Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:498b3687ee450e2eff26e720212ce6d52064c73b38c0fec60caaedc096c40552
+oid sha256:daacd75a106553a8fdc57b058edd252f244815f468339f9e09bae292c750a813
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:037a6f497e86b65b8c8b2d14930e65bad5f3ff7a37e25366a8385d20d78a3de5
+oid sha256:07719814aa9994e539f7d4094fab8e942ed9edc78425140c14daf38196388aa3
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f1c23e1e5fb41aca194dd42c51b4d1ef7c5b2c45f66230306d2c0a25ec25f6c
+oid sha256:74e1d166bd94c8d5feb6a09f0334c405dc805c0289ac58657df651915eaf6e15
 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": 1.2420746088027954,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.004927322000492732,
+  "best_metric": 1.224576473236084,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.007390983000739098,
   "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": 6.133,
       "eval_steps_per_second": 3.068,
       "step": 20
+    },
+    {
+      "epoch": 0.005173688100517369,
+      "grad_norm": 0.4509369730949402,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.15,
+      "step": 21
+    },
+    {
+      "epoch": 0.005912786400591279,
+      "grad_norm": 0.4589945375919342,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.2316,
+      "step": 24
+    },
+    {
+      "epoch": 0.006159152500615915,
+      "eval_loss": 1.2277593612670898,
+      "eval_runtime": 278.7654,
+      "eval_samples_per_second": 6.131,
+      "eval_steps_per_second": 3.067,
+      "step": 25
+    },
+    {
+      "epoch": 0.0066518847006651885,
+      "grad_norm": 0.428680419921875,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.2175,
+      "step": 27
+    },
+    {
+      "epoch": 0.007390983000739098,
+      "grad_norm": 0.5584115386009216,
+      "learning_rate": 0.0,
+      "loss": 1.1603,
+      "step": 30
+    },
+    {
+      "epoch": 0.007390983000739098,
+      "eval_loss": 1.224576473236084,
+      "eval_runtime": 278.8171,
+      "eval_samples_per_second": 6.129,
+      "eval_steps_per_second": 3.067,
+      "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": 9459062865395712.0,
+  "total_flos": 1.437406611898368e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null