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:fc0c99f4bdba2c20da46869fe9665f7e5ec2d3bf7f115392dbdc0d4d33556d1f
+oid sha256:1ab1de3dc5532b12edc087bfc6f5a4a67bbb98dfff07df6284ca66cbe027fd19
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9034ad05d7b7c67ff80ee8b114a1adad3132801520a95013438cd92c94a11c0
+oid sha256:641321c11dfd02079a9b57a6c891d6eeaff680725e42e7966ef9cea3d2a2042b
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d34319ff3df364313deadc6fed2a87af4dbaa25121577034e823762746bfdd8
+oid sha256:329800dec371ab8e9327d68e238f9ae91d404b8c18bfc75279f39dafcb010761
 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": 2.5634732246398926,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.019603038470963,
+  "best_metric": 2.5440735816955566,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.029404557706444498,
   "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": 109.392,
       "eval_steps_per_second": 54.696,
       "step": 20
+    },
+    {
+      "epoch": 0.02058319039451115,
+      "grad_norm": 0.8678022623062134,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 2.6216,
+      "step": 21
+    },
+    {
+      "epoch": 0.0235236461651556,
+      "grad_norm": 0.7674933075904846,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 2.4564,
+      "step": 24
+    },
+    {
+      "epoch": 0.02450379808870375,
+      "eval_loss": 2.547071933746338,
+      "eval_runtime": 3.9551,
+      "eval_samples_per_second": 108.72,
+      "eval_steps_per_second": 54.36,
+      "step": 25
+    },
+    {
+      "epoch": 0.02646410193580005,
+      "grad_norm": 0.7818556427955627,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 2.5608,
+      "step": 27
+    },
+    {
+      "epoch": 0.029404557706444498,
+      "grad_norm": 0.6539798974990845,
+      "learning_rate": 0.0,
+      "loss": 2.5075,
+      "step": 30
+    },
+    {
+      "epoch": 0.029404557706444498,
+      "eval_loss": 2.5440735816955566,
+      "eval_runtime": 3.9731,
+      "eval_samples_per_second": 108.228,
+      "eval_steps_per_second": 54.114,
+      "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": 138837586083840.0,
+  "total_flos": 208256379125760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null