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:f7f4e752979cdcca12c32b0aa81d08db0f264d88b3a7a665a1a936ac240243d9
+oid sha256:04b1670c25c88e76ea43c27dcb6783cf600d9d0667a174908ea5726bf170ef3c
 size 130583912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d39ddcef2c82de05bd04a165aa17b7ffbbd618034f49a3e6b789e634e80ceb12
+oid sha256:d718dde3827ca128d3e873db22780bb55b2d8249396855fb3ba1f44e73cd8cc6
 size 261311226

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aa91133351808aacad3e45f05aebdf1a2981ac4aa08431c95904a973b1b12d5
+oid sha256:b90cec581bf01b7b4ecfb930623a750a1d6c081eb2553ed745e3e8de8e41bc7c
 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": 0.019720349460840225,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0033819488480236735,
+  "best_metric": 0.017324844375252724,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0050729232720355105,
   "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": 8.979,
       "eval_steps_per_second": 4.49,
       "step": 20
+    },
+    {
+      "epoch": 0.0035510462904248573,
+      "grad_norm": 0.6280816197395325,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.0721,
+      "step": 21
+    },
+    {
+      "epoch": 0.004058338617628408,
+      "grad_norm": 0.6697679162025452,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.0797,
+      "step": 24
+    },
+    {
+      "epoch": 0.004227436060029592,
+      "eval_loss": 0.018337341025471687,
+      "eval_runtime": 277.3108,
+      "eval_samples_per_second": 8.979,
+      "eval_steps_per_second": 4.49,
+      "step": 25
+    },
+    {
+      "epoch": 0.004565630944831959,
+      "grad_norm": 0.7023375630378723,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.076,
+      "step": 27
+    },
+    {
+      "epoch": 0.0050729232720355105,
+      "grad_norm": 0.6577435731887817,
+      "learning_rate": 0.0,
+      "loss": 0.0726,
+      "step": 30
+    },
+    {
+      "epoch": 0.0050729232720355105,
+      "eval_loss": 0.017324844375252724,
+      "eval_runtime": 277.3945,
+      "eval_samples_per_second": 8.976,
+      "eval_steps_per_second": 4.488,
+      "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": 6545953825751040.0,
+  "total_flos": 9818930738626560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null