Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72d6c134cb747fb62e87b00acbd4a5b4a8fae0d162ddd1c1b985fdaa0e9b7b03
+oid sha256:ee027693389fe10c26b0f9c4e9afbc27e4fe4479f977c1f6592b6fca50dec1d8
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6f759edd90c389bd98984c129d44025884b76be54d3fcdcc5a8e672cf32b2b8
+oid sha256:1a60e29fb7be35352c12f2ef746bcafcfb8b310ffc4856053b7da588149b9461
 size 1601338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:878533f6657e20db16b97ee0694d0a09bb7a73b26f79c6b07a8803a12f1db7ef
+oid sha256:688df4983a0ab40b3c1bd4f6fc4cdf35bc2d9c335deddb81a222020476790c48
 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": 8.694866180419922,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.001162385214460072,
+  "best_metric": 8.605793952941895,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0017435778216901082,
   "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": 96.233,
       "eval_steps_per_second": 24.062,
       "step": 20
+    },
+    {
+      "epoch": 0.0012205044751830757,
+      "grad_norm": 2.4120562076568604,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 8.39,
+      "step": 21
+    },
+    {
+      "epoch": 0.0013948622573520864,
+      "grad_norm": 2.093318223953247,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 8.5658,
+      "step": 24
+    },
+    {
+      "epoch": 0.00145298151807509,
+      "eval_loss": 8.619199752807617,
+      "eval_runtime": 150.7975,
+      "eval_samples_per_second": 96.089,
+      "eval_steps_per_second": 24.026,
+      "step": 25
+    },
+    {
+      "epoch": 0.0015692200395210972,
+      "grad_norm": 2.264380693435669,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 8.4889,
+      "step": 27
+    },
+    {
+      "epoch": 0.0017435778216901082,
+      "grad_norm": 2.35832142829895,
+      "learning_rate": 0.0,
+      "loss": 8.2069,
+      "step": 30
+    },
+    {
+      "epoch": 0.0017435778216901082,
+      "eval_loss": 8.605793952941895,
+      "eval_runtime": 151.1869,
+      "eval_samples_per_second": 95.842,
+      "eval_steps_per_second": 23.964,
+      "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": 5769273016320.0,
+  "total_flos": 8484225024000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null