Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a94d62a3e3fbf7516378436560ae0c4aba7930c55caae4880ed1c284dbb8a53
+oid sha256:2de5645692f031ff1163822d7938f69ec0905d72bf9620ec4f3df209d58ce86f
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10358a3a0bc525075aa83e214c8ccb4aa0c4e9abd88b996e6dc9503d803ff4ca
+oid sha256:0219a555f57753057adea7fbc03c2a874f6039799186b95369b6bd2c141d12ae
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68453475ca6597bdf993ea58ab91e7754aa278825c08f5417b0c316948c14e34
+oid sha256:21f374fd9dca0179920eabd8211318207a9d1f812945ed9d8e84dde2321c7a5e
 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": 1.8018192052841187,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.017185821697099892,
+  "best_metric": 1.7526025772094727,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.02577873254564984,
   "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": 14.043,
       "eval_steps_per_second": 7.022,
       "step": 20
+    },
+    {
+      "epoch": 0.01804511278195489,
+      "grad_norm": 2.7733678817749023,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.9379,
+      "step": 21
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "grad_norm": 1.6699885129928589,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.781,
+      "step": 24
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "eval_loss": 1.762498140335083,
+      "eval_runtime": 34.919,
+      "eval_samples_per_second": 14.032,
+      "eval_steps_per_second": 7.016,
+      "step": 25
+    },
+    {
+      "epoch": 0.023200859291084855,
+      "grad_norm": 1.8251397609710693,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.7113,
+      "step": 27
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "grad_norm": 1.4449748992919922,
+      "learning_rate": 0.0,
+      "loss": 1.5557,
+      "step": 30
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "eval_loss": 1.7526025772094727,
+      "eval_runtime": 34.8758,
+      "eval_samples_per_second": 14.05,
+      "eval_steps_per_second": 7.025,
+      "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": 8627561567354880.0,
+  "total_flos": 1.3037204146225152e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null