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:efe36a94f99d499fa1028d4fcb22e45ac493603d6236eae9f0dddecf33d008f9
+oid sha256:7da0230666d946b5dfe651b6d6799996e39ed3e08810adf4dfe20c354bea23ef
 size 16794864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d204e5cbea2854cf468fd8e88d3a9b91735f508a66d871c6869f222bf5c4a26d
+oid sha256:81c42b761f972ed1328e194768a40d457c5a2f7db7e9b89c98f70ddc672ecf47
 size 8671162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de9277331b4a0c0a7edd4efcef7468e5c12a03150c0fcc67581dc8d9184679ee
+oid sha256:fae97fb35348dd7a815c49b0d5c119441b7f783204da2556af2d615c3d8c5927
 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": 1.2720811367034912,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00687108133642532,
+  "best_metric": 1.2580277919769287,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.008588851670531649,
   "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": 19.144,
       "eval_steps_per_second": 9.572,
       "step": 20
+    },
+    {
+      "epoch": 0.007214635403246586,
+      "grad_norm": 2.9532949924468994,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 6.0089,
+      "step": 21
+    },
+    {
+      "epoch": 0.007558189470067852,
+      "grad_norm": 2.5257441997528076,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 4.9061,
+      "step": 22
+    },
+    {
+      "epoch": 0.007901743536889118,
+      "grad_norm": 2.5308051109313965,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 5.0996,
+      "step": 23
+    },
+    {
+      "epoch": 0.008245297603710384,
+      "grad_norm": 2.255995035171509,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 5.1077,
+      "step": 24
+    },
+    {
+      "epoch": 0.008588851670531649,
+      "grad_norm": 2.6368045806884766,
+      "learning_rate": 0.0,
+      "loss": 5.4378,
+      "step": 25
+    },
+    {
+      "epoch": 0.008588851670531649,
+      "eval_loss": 1.2580277919769287,
+      "eval_runtime": 65.447,
+      "eval_samples_per_second": 18.733,
+      "eval_steps_per_second": 9.366,
+      "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": 869423728558080.0,
+  "total_flos": 1048917659615232.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null