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:a7ac51e23cabbc83510b192fdad5975482173fd7dc12c77b4614fe8487fb19dc
+oid sha256:ad36e8d63c95fc8ad6d179c1f8e4f8cdaf55be871037a5611c5f5ac049a3e957
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a445ba8d89027ee1bcfa1f68577d4e21f65bdf8440cd0f23452bfa1fa5b2a8
+oid sha256:dad7d844451236c02b96c77db45c2b62246c3ac4536d9ac1654ac2c2aa31ba9e
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71a795f6c896c1ba8578ff932d62192f0e7c472477b6fc1eb4cb69f1ba706703
+oid sha256:b5af24e28d9a2b19da6adf8978759756f5b3fd1a64e095fe1bdd04aa56ccdc59
 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": 0.675578236579895,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0016858786588835268,
+  "best_metric": 0.6711065173149109,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.00252881798832529,
   "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": 7.436,
       "eval_steps_per_second": 1.859,
       "step": 20
+    },
+    {
+      "epoch": 0.0017701725918277031,
+      "grad_norm": 0.3188973665237427,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.6429,
+      "step": 21
+    },
+    {
+      "epoch": 0.0020230543906602323,
+      "grad_norm": 0.3239786922931671,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.6285,
+      "step": 24
+    },
+    {
+      "epoch": 0.0021073483236044087,
+      "eval_loss": 0.6716910004615784,
+      "eval_runtime": 1343.2962,
+      "eval_samples_per_second": 7.437,
+      "eval_steps_per_second": 1.86,
+      "step": 25
+    },
+    {
+      "epoch": 0.0022759361894927614,
+      "grad_norm": 0.33125385642051697,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.7015,
+      "step": 27
+    },
+    {
+      "epoch": 0.00252881798832529,
+      "grad_norm": 0.3085085153579712,
+      "learning_rate": 0.0,
+      "loss": 2.535,
+      "step": 30
+    },
+    {
+      "epoch": 0.00252881798832529,
+      "eval_loss": 0.6711065173149109,
+      "eval_runtime": 1343.5007,
+      "eval_samples_per_second": 7.436,
+      "eval_steps_per_second": 1.859,
+      "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": 5.07826396987392e+16,
+  "total_flos": 7.61739595481088e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null