Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:786b25dcca4998b1aa92bdebd38eba21b55bfc78a8148edf273fad1181040671
+oid sha256:51ea8948e1648563e03e06249e1f618be71fb60c5fe406bc55c0d0afa47dab6f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d3622f2e415e4b1d766125d4b9fbd05cf151399534220c5b8c07e2f878fe03c
+oid sha256:e8db6c20e690843666083eeecbb6d430da91c182a11ec2bfbc8e424c1817eb59
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
+oid sha256:83eb5cdc8dd621b9d3b7cf06b9b893f32eef10d148e5187947364f07998add5d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8399719595909119,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.04048582995951417,
+  "best_metric": 0.8137642741203308,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.06072874493927125,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 7.611,
       "eval_steps_per_second": 3.805,
       "step": 20
+    },
+    {
+      "epoch": 0.04251012145748988,
+      "grad_norm": 1.021464467048645,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.875,
+      "step": 21
+    },
+    {
+      "epoch": 0.048582995951417005,
+      "grad_norm": 1.176374912261963,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.7684,
+      "step": 24
+    },
+    {
+      "epoch": 0.05060728744939271,
+      "eval_loss": 0.8207021951675415,
+      "eval_runtime": 27.3776,
+      "eval_samples_per_second": 7.597,
+      "eval_steps_per_second": 3.799,
+      "step": 25
+    },
+    {
+      "epoch": 0.05465587044534413,
+      "grad_norm": 0.9073843955993652,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.8368,
+      "step": 27
+    },
+    {
+      "epoch": 0.06072874493927125,
+      "grad_norm": 1.1118440628051758,
+      "learning_rate": 0.0,
+      "loss": 0.8223,
+      "step": 30
+    },
+    {
+      "epoch": 0.06072874493927125,
+      "eval_loss": 0.8137642741203308,
+      "eval_runtime": 27.3651,
+      "eval_samples_per_second": 7.601,
+      "eval_steps_per_second": 3.8,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null