Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dc9a736c5b56c25eb072012e523ce06dcb38a0f7dd7418b6bf7ea4fb9dec91c
+oid sha256:4aed06751cae1baa5e0b626bb88883d870d03b3895b7a4e863a0411366f26418
 size 891333320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:972d8d562b62d4c69c691fa7c9c8ced52eccbe5aba3efb05430986cd650b8b2f
+oid sha256:d19389f29d1ca04456aa0609ec5368d00094984ef88ba50d2a1c3efb7bde3a3a
 size 1782848954

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fe71e06afdccef85381591f2fc2ba1c8ddc072273ce9c77bed7c91959b30373
+oid sha256:8112cde53ce6b438ebd8492c5d287e06749e6a168ed1d4e688b771b0e73ce38b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7179549932479858,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.053763440860215055,
+  "best_metric": 1.644777774810791,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.10752688172043011,
   "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": 6.668,
       "eval_steps_per_second": 0.834,
       "step": 25
+    },
+    {
+      "epoch": 0.05591397849462366,
+      "grad_norm": 2.289424180984497,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 6.4329,
+      "step": 26
+    },
+    {
+      "epoch": 0.05806451612903226,
+      "grad_norm": 2.517298460006714,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 6.0302,
+      "step": 27
+    },
+    {
+      "epoch": 0.060215053763440864,
+      "grad_norm": 3.4784586429595947,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 6.5625,
+      "step": 28
+    },
+    {
+      "epoch": 0.06236559139784946,
+      "grad_norm": 3.08809494972229,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 7.3558,
+      "step": 29
+    },
+    {
+      "epoch": 0.06451612903225806,
+      "grad_norm": 2.907604455947876,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 6.9755,
+      "step": 30
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 2.4555325508117676,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 7.0884,
+      "step": 31
+    },
+    {
+      "epoch": 0.06881720430107527,
+      "grad_norm": 3.109780788421631,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 5.9083,
+      "step": 32
+    },
+    {
+      "epoch": 0.07096774193548387,
+      "grad_norm": 5.803027629852295,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 6.5149,
+      "step": 33
+    },
+    {
+      "epoch": 0.07311827956989247,
+      "grad_norm": 3.701385259628296,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 6.6396,
+      "step": 34
+    },
+    {
+      "epoch": 0.07526881720430108,
+      "grad_norm": 2.906161069869995,
+      "learning_rate": 5e-05,
+      "loss": 6.7558,
+      "step": 35
+    },
+    {
+      "epoch": 0.07741935483870968,
+      "grad_norm": 3.355015993118286,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 6.6618,
+      "step": 36
+    },
+    {
+      "epoch": 0.07956989247311828,
+      "grad_norm": 2.019418716430664,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 7.2221,
+      "step": 37
+    },
+    {
+      "epoch": 0.08172043010752689,
+      "grad_norm": 2.2855887413024902,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 5.8867,
+      "step": 38
+    },
+    {
+      "epoch": 0.08387096774193549,
+      "grad_norm": 5.668225288391113,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 7.0586,
+      "step": 39
+    },
+    {
+      "epoch": 0.08602150537634409,
+      "grad_norm": 49.42198181152344,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 6.7356,
+      "step": 40
+    },
+    {
+      "epoch": 0.08817204301075268,
+      "grad_norm": 3.67435359954834,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 6.6045,
+      "step": 41
+    },
+    {
+      "epoch": 0.09032258064516129,
+      "grad_norm": 3.468963146209717,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 6.9789,
+      "step": 42
+    },
+    {
+      "epoch": 0.09247311827956989,
+      "grad_norm": 1.8968158960342407,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 5.5492,
+      "step": 43
+    },
+    {
+      "epoch": 0.09462365591397849,
+      "grad_norm": 46.57176208496094,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 6.3358,
+      "step": 44
+    },
+    {
+      "epoch": 0.0967741935483871,
+      "grad_norm": 2.8659753799438477,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 5.6891,
+      "step": 45
+    },
+    {
+      "epoch": 0.0989247311827957,
+      "grad_norm": 6.436995983123779,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 6.5427,
+      "step": 46
+    },
+    {
+      "epoch": 0.1010752688172043,
+      "grad_norm": 2.667637825012207,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 5.9998,
+      "step": 47
+    },
+    {
+      "epoch": 0.1032258064516129,
+      "grad_norm": 4.361298084259033,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 6.8748,
+      "step": 48
+    },
+    {
+      "epoch": 0.1053763440860215,
+      "grad_norm": 4.055363655090332,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 6.2738,
+      "step": 49
+    },
+    {
+      "epoch": 0.10752688172043011,
+      "grad_norm": 3.4398603439331055,
+      "learning_rate": 0.0,
+      "loss": 6.8857,
+      "step": 50
+    },
+    {
+      "epoch": 0.10752688172043011,
+      "eval_loss": 1.644777774810791,
+      "eval_runtime": 117.505,
+      "eval_samples_per_second": 6.672,
+      "eval_steps_per_second": 0.834,
+      "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": 6.890566189056e+16,
+  "total_flos": 1.3781132378112e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null