Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:736c4682ba6186ab5e7a4e63e9ef56487e83ff16fc959028c028f0e1a8de811e
+oid sha256:6c250486a81e176aab03d0987495222bd955254497db289b35b2a46f91f25491
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1b0de3ef72cdd3a566e285fd6fe397cd6f573f93b3c5ca1a2deab126fbcea99
+oid sha256:c7196c13311084020b60eba866acfc6b7e2ce9e4c41aacdef109c2132d6ac8e0
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4b82d94a3f3ba4658ccb6aa5c8b6ba7ae6394ee1ce2647f24e42e072d6200c3
+oid sha256:f58b98283f0cf134b4005d9b921adb02a846a23631404be12129392a65cfe4e3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3715277314186096,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.02969561989606533,
+  "best_metric": 0.34634873270988464,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.03711952487008166,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 5.412,
       "eval_steps_per_second": 2.706,
       "step": 20
+    },
+    {
+      "epoch": 0.031180400890868598,
+      "grad_norm": 3.563546657562256,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.7269,
+      "step": 21
+    },
+    {
+      "epoch": 0.032665181885671864,
+      "grad_norm": 3.984164237976074,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.2789,
+      "step": 22
+    },
+    {
+      "epoch": 0.03414996288047513,
+      "grad_norm": 3.204500198364258,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.7305,
+      "step": 23
+    },
+    {
+      "epoch": 0.035634743875278395,
+      "grad_norm": 3.4421498775482178,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.6905,
+      "step": 24
+    },
+    {
+      "epoch": 0.03711952487008166,
+      "grad_norm": 3.3259477615356445,
+      "learning_rate": 0.0,
+      "loss": 1.3058,
+      "step": 25
+    },
+    {
+      "epoch": 0.03711952487008166,
+      "eval_loss": 0.34634873270988464,
+      "eval_runtime": 52.8815,
+      "eval_samples_per_second": 5.37,
+      "eval_steps_per_second": 2.685,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6332448610713600.0,
+  "total_flos": 7915560763392000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null