Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b56c7370c42d4da6894ab1d1032feb9a268536dbc7f5407540981400824be60
+oid sha256:bbbdbf742569ba963b5652c27e3609f51c86372b81bd748f7cc6aa3620f6f5d4
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9b5fbe6336f728755b745f9651ebfae22929a944eada1384a00fce2053c4282
+oid sha256:19c0e9e91748160793cfd205ed09a5b03d852c45acad3e55f5246e8c15dc8274
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9b8f3c2d3598a9a04a5ea7aeb36b1fc836c4e69963500b30df13ecb47949b07
+oid sha256:095670adb63b208497762df0b96a90171bea703270c605fd50bd872eca7637a2
 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": 1.716334581375122,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.04810583283223091,
+  "best_metric": 1.6978141069412231,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.07215874924834637,
   "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": 4.667,
       "eval_steps_per_second": 2.347,
       "step": 20
+    },
+    {
+      "epoch": 0.050511124473842456,
+      "grad_norm": 0.6163607239723206,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.45,
+      "step": 21
+    },
+    {
+      "epoch": 0.05772699939867709,
+      "grad_norm": 0.4879400134086609,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.6064,
+      "step": 24
+    },
+    {
+      "epoch": 0.06013229104028864,
+      "eval_loss": 1.7004387378692627,
+      "eval_runtime": 37.4636,
+      "eval_samples_per_second": 4.671,
+      "eval_steps_per_second": 2.349,
+      "step": 25
+    },
+    {
+      "epoch": 0.06494287432351173,
+      "grad_norm": 0.3684472441673279,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.4877,
+      "step": 27
+    },
+    {
+      "epoch": 0.07215874924834637,
+      "grad_norm": 0.3609531819820404,
+      "learning_rate": 0.0,
+      "loss": 1.4665,
+      "step": 30
+    },
+    {
+      "epoch": 0.07215874924834637,
+      "eval_loss": 1.6978141069412231,
+      "eval_runtime": 37.5099,
+      "eval_samples_per_second": 4.665,
+      "eval_steps_per_second": 2.346,
+      "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": 1.2612083820527616e+16,
+  "total_flos": 1.9381805283016704e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null