Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8588b129197ba536e22f31768f7613f554c8e309180200a4d0029f902770f333
+oid sha256:ced0593805a48bad804cc1fd0a543aeb3b196dc720b8018d949a198f64263e83
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2ceda64f9b4bc13464e324f76e252bd7a0e47d2990afd2ae8fb10963c35d06e
+oid sha256:62e4eebe8b4a7b6d054c6eb7a11879998db3b193d6e5681df3ab43984db9d1a0
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2b8943e674f8bbdced045cb2530ea33584297335f08ea6bc4a911f482fdfb11
+oid sha256:4e31a0db1fe901aae8d342a723e96edfbdf00ec59df64e785ff59a6a197f3a04
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e883b7b3f89fde3f0f981a15cfeb8504571510ffa0b99f735bed98a1fe00478
+oid sha256:d5ad005f18ad2c3c460e78d824d33373300bb1b0c9741a994c687b284a694890
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.36381667852401733,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.13129102844638948,
+  "best_metric": 0.35675832629203796,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.175054704595186,
   "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": 9.996,
       "eval_steps_per_second": 2.515,
       "step": 150
+    },
+    {
+      "epoch": 0.1400437636761488,
+      "grad_norm": 0.5591445565223694,
+      "learning_rate": 0.00017451298973437308,
+      "loss": 0.9412,
+      "step": 160
+    },
+    {
+      "epoch": 0.1487964989059081,
+      "grad_norm": 0.30725646018981934,
+      "learning_rate": 0.0001694167565454241,
+      "loss": 0.4974,
+      "step": 170
+    },
+    {
+      "epoch": 0.1575492341356674,
+      "grad_norm": 0.11813530325889587,
+      "learning_rate": 0.0001639896397455543,
+      "loss": 0.0992,
+      "step": 180
+    },
+    {
+      "epoch": 0.16630196936542668,
+      "grad_norm": 0.009045140817761421,
+      "learning_rate": 0.0001582580797022808,
+      "loss": 0.0109,
+      "step": 190
+    },
+    {
+      "epoch": 0.175054704595186,
+      "grad_norm": 0.017792249098420143,
+      "learning_rate": 0.00015225,
+      "loss": 0.0007,
+      "step": 200
+    },
+    {
+      "epoch": 0.175054704595186,
+      "eval_loss": 0.35675832629203796,
+      "eval_runtime": 47.8961,
+      "eval_samples_per_second": 10.043,
+      "eval_steps_per_second": 2.526,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.905515964432384e+16,
+  "total_flos": 6.540687952576512e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null