Training in progress, step 143, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4482a0859dbc0c09cbecf9061a8c6e9d1ed609f6fba7a0310b762775f34ce28a
+oid sha256:028e9c324935382412c9e6de805da452757d7ae87fc44b169ee02e65ea311592
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f42b8bea893c351df7f112f14588f1ee6e7183cdc8cc49b7464a0d1cb6cfb48
+oid sha256:db54a4426452b64b4027e4dfa9ef0535906c38efe4d080f388c742a719a5fac0
 size 111142

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49a69175eebd96d9abef5a70c95df2a121f5eab8841cb5b743e18797c301adb9
+oid sha256:7ace8e8b5fa5c901a16c2d027e66f97b4fcf6e88e1f35448babcdafe63e22ff7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f898282f5441a4001bfc295ec53b08bdc8d00e4f4d60b2e54baad9e1e0754a20
+oid sha256:544ca722df0421adc4c8d7e37de997de6c391ac56739a37eab2f58b5d53e7f1f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.731181144714355,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.7017543859649122,
+  "epoch": 1.0035087719298246,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 143,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,34 @@
       "eval_samples_per_second": 316.765,
       "eval_steps_per_second": 79.191,
       "step": 100
+    },
+    {
+      "epoch": 0.7719298245614035,
+      "grad_norm": 0.06784291565418243,
+      "learning_rate": 2.8872993029040508e-05,
+      "loss": 11.7303,
+      "step": 110
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.05094173923134804,
+      "learning_rate": 1.439838153227e-05,
+      "loss": 11.73,
+      "step": 120
+    },
+    {
+      "epoch": 0.9122807017543859,
+      "grad_norm": 0.06301553547382355,
+      "learning_rate": 4.6777594000230855e-06,
+      "loss": 11.731,
+      "step": 130
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "grad_norm": 0.14561209082603455,
+      "learning_rate": 2.509731335744281e-07,
+      "loss": 11.7305,
+      "step": 140
     }
   ],
   "logging_steps": 10,
@@ -124,12 +152,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 22865329913856.0,
+  "total_flos": 32693857026048.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null