Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95de024d1ec5e02c7af4e3a7f54e4e7dd4aeec327c2d2563e4275c6ae7e9707d
+oid sha256:736c4682ba6186ab5e7a4e63e9ef56487e83ff16fc959028c028f0e1a8de811e
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fedd60c2f2d7f0ed997a8178f7c367d989bd5b9906a02cd40df3fd5153896d69
+oid sha256:e1b0de3ef72cdd3a566e285fd6fe397cd6f573f93b3c5ca1a2deab126fbcea99
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:565c117b0554bcadbb2962d5778f478da838b047d26cc08e6b3663c916f71fed
+oid sha256:e4b82d94a3f3ba4658ccb6aa5c8b6ba7ae6394ee1ce2647f24e42e072d6200c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0966575145721436,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.014847809948032665,
+  "best_metric": 0.3715277314186096,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.02969561989606533,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 5.345,
       "eval_steps_per_second": 2.673,
       "step": 10
+    },
+    {
+      "epoch": 0.016332590942835932,
+      "grad_norm": 5.9748125076293945,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 4.4809,
+      "step": 11
+    },
+    {
+      "epoch": 0.017817371937639197,
+      "grad_norm": 4.773859024047852,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 4.0181,
+      "step": 12
+    },
+    {
+      "epoch": 0.019302152932442463,
+      "grad_norm": 4.2915544509887695,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.8875,
+      "step": 13
+    },
+    {
+      "epoch": 0.020786933927245732,
+      "grad_norm": 4.280338287353516,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.363,
+      "step": 14
+    },
+    {
+      "epoch": 0.022271714922048998,
+      "grad_norm": 5.092531681060791,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.1731,
+      "step": 15
+    },
+    {
+      "epoch": 0.022271714922048998,
+      "eval_loss": 0.5182551145553589,
+      "eval_runtime": 51.7607,
+      "eval_samples_per_second": 5.487,
+      "eval_steps_per_second": 2.743,
+      "step": 15
+    },
+    {
+      "epoch": 0.023756495916852263,
+      "grad_norm": 5.672760486602783,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.6013,
+      "step": 16
+    },
+    {
+      "epoch": 0.025241276911655532,
+      "grad_norm": 6.637510776519775,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 2.5146,
+      "step": 17
+    },
+    {
+      "epoch": 0.026726057906458798,
+      "grad_norm": 4.401640892028809,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.8105,
+      "step": 18
+    },
+    {
+      "epoch": 0.028210838901262063,
+      "grad_norm": 4.6342902183532715,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.7016,
+      "step": 19
+    },
+    {
+      "epoch": 0.02969561989606533,
+      "grad_norm": 3.619751453399658,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.7681,
+      "step": 20
+    },
+    {
+      "epoch": 0.02969561989606533,
+      "eval_loss": 0.3715277314186096,
+      "eval_runtime": 52.4711,
+      "eval_samples_per_second": 5.412,
+      "eval_steps_per_second": 2.706,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3166224305356800.0,
+  "total_flos": 6332448610713600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null