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:d17b20eadb596f829316f075e8935cd0ff0627e678e6ee03a973b7940659d00b
+oid sha256:b61a63e9d93b9854378bef6c7c01a0ff5ae7e3cf72ff4fcfa4ca22801b8813ec
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bffa54e7f9217ec52d2d42a45fe08b7255b51db289cfabcde85ad425fd5a4f9
+oid sha256:737dd1ab37a4eb401aa12898eb10e206729d3c198e609b2b4df19b1ad168bdde
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f87b77ca5d255867312cd9efd43af4b0b13cfa59d6e44cdde83d6042050b9a32
+oid sha256:18c10a288dd2366325431ce28207aa0646a613348cf3f349d8c9353cacebc862
 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": 0.16609641909599304,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.04106776180698152,
+  "best_metric": 0.1640225350856781,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0513347022587269,
   "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": 1.63,
       "eval_steps_per_second": 0.819,
       "step": 20
+    },
+    {
+      "epoch": 0.043121149897330596,
+      "grad_norm": 0.8708037734031677,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.6053,
+      "step": 21
+    },
+    {
+      "epoch": 0.045174537987679675,
+      "grad_norm": 0.9391026496887207,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.6941,
+      "step": 22
+    },
+    {
+      "epoch": 0.04722792607802875,
+      "grad_norm": 0.6442247033119202,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.7088,
+      "step": 23
+    },
+    {
+      "epoch": 0.049281314168377825,
+      "grad_norm": 0.5883622169494629,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.7006,
+      "step": 24
+    },
+    {
+      "epoch": 0.0513347022587269,
+      "grad_norm": 0.6451522707939148,
+      "learning_rate": 0.0,
+      "loss": 0.8123,
+      "step": 25
+    },
+    {
+      "epoch": 0.0513347022587269,
+      "eval_loss": 0.1640225350856781,
+      "eval_runtime": 125.5464,
+      "eval_samples_per_second": 1.633,
+      "eval_steps_per_second": 0.82,
+      "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": 1.211080796798976e+16,
+  "total_flos": 1.519787666571264e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null