Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74f183633dad000a0e47c32abe84d5827c40702ccecfff49901512389350c58c
+oid sha256:919b9cf7dbc7d7c3b50fa0f4b95ad2058e452af8d0b03b52bff363d441a81e14
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be51221098653bc48f6099edc2dc5f0896063d279182a03e8a63c443afa82186
+oid sha256:eb098dc9332c76a533a836ff2cdee42652ce8be67c5b5def8557ae26ef0e977b
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82b93107c2130590d832409ff5536612f9a10a908a196ef6b6c07e81941a0ae5
+oid sha256:52198293cd301557ee1bb22f7d729e9fafea7b6e5db7f081b63ae3eaec47afcd
 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": 2.385772705078125,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00028842236571234917,
+  "best_metric": 2.3591372966766357,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.00043263354856852375,
   "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": 28.641,
       "eval_steps_per_second": 14.321,
       "step": 20
+    },
+    {
+      "epoch": 0.0003028434839979666,
+      "grad_norm": 10.232197761535645,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 9.2268,
+      "step": 21
+    },
+    {
+      "epoch": 0.000346106838854819,
+      "grad_norm": 8.313934326171875,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 9.2689,
+      "step": 24
+    },
+    {
+      "epoch": 0.00036052795714043643,
+      "eval_loss": 2.363536834716797,
+      "eval_runtime": 1016.6937,
+      "eval_samples_per_second": 28.718,
+      "eval_steps_per_second": 14.359,
+      "step": 25
+    },
+    {
+      "epoch": 0.00038937019371167137,
+      "grad_norm": 10.205106735229492,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 9.7311,
+      "step": 27
+    },
+    {
+      "epoch": 0.00043263354856852375,
+      "grad_norm": 11.081389427185059,
+      "learning_rate": 0.0,
+      "loss": 9.4674,
+      "step": 30
+    },
+    {
+      "epoch": 0.00043263354856852375,
+      "eval_loss": 2.3591372966766357,
+      "eval_runtime": 1012.2314,
+      "eval_samples_per_second": 28.844,
+      "eval_steps_per_second": 14.423,
+      "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": 1202020417536000.0,
+  "total_flos": 1803030626304000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null