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:a252fac8ad2ad861a2699585dd771f1be1093e0799f8e440ababf1b1cf7566d4
+oid sha256:e397edbff90f4c265b4b7da104ee82726538bb19f43cf520b077c88744bc2e5c
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efb1fc9d46e3a41eddc973c03b5a13db8c35bcaeaaca5830db31260ce3c5f107
+oid sha256:aeb1c01d8ec3b0f0b98281542fc77de589dd0b71493c88a25102769f6f07d02e
 size 418030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:953d13a07631d6b84b089a0fba90cdb770c128c831c2d0e01869712cc64772bb
+oid sha256:57ebc46305e8b6569c846fc940c43a19a3b6d56111192e167f8fbf40669c9c6b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20b846236f686f34a315088700cd866bd66ffc165610b7eec245275ac6103428
+oid sha256:0b764a7feea336c9409f04ca3df4d8b4349bea019384446d21739ad3565001bd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.80977725982666,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.04705328784848841,
+  "best_metric": 6.803854465484619,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.058816609810610515,
   "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": 557.461,
       "eval_steps_per_second": 139.521,
       "step": 200
+    },
+    {
+      "epoch": 0.049405952240912834,
+      "grad_norm": 0.6835295557975769,
+      "learning_rate": 0.00015390571270643128,
+      "loss": 6.8697,
+      "step": 210
+    },
+    {
+      "epoch": 0.05175861663333725,
+      "grad_norm": 0.723054826259613,
+      "learning_rate": 0.0001470829054955026,
+      "loss": 6.8365,
+      "step": 220
+    },
+    {
+      "epoch": 0.054111281025761675,
+      "grad_norm": 0.6531696319580078,
+      "learning_rate": 0.00014006481839811937,
+      "loss": 6.8019,
+      "step": 230
+    },
+    {
+      "epoch": 0.0564639454181861,
+      "grad_norm": 0.5882543921470642,
+      "learning_rate": 0.00013288564282916442,
+      "loss": 6.7801,
+      "step": 240
+    },
+    {
+      "epoch": 0.058816609810610515,
+      "grad_norm": 0.7119730710983276,
+      "learning_rate": 0.00012558035501036158,
+      "loss": 6.7837,
+      "step": 250
+    },
+    {
+      "epoch": 0.058816609810610515,
+      "eval_loss": 6.803854465484619,
+      "eval_runtime": 3.3022,
+      "eval_samples_per_second": 542.059,
+      "eval_steps_per_second": 135.666,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 480564019200.0,
+  "total_flos": 600705024000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null