Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e8d954c7844c2ec37937de49ca81455e22c777b4ead8bd057f1a4371ad4a8b3
+oid sha256:87563151006a3a13e4425ccc52a2d34c577f56fdddf69a7c85e3f1f8a46fa8df
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0a15d4a5106ad9311c235e1d225edf1e03835ec932cf969ce7eee760cc81e3c
+oid sha256:139511fada179d4dfcb7905e9a6a2f163803b67843c844aa028b9e7cefc7ec36
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fd49d8ffdc507288356cd9d5ee3dbcd6398ee312f86ab554d873f3444e85b89
+oid sha256:6a36302cbe8411ef5d275e8bc320adbf172256e8b2c26158c8fb833c29a9feec
 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": 0.6183786392211914,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.004927322000492732,
+  "best_metric": 0.6138322353363037,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.006159152500615915,
   "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": 5.384,
       "eval_steps_per_second": 2.694,
       "step": 20
+    },
+    {
+      "epoch": 0.005173688100517369,
+      "grad_norm": 0.39517274498939514,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.8512,
+      "step": 21
+    },
+    {
+      "epoch": 0.005420054200542005,
+      "grad_norm": 0.35510003566741943,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.8077,
+      "step": 22
+    },
+    {
+      "epoch": 0.005666420300566642,
+      "grad_norm": 0.23273567855358124,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.2846,
+      "step": 23
+    },
+    {
+      "epoch": 0.005912786400591279,
+      "grad_norm": 0.38091930747032166,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.8437,
+      "step": 24
+    },
+    {
+      "epoch": 0.006159152500615915,
+      "grad_norm": 0.3586118817329407,
+      "learning_rate": 0.0,
+      "loss": 0.8139,
+      "step": 25
+    },
+    {
+      "epoch": 0.006159152500615915,
+      "eval_loss": 0.6138322353363037,
+      "eval_runtime": 316.5536,
+      "eval_samples_per_second": 5.399,
+      "eval_steps_per_second": 2.701,
+      "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": 6196040231288832.0,
+  "total_flos": 7906887160823808.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null