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:e315d33d4c606ec4fbbd365cb480c8eea7a7dd8701fe2aee858b516d87f4884b
+oid sha256:b865b63efc504b549a31e28baff58d6ec627669803b5c0317db3a2411c7fdbc5
 size 10636096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:662b201dd43e8c881c901d95e622868ce17bfb412f89ba1e0c24b510a0f9fc37
+oid sha256:4f4ed78860079add63626e1fc0019a28abb3f7f3069f5caafbe22a15ab2780b7
 size 21354682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408d8bdaaebb000f68ca271b695e3835b6d5987b17262d31ca5afd02b07baad7
+oid sha256:c932858f5eb01eca93935673917e737396fa8cf887bb233118400fc1859dea06
 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": 5.943029880523682,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00038320783276810176,
+  "best_metric": 5.895191669464111,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0005748117491521527,
   "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": 25.605,
       "eval_steps_per_second": 12.802,
       "step": 20
+    },
+    {
+      "epoch": 0.0004023682244065069,
+      "grad_norm": 2.806539297103882,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 23.9984,
+      "step": 21
+    },
+    {
+      "epoch": 0.00045984939932172214,
+      "grad_norm": 2.745965003967285,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 23.6364,
+      "step": 24
+    },
+    {
+      "epoch": 0.0004790097909601272,
+      "eval_loss": 5.9025092124938965,
+      "eval_runtime": 859.0726,
+      "eval_samples_per_second": 25.581,
+      "eval_steps_per_second": 12.791,
+      "step": 25
+    },
+    {
+      "epoch": 0.0005173305742369374,
+      "grad_norm": 3.105595588684082,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 23.8073,
+      "step": 27
+    },
+    {
+      "epoch": 0.0005748117491521527,
+      "grad_norm": 2.740097761154175,
+      "learning_rate": 0.0,
+      "loss": 23.5683,
+      "step": 30
+    },
+    {
+      "epoch": 0.0005748117491521527,
+      "eval_loss": 5.895191669464111,
+      "eval_runtime": 858.9774,
+      "eval_samples_per_second": 25.584,
+      "eval_steps_per_second": 12.792,
+      "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": 172390927564800.0,
+  "total_flos": 258586391347200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null