Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11baf582a2f22eee45a402c32addc85caa10b8a6d119e2e3c586efd0ce48bbf1
+oid sha256:0a1e515ec390825369f46d590d214d1922ef320b0419d38697189452c8e172ae
 size 56660888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66a60d8d325c61a2c151ca65f63275a60f0e090f51a7c161bf8f2d45886bdef8
+oid sha256:e502b57c1d452f5e99d2221251962288892d2209256a8849ed7035af5c29aff4
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11dc50ba25204dd40ecba0ebf665a51f0363460963d143cee1ec68e4484546f8
+oid sha256:df8858c90e3ec0b2712a82e58c95ccbba4f88066ef79a6ae42ddb00c1dcfc5fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.954017400741577,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00038803682469466355,
+  "best_metric": 2.9403679370880127,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0005820552370419952,
   "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": 10.702,
       "eval_steps_per_second": 5.351,
       "step": 20
+    },
+    {
+      "epoch": 0.0004074386659293967,
+      "grad_norm": 0.40540552139282227,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 3.0663,
+      "step": 21
+    },
+    {
+      "epoch": 0.00046564418963359624,
+      "grad_norm": 0.3658403158187866,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 2.9409,
+      "step": 24
+    },
+    {
+      "epoch": 0.0004850460308683294,
+      "eval_loss": 2.942352056503296,
+      "eval_runtime": 2026.1692,
+      "eval_samples_per_second": 10.711,
+      "eval_steps_per_second": 5.355,
+      "step": 25
+    },
+    {
+      "epoch": 0.0005238497133377958,
+      "grad_norm": 0.6082600951194763,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 3.0562,
+      "step": 27
+    },
+    {
+      "epoch": 0.0005820552370419952,
+      "grad_norm": 0.45390358567237854,
+      "learning_rate": 0.0,
+      "loss": 2.8248,
+      "step": 30
+    },
+    {
+      "epoch": 0.0005820552370419952,
+      "eval_loss": 2.9403679370880127,
+      "eval_runtime": 2027.2099,
+      "eval_samples_per_second": 10.705,
+      "eval_steps_per_second": 5.353,
+      "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": 2610106655047680.0,
+  "total_flos": 3915159982571520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null