Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37e6870880a5ad8d93831dad4bce06aa97558937878d00882402d01df9a2401f
+oid sha256:093105308a7694d730e44a7d62f0919f6bb60c325d766ddeb327bd7ece979d2f
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03401dc0aa15e6b55de1ab2a27609ff9cd74a3224d8b8a530bffa0cb81628ab8
+oid sha256:15041c809b081b7b14e26d6fc6c3b98e27ce2bb9fc50fd6d50034c6ebcefd30d
 size 201478138

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d313fe8b97eb646cf518fab58b5d077a385b0d98110cb7bab5cfdfdaa5f86e5
+oid sha256:ac98c838dccd074639e114ecbed2f841eacd1e9db79cae3f20d1b456849c607e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0656561851501465,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0016284324302318482,
+  "best_metric": 2.0538229942321777,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.002442648645347772,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 5.805,
       "eval_steps_per_second": 2.903,
       "step": 20
+    },
+    {
+      "epoch": 0.0017098540517434405,
+      "grad_norm": 1.0811505317687988,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 8.3596,
+      "step": 21
+    },
+    {
+      "epoch": 0.0019541189162782177,
+      "grad_norm": 1.0642000436782837,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 8.0844,
+      "step": 24
+    },
+    {
+      "epoch": 0.0020355405377898103,
+      "eval_loss": 2.055866003036499,
+      "eval_runtime": 890.5227,
+      "eval_samples_per_second": 5.808,
+      "eval_steps_per_second": 2.904,
+      "step": 25
+    },
+    {
+      "epoch": 0.002198383780812995,
+      "grad_norm": 1.077531099319458,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 8.3103,
+      "step": 27
+    },
+    {
+      "epoch": 0.002442648645347772,
+      "grad_norm": 1.0193705558776855,
+      "learning_rate": 0.0,
+      "loss": 8.3276,
+      "step": 30
+    },
+    {
+      "epoch": 0.002442648645347772,
+      "eval_loss": 2.0538229942321777,
+      "eval_runtime": 890.5686,
+      "eval_samples_per_second": 5.808,
+      "eval_steps_per_second": 2.904,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5065751648010240.0,
+  "total_flos": 7460470608887808.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null