Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:126a66d18f2f278dbd3cded4934a66581f83aaf7cf7a9ab2d6d79cb0d85f96b5
+oid sha256:60938808b66ebf1e88f1a3f5b65a389eac61f5c4dbd28dab5fd7d3ab824c2f58
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5c175559df9f9faf7cb805ee51a6b30c6664a101be487908b6bd4c6dbc8583
+oid sha256:0f7f7f6a4cacd0d8e4eaf8d8b4f4fd9f657628c81e13281eb678a5ce0b122639
 size 250679090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8be70d832a1bbff101f33c955af2006518b5495f9530a45087a280e66288a93d
+oid sha256:23ba6f4e1ddd9457b39425bc60bf390070addbb761f15a038321aac470417dab
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7af249df5fe11a9896f83a1f972a51ac4c516f61ca7fde0473cca60d389d7ec
+oid sha256:4677d15317405bcdd600dfdae9d04715d81517a0dbc7789a073149e371184d8c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0622997283935547,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.019985011241568824,
+  "best_metric": 2.044719934463501,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.02498126405196103,
   "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": 4.918,
       "eval_steps_per_second": 2.459,
       "step": 20
+    },
+    {
+      "epoch": 0.020984261803647264,
+      "grad_norm": 5.099001407623291,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 8.2414,
+      "step": 21
+    },
+    {
+      "epoch": 0.021983512365725707,
+      "grad_norm": 5.913036346435547,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 9.1997,
+      "step": 22
+    },
+    {
+      "epoch": 0.022982762927804146,
+      "grad_norm": 6.968205451965332,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 9.1247,
+      "step": 23
+    },
+    {
+      "epoch": 0.02398201348988259,
+      "grad_norm": 7.832215785980225,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 6.6349,
+      "step": 24
+    },
+    {
+      "epoch": 0.02498126405196103,
+      "grad_norm": 5.372540473937988,
+      "learning_rate": 0.0,
+      "loss": 7.4628,
+      "step": 25
+    },
+    {
+      "epoch": 0.02498126405196103,
+      "eval_loss": 2.044719934463501,
+      "eval_runtime": 85.8196,
+      "eval_samples_per_second": 4.917,
+      "eval_steps_per_second": 2.459,
+      "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