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:ef448f02bfa0874d8b984dd7fea8948ca11655f23b7bd607cb738ceee5453c02
+oid sha256:6c8a6b00e5776cabadc4aa0084f5a1ad70e7e626836f9dd3ed82b99e9dd8f98e
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cef699405e3f3ff010fa2459093c116515d0495548b42175b88ce72dcea444c5
+oid sha256:076c8faefe4b7f4e7cfffd7e6c1f545ebe8b18bbff36a2f5be36df3586b0652d
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:895c063d601a85133104ef08e5880ca891f08de28269ee26dd5ffc2f63690c87
+oid sha256:23d0da5716a117590c76ee48240cb6d209a0b5465edb3c25b2fabc89c80cb9d7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8730665445327759,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.010591817820733483,
+  "best_metric": 1.775823950767517,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.015887726731100223,
   "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": 6.937,
       "eval_steps_per_second": 1.736,
       "step": 20
+    },
+    {
+      "epoch": 0.011121408711770158,
+      "grad_norm": 1.6087003946304321,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.7482,
+      "step": 21
+    },
+    {
+      "epoch": 0.01271018138488018,
+      "grad_norm": 1.8329598903656006,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.9398,
+      "step": 24
+    },
+    {
+      "epoch": 0.013239772275916854,
+      "eval_loss": 1.7912617921829224,
+      "eval_runtime": 231.298,
+      "eval_samples_per_second": 6.874,
+      "eval_steps_per_second": 1.721,
+      "step": 25
+    },
+    {
+      "epoch": 0.014298954057990202,
+      "grad_norm": 1.8112682104110718,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.9812,
+      "step": 27
+    },
+    {
+      "epoch": 0.015887726731100223,
+      "grad_norm": 1.7277368307113647,
+      "learning_rate": 0.0,
+      "loss": 1.9401,
+      "step": 30
+    },
+    {
+      "epoch": 0.015887726731100223,
+      "eval_loss": 1.775823950767517,
+      "eval_runtime": 232.2493,
+      "eval_samples_per_second": 6.846,
+      "eval_steps_per_second": 1.714,
+      "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": 6560389319884800.0,
+  "total_flos": 9840583979827200.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null