Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4d7b7470072ae09cfb7dc244139594ebd1af72660dbbc7d5b1e394b6b6ae8b1
+oid sha256:fe123da87db7be6ff796fbc69953527f60e62c22cf8e6641d46efdcf59ee8b53
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f898fd4b114b68e5b4c8a2c369f19e46cef8c68f277fc5d1885977d57f67f735
+oid sha256:47bc2eedd646997c29bf3476367f0d685c1dc42233ebad27a17d5fb4352251f7
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1ec906b21013b12bbd77ee479c9e72af02946504171a3eedf686278309afcb3
+oid sha256:5159a80a8009feb53884b61c660979623432af40d97273a9039a41a7d0a1a5dd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.2083852291107178,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.019638648860958365,
+  "best_metric": 2.13885760307312,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03927729772191673,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 28.065,
       "eval_steps_per_second": 3.508,
       "step": 25
+    },
+    {
+      "epoch": 0.0204241948153967,
+      "grad_norm": 1.4164680242538452,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.0483,
+      "step": 26
+    },
+    {
+      "epoch": 0.021209740769835034,
+      "grad_norm": 1.6712983846664429,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.0685,
+      "step": 27
+    },
+    {
+      "epoch": 0.02199528672427337,
+      "grad_norm": 1.9225305318832397,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.2575,
+      "step": 28
+    },
+    {
+      "epoch": 0.022780832678711706,
+      "grad_norm": 1.6477164030075073,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.9326,
+      "step": 29
+    },
+    {
+      "epoch": 0.02356637863315004,
+      "grad_norm": 1.5422395467758179,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.0637,
+      "step": 30
+    },
+    {
+      "epoch": 0.024351924587588374,
+      "grad_norm": 1.8422183990478516,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.2265,
+      "step": 31
+    },
+    {
+      "epoch": 0.02513747054202671,
+      "grad_norm": 1.585951328277588,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.1411,
+      "step": 32
+    },
+    {
+      "epoch": 0.025923016496465043,
+      "grad_norm": 1.7203665971755981,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.0596,
+      "step": 33
+    },
+    {
+      "epoch": 0.02670856245090338,
+      "grad_norm": 1.5029610395431519,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 2.0878,
+      "step": 34
+    },
+    {
+      "epoch": 0.02749410840534171,
+      "grad_norm": 1.9266526699066162,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.272,
+      "step": 35
+    },
+    {
+      "epoch": 0.028279654359780047,
+      "grad_norm": 1.702233076095581,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.1302,
+      "step": 36
+    },
+    {
+      "epoch": 0.029065200314218383,
+      "grad_norm": 1.6544063091278076,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 2.2028,
+      "step": 37
+    },
+    {
+      "epoch": 0.029850746268656716,
+      "grad_norm": 1.5446559190750122,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.1236,
+      "step": 38
+    },
+    {
+      "epoch": 0.030636292223095052,
+      "grad_norm": 1.8277156352996826,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.1114,
+      "step": 39
+    },
+    {
+      "epoch": 0.031421838177533384,
+      "grad_norm": 1.5965498685836792,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.9287,
+      "step": 40
+    },
+    {
+      "epoch": 0.03220738413197172,
+      "grad_norm": 1.9387294054031372,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.3824,
+      "step": 41
+    },
+    {
+      "epoch": 0.032992930086410056,
+      "grad_norm": 1.9508612155914307,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.423,
+      "step": 42
+    },
+    {
+      "epoch": 0.03377847604084839,
+      "grad_norm": 1.6150997877120972,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.0942,
+      "step": 43
+    },
+    {
+      "epoch": 0.03456402199528672,
+      "grad_norm": 2.2546896934509277,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.1891,
+      "step": 44
+    },
+    {
+      "epoch": 0.03534956794972506,
+      "grad_norm": 1.862958312034607,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.0973,
+      "step": 45
+    },
+    {
+      "epoch": 0.03613511390416339,
+      "grad_norm": 1.9793145656585693,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.0145,
+      "step": 46
+    },
+    {
+      "epoch": 0.036920659858601726,
+      "grad_norm": 2.037611484527588,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.128,
+      "step": 47
+    },
+    {
+      "epoch": 0.037706205813040065,
+      "grad_norm": 1.9299999475479126,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.0905,
+      "step": 48
+    },
+    {
+      "epoch": 0.0384917517674784,
+      "grad_norm": 1.8549494743347168,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.1282,
+      "step": 49
+    },
+    {
+      "epoch": 0.03927729772191673,
+      "grad_norm": 2.6206631660461426,
+      "learning_rate": 0.0,
+      "loss": 2.537,
+      "step": 50
+    },
+    {
+      "epoch": 0.03927729772191673,
+      "eval_loss": 2.13885760307312,
+      "eval_runtime": 76.3641,
+      "eval_samples_per_second": 28.076,
+      "eval_steps_per_second": 3.51,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.67755080794112e+16,
+  "total_flos": 3.35510161588224e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null