Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:529ad1f116fc12d499b97a486b37a4e98e0a009464f852ec5cbbafee59072742
+oid sha256:f7ef714e71c09e34ac9cfb907ac8c72c7b0f08ac961dc173a331d9024d7e0fb0
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56397505869e264136e501560990b2600e7dd4a79d65e7ad648c8cc35539c04a
+oid sha256:2584c393dc49d062f4dce8f9eaca069317e95cde5abc1b6921abcfe4e290ed9a
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
+oid sha256:83eb5cdc8dd621b9d3b7cf06b9b893f32eef10d148e5187947364f07998add5d
 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": 2.206324815750122,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.006077641874952518,
+  "best_metric": 2.168490409851074,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.009116462812428778,
   "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": 7.644,
       "eval_steps_per_second": 3.822,
       "step": 20
+    },
+    {
+      "epoch": 0.0063815239687001445,
+      "grad_norm": 2.3398468494415283,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.2411,
+      "step": 21
+    },
+    {
+      "epoch": 0.007293170249943022,
+      "grad_norm": 2.6244406700134277,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.0876,
+      "step": 24
+    },
+    {
+      "epoch": 0.007597052343690648,
+      "eval_loss": 2.176274538040161,
+      "eval_runtime": 181.6842,
+      "eval_samples_per_second": 7.629,
+      "eval_steps_per_second": 3.814,
+      "step": 25
+    },
+    {
+      "epoch": 0.0082048165311859,
+      "grad_norm": 3.688023328781128,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.1679,
+      "step": 27
+    },
+    {
+      "epoch": 0.009116462812428778,
+      "grad_norm": 3.1167757511138916,
+      "learning_rate": 0.0,
+      "loss": 2.0348,
+      "step": 30
+    },
+    {
+      "epoch": 0.009116462812428778,
+      "eval_loss": 2.168490409851074,
+      "eval_runtime": 181.2847,
+      "eval_samples_per_second": 7.645,
+      "eval_steps_per_second": 3.823,
+      "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": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null