Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ced0593805a48bad804cc1fd0a543aeb3b196dc720b8018d949a198f64263e83
+oid sha256:b218bfb01580e03be44ca48b3a7796be0d9cc23fde2adf54d7ca840c442a90e9
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62e4eebe8b4a7b6d054c6eb7a11879998db3b193d6e5681df3ab43984db9d1a0
+oid sha256:89338a1e7e3c931a3f388f9d7f975a3c55792f6048c00706fc44cb172274658a
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e31a0db1fe901aae8d342a723e96edfbdf00ec59df64e785ff59a6a197f3a04
+oid sha256:95226b9443ed4e38c27bbb8187789d508a89cfc90744595951e5068e3128acf8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5ad005f18ad2c3c460e78d824d33373300bb1b0c9741a994c687b284a694890
+oid sha256:c9b2510d4f3300d86de2c5b705a4b3113b18ea2234bf5e3432bd4dee5175a4db
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.35675832629203796,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.175054704595186,
+  "best_metric": 0.3523136377334595,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.2188183807439825,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 10.043,
       "eval_steps_per_second": 2.526,
       "step": 200
+    },
+    {
+      "epoch": 0.1838074398249453,
+      "grad_norm": 0.5258771777153015,
+      "learning_rate": 0.00014599467139909136,
+      "loss": 0.7887,
+      "step": 210
+    },
+    {
+      "epoch": 0.1925601750547046,
+      "grad_norm": 0.5954610109329224,
+      "learning_rate": 0.0001395225692317151,
+      "loss": 0.7499,
+      "step": 220
+    },
+    {
+      "epoch": 0.2013129102844639,
+      "grad_norm": 0.0030906260944902897,
+      "learning_rate": 0.00013286522492905717,
+      "loss": 0.1606,
+      "step": 230
+    },
+    {
+      "epoch": 0.2100656455142232,
+      "grad_norm": 0.0038282345049083233,
+      "learning_rate": 0.00012605507240336626,
+      "loss": 0.0009,
+      "step": 240
+    },
+    {
+      "epoch": 0.2188183807439825,
+      "grad_norm": 0.01913132704794407,
+      "learning_rate": 0.00011912529003319345,
+      "loss": 0.0004,
+      "step": 250
+    },
+    {
+      "epoch": 0.2188183807439825,
+      "eval_loss": 0.3523136377334595,
+      "eval_runtime": 48.1668,
+      "eval_samples_per_second": 9.986,
+      "eval_steps_per_second": 2.512,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.540687952576512e+16,
+  "total_flos": 8.17585994072064e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null