Training in progress, step 49, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3e930eef78c75921b12dbf50e2a5761711587949321829d955952e00cdfa923
+oid sha256:f8f9cb33f06e24b66626bbe1b0d59db9016bbdf5cb26fbf3df33e25b0b8dea3a
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5f74a26db96fb589be88dad2010752d3297cc21f1262ad404899f2b3b1df784
+oid sha256:9c8f65051944a0e888846aa160bedcbe222c3bf3bf41a70ca0060106b158a8c2
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15b1d443a5d8a7658af1ef0766d68ffb6dec16dbe3bf42e92df0ab32cee94597
+oid sha256:1bcf6e5658b0a6cbc255b90dc59c9dfc1ad300ecfef08f0956ef1d3cd85b1a03
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:902075d31a380e9aadd567d44cfc00b96c9ada0b1a8513512c781b71033bda2c
+oid sha256:4840430526f788f4d5eca4f42d713228f6bc8b78036fcb10a722f43ded71f3b4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0857e29d20ac9ff5fb8766baa246ca4ddf89c83b6d5cda493472daa240c6a731
+oid sha256:1edadec0afa15444d6a230113463f9f679d2732e370036d3c18a84c2e36a31ea
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3066d70ddb46a6ca814d7df3ca80ba657e4cad13049610c87467153a79895ea0
+oid sha256:86d2622d346b98999b0de1665d773fbd7a7e8b93470eb499da9d69fd5ac49631
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:840657c72d1644d32902ed3baed4169f8fa8749780cabcde307874a07544bcbd
+oid sha256:25704ee5478cd4521ee5db3e9e14050e9c72edebe1088acf05e49ba2bb8ed7fb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.556420233463035,
+  "epoch": 3.0505836575875485,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 49,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,174 @@
       "eval_samples_per_second": 15.079,
       "eval_steps_per_second": 1.937,
       "step": 25
+    },
+    {
+      "epoch": 1.6186770428015564,
+      "grad_norm": 18.992616653442383,
+      "learning_rate": 4.832925114961629e-05,
+      "loss": 2.7107,
+      "step": 26
+    },
+    {
+      "epoch": 1.6809338521400778,
+      "grad_norm": 37.28364944458008,
+      "learning_rate": 4.4995215418795085e-05,
+      "loss": 1.4825,
+      "step": 27
+    },
+    {
+      "epoch": 1.7431906614785992,
+      "grad_norm": 19.023557662963867,
+      "learning_rate": 4.1683532270843504e-05,
+      "loss": 9.7886,
+      "step": 28
+    },
+    {
+      "epoch": 1.8054474708171206,
+      "grad_norm": 24.320850372314453,
+      "learning_rate": 3.840899248662358e-05,
+      "loss": 5.4721,
+      "step": 29
+    },
+    {
+      "epoch": 1.867704280155642,
+      "grad_norm": 38.466636657714844,
+      "learning_rate": 3.5186220955718306e-05,
+      "loss": 2.5858,
+      "step": 30
+    },
+    {
+      "epoch": 1.9299610894941635,
+      "grad_norm": 37.14291763305664,
+      "learning_rate": 3.202961135812437e-05,
+      "loss": 2.0515,
+      "step": 31
+    },
+    {
+      "epoch": 1.9922178988326849,
+      "grad_norm": 67.8818588256836,
+      "learning_rate": 2.895326187858326e-05,
+      "loss": 6.3966,
+      "step": 32
+    },
+    {
+      "epoch": 2.054474708171206,
+      "grad_norm": 17.14106559753418,
+      "learning_rate": 2.5970912240665813e-05,
+      "loss": 1.972,
+      "step": 33
+    },
+    {
+      "epoch": 2.1167315175097277,
+      "grad_norm": 65.180908203125,
+      "learning_rate": 2.3095882341831372e-05,
+      "loss": 4.4205,
+      "step": 34
+    },
+    {
+      "epoch": 2.178988326848249,
+      "grad_norm": 25.168292999267578,
+      "learning_rate": 2.0341012763532243e-05,
+      "loss": 2.164,
+      "step": 35
+    },
+    {
+      "epoch": 2.2412451361867705,
+      "grad_norm": 17.58421516418457,
+      "learning_rate": 1.771860742205988e-05,
+      "loss": 15.0917,
+      "step": 36
+    },
+    {
+      "epoch": 2.3035019455252916,
+      "grad_norm": 29.59916877746582,
+      "learning_rate": 1.5240378616267886e-05,
+      "loss": 2.138,
+      "step": 37
+    },
+    {
+      "epoch": 2.3657587548638133,
+      "grad_norm": 26.598777770996094,
+      "learning_rate": 1.2917394717602121e-05,
+      "loss": 3.6291,
+      "step": 38
+    },
+    {
+      "epoch": 2.4280155642023344,
+      "grad_norm": 34.868186950683594,
+      "learning_rate": 1.0760030736066951e-05,
+      "loss": 2.83,
+      "step": 39
+    },
+    {
+      "epoch": 2.490272373540856,
+      "grad_norm": 18.106393814086914,
+      "learning_rate": 8.777921982911996e-06,
+      "loss": 36.5244,
+      "step": 40
+    },
+    {
+      "epoch": 2.5525291828793772,
+      "grad_norm": 41.7713508605957,
+      "learning_rate": 6.979921036993042e-06,
+      "loss": 2.0097,
+      "step": 41
+    },
+    {
+      "epoch": 2.614785992217899,
+      "grad_norm": 36.23786163330078,
+      "learning_rate": 5.374058207005944e-06,
+      "loss": 3.8853,
+      "step": 42
+    },
+    {
+      "epoch": 2.6770428015564205,
+      "grad_norm": 39.74626922607422,
+      "learning_rate": 3.967505666178556e-06,
+      "loss": 2.0171,
+      "step": 43
+    },
+    {
+      "epoch": 2.7392996108949417,
+      "grad_norm": 32.494911193847656,
+      "learning_rate": 2.7665454196040664e-06,
+      "loss": 8.4961,
+      "step": 44
+    },
+    {
+      "epoch": 2.801556420233463,
+      "grad_norm": 41.86767578125,
+      "learning_rate": 1.7765412472811771e-06,
+      "loss": 2.7977,
+      "step": 45
+    },
+    {
+      "epoch": 2.8638132295719845,
+      "grad_norm": 47.389488220214844,
+      "learning_rate": 1.0019147481706625e-06,
+      "loss": 3.5359,
+      "step": 46
+    },
+    {
+      "epoch": 2.926070038910506,
+      "grad_norm": 39.33119583129883,
+      "learning_rate": 4.461255922609986e-07,
+      "loss": 2.4863,
+      "step": 47
+    },
+    {
+      "epoch": 2.9883268482490273,
+      "grad_norm": 170.0821990966797,
+      "learning_rate": 1.1165606884234181e-07,
+      "loss": 6.6675,
+      "step": 48
+    },
+    {
+      "epoch": 3.0505836575875485,
+      "grad_norm": 93.12586975097656,
+      "learning_rate": 0.0,
+      "loss": 2.3611,
+      "step": 49
     }
   ],
   "logging_steps": 1,
@@ -221,12 +389,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.829062208749568e+17,
+  "total_flos": 5.544961929149153e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null