Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4decf62e2186d1e7f80fc13575fec02bad7e07bfd05f7a8861fb7d2eca46114
+oid sha256:4628c48ef693d8f7e59619fd1d49e0bd7989052fb8ef61b2c5f365b501b20a81
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72d385f7b81f2f06360950bfeec7841f5529e9368a0a5db9131784c40545a46a
+oid sha256:443f4bb1fe022ac4edc63a08276a3234b15cda5f9a3a55b7ea8788a54ff9d5c4
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cf355fd48ca7fbf33eb7fc35115a0613a7bff5e1759da5fa0cb1ec53729b7e7
+oid sha256:0f961351929a5df16fd6f95a46d2cc68ae8eb220a0a4dcd52e4105e45b02d8ec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4633499383926392,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.017185821697099892,
+  "best_metric": 1.4563179016113281,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.021482277121374866,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 11.313,
       "eval_steps_per_second": 5.656,
       "step": 20
+    },
+    {
+      "epoch": 0.01804511278195489,
+      "grad_norm": 0.18878105282783508,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.3512,
+      "step": 21
+    },
+    {
+      "epoch": 0.01890440386680988,
+      "grad_norm": 0.1834011822938919,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.4658,
+      "step": 22
+    },
+    {
+      "epoch": 0.019763694951664877,
+      "grad_norm": 0.19138497114181519,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.4699,
+      "step": 23
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "grad_norm": 0.21401111781597137,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.4216,
+      "step": 24
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "grad_norm": 0.20592810213565826,
+      "learning_rate": 0.0,
+      "loss": 1.4432,
+      "step": 25
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "eval_loss": 1.4563179016113281,
+      "eval_runtime": 43.2353,
+      "eval_samples_per_second": 11.333,
+      "eval_steps_per_second": 5.667,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1023167913000960.0,
+  "total_flos": 1278959891251200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null