Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d1b0ea30c4bcb64065b1fd7843ab3183183506b9171498c2cff82c764ef7c1b
+oid sha256:7dd3b1684864193acaa492a7cdd79b4676240fb6957b18d95ceabf8bc55a1d8a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43557e0cd49c2e9f65940c5a2aea5bfa498aaea3012e63b43141f64965dfc448
+oid sha256:4fac27c83a09268b3930d7d459704c79710a9cd3505689b5b1fb321c423777ad
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dc3e5265caade9b4765ce3bea88afed07b875a6b1b6dbe83b1b96d505d55d4b
+oid sha256:c70a576494e56c909be11c04fa488ebbe191aee3195b0dd47c32f36094b31b77
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8112471699714661,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.01677500524218914,
+  "best_metric": 0.797995388507843,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.020968756552736424,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 5.183,
       "eval_steps_per_second": 2.591,
       "step": 20
+    },
+    {
+      "epoch": 0.017613755504298594,
+      "grad_norm": 2.1474497318267822,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.7525,
+      "step": 21
+    },
+    {
+      "epoch": 0.018452505766408053,
+      "grad_norm": 0.7059950828552246,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.8577,
+      "step": 22
+    },
+    {
+      "epoch": 0.019291256028517507,
+      "grad_norm": 0.6999573707580566,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.7959,
+      "step": 23
+    },
+    {
+      "epoch": 0.020130006290626966,
+      "grad_norm": 0.6433355212211609,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.7974,
+      "step": 24
+    },
+    {
+      "epoch": 0.020968756552736424,
+      "grad_norm": 0.6609203219413757,
+      "learning_rate": 0.0,
+      "loss": 0.7579,
+      "step": 25
+    },
+    {
+      "epoch": 0.020968756552736424,
+      "eval_loss": 0.797995388507843,
+      "eval_runtime": 96.86,
+      "eval_samples_per_second": 5.183,
+      "eval_steps_per_second": 2.591,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3699128496291840.0,
+  "total_flos": 4623910620364800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null