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:fe3ad8513eb75dc736315b7297998bf158e5e0527bfe7611c312479de6b290be
+oid sha256:bef8ebf1df6a6ec9f1b8e32b71d9e7d0bebab76f75a97e806fa076f1182a760f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81c42d2bbf0fd47b45c80cf54b3c4c03a05bfa8d807512c99116751a23b1d5eb
+oid sha256:7728e177154698c4a2b34404ef45caabd1d4968ffb9210b173fcb580206e3776
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
+oid sha256:5e4bf376a26ef3a41f31841495fb80208a94d06a0cd262d9065eabcdfb519878
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.1887054443359375,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0009422517461102671,
+  "best_metric": 2.177536964416504,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0014133776191654005,
   "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": 4.68,
       "eval_steps_per_second": 2.34,
       "step": 20
+    },
+    {
+      "epoch": 0.0009893643334157804,
+      "grad_norm": 0.680305540561676,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 2.1851,
+      "step": 21
+    },
+    {
+      "epoch": 0.0011307020953323205,
+      "grad_norm": 0.6678304076194763,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 2.2019,
+      "step": 24
+    },
+    {
+      "epoch": 0.0011778146826378337,
+      "eval_loss": 2.1794984340667725,
+      "eval_runtime": 1908.038,
+      "eval_samples_per_second": 4.684,
+      "eval_steps_per_second": 2.342,
+      "step": 25
+    },
+    {
+      "epoch": 0.0012720398572488604,
+      "grad_norm": 0.6334486603736877,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 2.149,
+      "step": 27
+    },
+    {
+      "epoch": 0.0014133776191654005,
+      "grad_norm": 0.5381951928138733,
+      "learning_rate": 0.0,
+      "loss": 2.1624,
+      "step": 30
+    },
+    {
+      "epoch": 0.0014133776191654005,
+      "eval_loss": 2.177536964416504,
+      "eval_runtime": 1909.3608,
+      "eval_samples_per_second": 4.681,
+      "eval_steps_per_second": 2.341,
+      "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": 7418872835604480.0,
+  "total_flos": 1.1221045163851776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null