Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8766347f449532efab219dc598d5a304e94b194073892863393d8c5099bd4f37
+oid sha256:4fae99386f492f7fb41a65129f1267cec947f56d4f097f886d1564ef88282e57
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3f9d01b8fe589cb738904591ab4f7082b5b7caf6e0a636b0ea00c24892e69d9
+oid sha256:49c1738352bb280057f08db72ccf7342e10c2df904aba7ed3c85bde54c153ade
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49ba7598c1d0cfdd44ffe49c303fb8b51ec0600e8e2134c278d45670ae3566af
+oid sha256:3ce24057a5ba39f6bb8e65b69b5d8d23e014a623d505ecfe88ab29560bdf006b
 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": 1.5172053575515747,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003500940877860925,
+  "best_metric": 1.5101369619369507,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0043761760973261565,
   "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": 5.929,
       "eval_steps_per_second": 2.964,
       "step": 20
+    },
+    {
+      "epoch": 0.0036759879217539712,
+      "grad_norm": 3.809283971786499,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 7.2163,
+      "step": 21
+    },
+    {
+      "epoch": 0.003851034965647018,
+      "grad_norm": 1.9340250492095947,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 5.3483,
+      "step": 22
+    },
+    {
+      "epoch": 0.004026082009540064,
+      "grad_norm": 1.6621471643447876,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 6.46,
+      "step": 23
+    },
+    {
+      "epoch": 0.00420112905343311,
+      "grad_norm": 1.4169622659683228,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 6.3164,
+      "step": 24
+    },
+    {
+      "epoch": 0.0043761760973261565,
+      "grad_norm": 1.331876516342163,
+      "learning_rate": 0.0,
+      "loss": 6.8027,
+      "step": 25
+    },
+    {
+      "epoch": 0.0043761760973261565,
+      "eval_loss": 1.5101369619369507,
+      "eval_runtime": 403.9644,
+      "eval_samples_per_second": 5.956,
+      "eval_steps_per_second": 2.978,
+      "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": 4967685188222976.0,
+  "total_flos": 6107809657651200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null