Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60565bcfef35e7907ecfd5ce5e92d0b9628bc219791a1ab7d3bbf894978f7923
+oid sha256:e9cfe66170a280709f3a64f328e3fc088bf9b3b0874cede4a6aea543f99615be
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94620b8e60a63415f83977a09db5495c668499a6c41fb607ea3c1c7e6867c68e
+oid sha256:625206082755a225f45589e9cf201d443db516dd5382e044603051bdff6fb1f5
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:641b8ec8c2887df501e48d33d5ba534e1c1b6a3a53e8ff4ad23107271bccc8b7
+oid sha256:ba3723c1c5126a6600e7c5724e27ac95b0c09f4c8f78861394a67418fa3b7346
 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": 1.6888372898101807,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.03508771929824561,
+  "best_metric": 1.685112714767456,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.043859649122807015,
   "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": 24.679,
       "eval_steps_per_second": 12.34,
       "step": 20
+    },
+    {
+      "epoch": 0.03684210526315789,
+      "grad_norm": 5.087654113769531,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 6.7153,
+      "step": 21
+    },
+    {
+      "epoch": 0.03859649122807018,
+      "grad_norm": 6.177897930145264,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 8.1668,
+      "step": 22
+    },
+    {
+      "epoch": 0.04035087719298246,
+      "grad_norm": 5.303010940551758,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 6.6497,
+      "step": 23
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 7.176314353942871,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 8.298,
+      "step": 24
+    },
+    {
+      "epoch": 0.043859649122807015,
+      "grad_norm": 5.998678207397461,
+      "learning_rate": 0.0,
+      "loss": 7.0533,
+      "step": 25
+    },
+    {
+      "epoch": 0.043859649122807015,
+      "eval_loss": 1.685112714767456,
+      "eval_runtime": 9.6984,
+      "eval_samples_per_second": 24.746,
+      "eval_steps_per_second": 12.373,
+      "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": 67934437244928.0,
+  "total_flos": 85448784347136.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null