Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:218a324243be9beda6d8d0bae591d628e1ced7130b6f3b6064b542d1c20dee29
+oid sha256:2fb97299622fc7eddf66697c8540171dfdc8f3eb43c20bacc0317db5c32b3b3c
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb0625b787aecf46fe716b1d2762fff334b61617ddcd5b85a93c306687f49e14
+oid sha256:cfbb59f1a31c6a38f6444fee51c2a59a760355f9c6482180f3d5d378e9b6ecaa
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ef0b4d7708196f19e9afea3ba40c0ea7f084661100c53f1623c51587ea9369
+oid sha256:6a07e4a4fc3af56c2c7d66676e6107c1b7f81d528bc966d7e69b8af726735985
 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": 1.5928586721420288,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.008547921786515653,
+  "best_metric": 1.523171067237854,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.01282188267977348,
   "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": 8.956,
       "eval_steps_per_second": 2.24,
       "step": 20
+    },
+    {
+      "epoch": 0.008975317875841436,
+      "grad_norm": 0.4654037356376648,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.253,
+      "step": 21
+    },
+    {
+      "epoch": 0.010257506143818785,
+      "grad_norm": 0.5114231705665588,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.2179,
+      "step": 24
+    },
+    {
+      "epoch": 0.010684902233144567,
+      "eval_loss": 1.5684505701065063,
+      "eval_runtime": 220.2135,
+      "eval_samples_per_second": 8.95,
+      "eval_steps_per_second": 2.239,
+      "step": 25
+    },
+    {
+      "epoch": 0.011539694411796132,
+      "grad_norm": 1.6363476514816284,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.5796,
+      "step": 27
+    },
+    {
+      "epoch": 0.01282188267977348,
+      "grad_norm": 1.8116801977157593,
+      "learning_rate": 0.0,
+      "loss": 1.7591,
+      "step": 30
+    },
+    {
+      "epoch": 0.01282188267977348,
+      "eval_loss": 1.523171067237854,
+      "eval_runtime": 220.1741,
+      "eval_samples_per_second": 8.952,
+      "eval_steps_per_second": 2.239,
+      "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": 1.306916403806208e+16,
+  "total_flos": 1.960374605709312e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null