Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92fbe0c9c7b353687d341212b7a8820fe4c5ef835d008ef0a61278ca62711174
+oid sha256:b64599378700308001ed236c6b0c04544e4ba48dbc45a138e43ed62fc23173f4
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aca8ca79bc7d6699dd081ae60ee46d729ecfbfbd5e25b9f978e8b434835fecb0
+oid sha256:821a78e090c839d446b1180c8a385adf9d7120da4338aa1a3cced96831fcd413
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b76fb184def3280d3ccdb58c41f578f8e1aaa16c64a7b30742bd68dc37494d
+oid sha256:3afc98a924dfc656f7cc4ced747b1ff854e9a7470a3497575ee8a5ed4cf9cc16
 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": 2.7887346744537354,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0072503172013775605,
+  "best_metric": 2.7828643321990967,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.010875475802066341,
   "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": 26.488,
       "eval_steps_per_second": 13.244,
       "step": 20
+    },
+    {
+      "epoch": 0.0076128330614464385,
+      "grad_norm": 0.667388916015625,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.8908,
+      "step": 21
+    },
+    {
+      "epoch": 0.008700380641653072,
+      "grad_norm": 0.6787062287330627,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.8226,
+      "step": 24
+    },
+    {
+      "epoch": 0.00906289650172195,
+      "eval_loss": 2.783844470977783,
+      "eval_runtime": 43.9784,
+      "eval_samples_per_second": 26.422,
+      "eval_steps_per_second": 13.211,
+      "step": 25
+    },
+    {
+      "epoch": 0.009787928221859706,
+      "grad_norm": 0.6023674011230469,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.864,
+      "step": 27
+    },
+    {
+      "epoch": 0.010875475802066341,
+      "grad_norm": 0.6628087162971497,
+      "learning_rate": 0.0,
+      "loss": 2.8414,
+      "step": 30
+    },
+    {
+      "epoch": 0.010875475802066341,
+      "eval_loss": 2.7828643321990967,
+      "eval_runtime": 43.787,
+      "eval_samples_per_second": 26.538,
+      "eval_steps_per_second": 13.269,
+      "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": 495656081817600.0,
+  "total_flos": 743484122726400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null