Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62fe4eb37dcc27159b69b4272703b9ed0c60117e0bdda18be2931f03ae45a067
+oid sha256:ce2024db9e3456c53fbb39160b46b0ad282920bf6e6eb6dd7a56272cc7f5c37a
 size 1006723888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc14e85a8b429accc321673e7f038fa0692a55b6909485148cd720f3388c259
+oid sha256:accd76af90c40da5ab56adca2ad9647ce4e1dda94ff88f6f33ac07ea2ac63d27
 size 2013843826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4db48a76aa5bd653fabe778f0af4a3e86983afe7bd7ad551d58cc7012d9149c3
+oid sha256:c75652044304b6b2f7db5e60f04511c19eeaa30fbad5859b076478006556b542
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cb0ffccf56c22a1dd3ad25cb6d79ca1624bb80d493fcdfdfc22b9a15102a512
+oid sha256:f04c227e0176d5f21cddc1bacb9a42bc1c02eff8bbe2230f52417e99b6f0941e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0079442262649536,
-  "best_model_checkpoint": "miner_id_24/checkpoint-700",
-  "epoch": 0.5932831867782604,
+  "best_metric": 1.0038142204284668,
+  "best_model_checkpoint": "miner_id_24/checkpoint-800",
+  "epoch": 0.6780379277465833,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -169,6 +169,28 @@
       "eval_samples_per_second": 3.359,
       "eval_steps_per_second": 0.84,
       "step": 700
+    },
+    {
+      "epoch": 0.6356605572624219,
+      "grad_norm": 25.23514747619629,
+      "learning_rate": 2.720321528272137e-06,
+      "loss": 8.1489,
+      "step": 750
+    },
+    {
+      "epoch": 0.6780379277465833,
+      "grad_norm": 25.03769302368164,
+      "learning_rate": 0.0,
+      "loss": 8.0241,
+      "step": 800
+    },
+    {
+      "epoch": 0.6780379277465833,
+      "eval_loss": 1.0038142204284668,
+      "eval_runtime": 594.1032,
+      "eval_samples_per_second": 3.346,
+      "eval_steps_per_second": 0.837,
+      "step": 800
     }
   ],
   "logging_steps": 50,
@@ -192,12 +214,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.987056392516403e+18,
+  "total_flos": 3.413778734304461e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null