Training in progress, step 41, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f62a6eb1768ee932a301d8831cea644b16ca3cbaa29cf8a383303d36900c2915
+oid sha256:c4f32eb339a0a3b9a69c30592511868c51e8cecbf1700d09b00d72567e6f92bb
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38b9192a229cb13ad6f02b1fbfaa55f06914c19349637257308c1038630ec7f5
+oid sha256:17c07c928871c4be87716c7731fcdc7e2d521c3982b1bc2543de15deaf28a875
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73464f5c03c1b044beaa9a43d5d5dbf215ee42f8d72788dbd8aae205c443a2fb
+oid sha256:ec684daa26188306a57c5592384606a5d8ef0dd8fd9a2b9b015571d9e55b31ff
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2321160360f0869a640c4db1ac92d96f0906aaf4858fa3e0971e87971bf88441
+oid sha256:77ed2668c66e15fef978070af3b112272955a81278a417ee23c724914f309bcb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0db25a0543b49b32b0743ab3aebde93a07e83cb56527812ed97e2834b6d1f576
+oid sha256:31e39c22adc7f851cb4dfb1b8ca342fb69fb987f5fefed5cd8faa7a7e9dc6dad
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cb8cf35bf94a419ce3db03855521f0a295e2d9dd1cdd78580a34a15b60c184d
+oid sha256:84eb3f9af442510bffa023e3c6bdd79209c9e3e15bc60a2b39166fa92e908015
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935c3511559349a68e0c75c3b87066ca7d4af7863dcb94ee59a533b76c75ad0c
+oid sha256:9a58533f5e61baaf0d295b9a19b1c4d2a6e1e9d96b361593f4d95a0f3cb76170
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7650073170661926,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.8790697674418606,
+  "epoch": 3.1069767441860465,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 41,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,118 @@
       "eval_samples_per_second": 14.942,
       "eval_steps_per_second": 3.885,
       "step": 25
+    },
+    {
+      "epoch": 1.9534883720930232,
+      "grad_norm": 7.476520538330078,
+      "learning_rate": 3.904278008308589e-05,
+      "loss": 11.5912,
+      "step": 26
+    },
+    {
+      "epoch": 2.046511627906977,
+      "grad_norm": 5.527069091796875,
+      "learning_rate": 3.570883473686256e-05,
+      "loss": 11.2094,
+      "step": 27
+    },
+    {
+      "epoch": 2.1209302325581394,
+      "grad_norm": 5.50228214263916,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.0862,
+      "step": 28
+    },
+    {
+      "epoch": 2.1953488372093024,
+      "grad_norm": 6.5125651359558105,
+      "learning_rate": 2.9437086397097995e-05,
+      "loss": 10.4032,
+      "step": 29
+    },
+    {
+      "epoch": 2.269767441860465,
+      "grad_norm": 6.218883514404297,
+      "learning_rate": 2.6539958098208027e-05,
+      "loss": 10.4676,
+      "step": 30
+    },
+    {
+      "epoch": 2.344186046511628,
+      "grad_norm": 5.223501205444336,
+      "learning_rate": 2.3827404092068032e-05,
+      "loss": 10.3137,
+      "step": 31
+    },
+    {
+      "epoch": 2.4186046511627906,
+      "grad_norm": 6.159942150115967,
+      "learning_rate": 2.1317016332300447e-05,
+      "loss": 10.5853,
+      "step": 32
+    },
+    {
+      "epoch": 2.4930232558139536,
+      "grad_norm": 6.657078266143799,
+      "learning_rate": 1.902507564684246e-05,
+      "loss": 10.3025,
+      "step": 33
+    },
+    {
+      "epoch": 2.567441860465116,
+      "grad_norm": 5.459758758544922,
+      "learning_rate": 1.6966446150529244e-05,
+      "loss": 10.4436,
+      "step": 34
+    },
+    {
+      "epoch": 2.641860465116279,
+      "grad_norm": 6.186044692993164,
+      "learning_rate": 1.515447884560556e-05,
+      "loss": 10.5271,
+      "step": 35
+    },
+    {
+      "epoch": 2.7162790697674417,
+      "grad_norm": 7.22088098526001,
+      "learning_rate": 1.3600925035352913e-05,
+      "loss": 10.1892,
+      "step": 36
+    },
+    {
+      "epoch": 2.7906976744186047,
+      "grad_norm": 5.603003025054932,
+      "learning_rate": 1.2315860112378455e-05,
+      "loss": 10.7062,
+      "step": 37
+    },
+    {
+      "epoch": 2.8651162790697673,
+      "grad_norm": 5.911949157714844,
+      "learning_rate": 1.130761821582766e-05,
+      "loss": 10.5918,
+      "step": 38
+    },
+    {
+      "epoch": 2.9395348837209303,
+      "grad_norm": 6.643774032592773,
+      "learning_rate": 1.0582738181293923e-05,
+      "loss": 10.518,
+      "step": 39
+    },
+    {
+      "epoch": 3.0325581395348835,
+      "grad_norm": 5.792553424835205,
+      "learning_rate": 1.0145921133960554e-05,
+      "loss": 10.4178,
+      "step": 40
+    },
+    {
+      "epoch": 3.1069767441860465,
+      "grad_norm": 5.410275936126709,
+      "learning_rate": 1e-05,
+      "loss": 10.3721,
+      "step": 41
     }
   ],
   "logging_steps": 1,
@@ -221,12 +333,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.829013890367488e+17,
+  "total_flos": 4.63958278020268e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null