498076915741,
+      "learning_rate": 0.0001811006707899361,
+      "loss": 0.8553,
+      "step": 170
+    },
+    {
+      "epoch": 0.12569832402234637,
+      "grad_norm": 0.44848743081092834,
+      "learning_rate": 0.0001752992700728339,
+      "loss": 0.8601,
+      "step": 180
+    },
+    {
+      "epoch": 0.13268156424581007,
+      "grad_norm": 0.49805349111557007,
+      "learning_rate": 0.00016917243002657602,
+      "loss": 0.7799,
+      "step": 190
+    },
+    {
+      "epoch": 0.13966480446927373,
+      "grad_norm": 1.24271821975708,
+      "learning_rate": 0.00016275,
+      "loss": 1.9841,
+      "step": 200
+    },
+    {
+      "epoch": 0.13966480446927373,
+      "eval_loss": 1.2006936073303223,
+      "eval_runtime": 51.8223,
+      "eval_samples_per_second": 11.636,
+      "eval_steps_per_second": 2.914,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.212345230327808e+16,
+  "total_flos": 5.652007524237312e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null