Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dde485dbcd18a9f55dbc7d32b88594c95770cc787215dac9aa8d636deaa5dfd
+oid sha256:eb384ac909fc0018b4cca799d6ca5238ecc24c8a2e56521edf2df0e7b844e173
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d4f069935b5fd59577d9363a87a4f60be1ea57f283a2309a2074dd907a0d671
+oid sha256:9f36c5e6cf25e74a3cfe78204bc12e6695a81db1cf57f8595466e012adafa193
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d2be4059750be4e71470e704684e42897fbcc04f3e100d4d1c061b02a3d0fa8
+oid sha256:8746fc39ee39c210f91e7f050f3c3a8b1f0559d162dfac4e641fe38be11804cc
 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": 1.5246868133544922,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.04405286343612335,
+  "best_metric": 1.5037736892700195,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.05506607929515418,
   "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": 5.235,
       "eval_steps_per_second": 2.618,
       "step": 20
+    },
+    {
+      "epoch": 0.046255506607929514,
+      "grad_norm": 2.0345118045806885,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.6812,
+      "step": 21
+    },
+    {
+      "epoch": 0.048458149779735685,
+      "grad_norm": 2.8013086318969727,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.3621,
+      "step": 22
+    },
+    {
+      "epoch": 0.05066079295154185,
+      "grad_norm": 1.9331738948822021,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.4922,
+      "step": 23
+    },
+    {
+      "epoch": 0.05286343612334802,
+      "grad_norm": 1.893699049949646,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.4471,
+      "step": 24
+    },
+    {
+      "epoch": 0.05506607929515418,
+      "grad_norm": 2.7612457275390625,
+      "learning_rate": 0.0,
+      "loss": 1.4832,
+      "step": 25
+    },
+    {
+      "epoch": 0.05506607929515418,
+      "eval_loss": 1.5037736892700195,
+      "eval_runtime": 36.7219,
+      "eval_samples_per_second": 5.228,
+      "eval_steps_per_second": 2.614,
+      "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": 249306858651648.0,
+  "total_flos": 309407619219456.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null