Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23b716fb6ed2faa4d75a719be94a9fa9eb4ab737d9a4fcb5a5a93c5f21b569ff
+oid sha256:369bd6cf63f313aaf118f9141b82a4c382863414292bd8a49179f71f3fcb8cbf
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38a8cb5082ff546cdb94c38713491e6840a8a262859da2bd5d58449625d844d8
+oid sha256:dcc418f3f914380a5fcd918937ddcf5cda6510545d63226d4b3bb80b1ba2ea6e
 size 203622650

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9b34add5ab0f68716c96806d540c00b03453de42a09c62ec53261dcc22d0d5c
+oid sha256:25d960a831daf6b1ac2cd05e852fcd6720121cbdf2ebde51ad9091846040f72a
 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": 1.903814435005188,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.001661371046456088,
+  "best_metric": 1.8493242263793945,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0024920565696841318,
   "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": 6.594,
       "eval_steps_per_second": 3.298,
       "step": 20
+    },
+    {
+      "epoch": 0.0017444395987788923,
+      "grad_norm": 0.4985509514808655,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.7729,
+      "step": 21
+    },
+    {
+      "epoch": 0.0019936452557473053,
+      "grad_norm": 0.38667380809783936,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.4537,
+      "step": 24
+    },
+    {
+      "epoch": 0.00207671380807011,
+      "eval_loss": 1.8569525480270386,
+      "eval_runtime": 769.4611,
+      "eval_samples_per_second": 6.588,
+      "eval_steps_per_second": 3.295,
+      "step": 25
+    },
+    {
+      "epoch": 0.0022428509127157188,
+      "grad_norm": 0.31409791111946106,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.4032,
+      "step": 27
+    },
+    {
+      "epoch": 0.0024920565696841318,
+      "grad_norm": 0.32961758971214294,
+      "learning_rate": 0.0,
+      "loss": 1.583,
+      "step": 30
+    },
+    {
+      "epoch": 0.0024920565696841318,
+      "eval_loss": 1.8493242263793945,
+      "eval_runtime": 769.479,
+      "eval_samples_per_second": 6.588,
+      "eval_steps_per_second": 3.294,
+      "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": 3868913109565440.0,
+  "total_flos": 5968004264755200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null