Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c571f8bde4644026b7839e7bc2850999fe9b74b068a74bc8b1be7b66d784300
+oid sha256:c7d65820e5de7c9f78eb14a276fe63c7cd918f72ec7bffa409b509d3d29f8c24
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b16953590e9b667bf38e1c63c983d536e9774d128ebfa1b3935278eed1ad19cc
+oid sha256:1a38c3eef8ed4cf60cffd6b73c47b00d98548719585d27a7f011068744e91274
 size 68874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ae25564f810a8fa1d5e44004d08680ae5ec0003ba96d447ea464eb3f04c096c
+oid sha256:e8a60fcf52e32093d451f7bd31231e63f49254a3fb594a502d9bc64dd53a2c0c
 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": 11.927800178527832,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.17857142857142858,
+  "best_metric": 11.927637100219727,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.26785714285714285,
   "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": 69.974,
       "eval_steps_per_second": 17.678,
       "step": 20
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 0.026569347828626633,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 11.9276,
+      "step": 21
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 0.027363870292901993,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 11.9282,
+      "step": 24
+    },
+    {
+      "epoch": 0.22321428571428573,
+      "eval_loss": 11.92770004272461,
+      "eval_runtime": 1.3542,
+      "eval_samples_per_second": 70.15,
+      "eval_steps_per_second": 17.722,
+      "step": 25
+    },
+    {
+      "epoch": 0.24107142857142858,
+      "grad_norm": 0.03920485079288483,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 11.9263,
+      "step": 27
+    },
+    {
+      "epoch": 0.26785714285714285,
+      "grad_norm": 0.01625853404402733,
+      "learning_rate": 0.0,
+      "loss": 11.9294,
+      "step": 30
+    },
+    {
+      "epoch": 0.26785714285714285,
+      "eval_loss": 11.927637100219727,
+      "eval_runtime": 1.3512,
+      "eval_samples_per_second": 70.31,
+      "eval_steps_per_second": 17.763,
+      "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": 14989393920.0,
+  "total_flos": 22484090880.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null