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:b38af76083b7209203eade323f609157f5e5e039376c484efaa9222208fd8e39
+oid sha256:f19d48ac3c5b4161cdf337942f7fc34427109155164e8007943b027243d803a5
 size 1101095848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cef980dda2627325eed86a5751ad1c2d3f8c5f1e53af808cfddefb1c8ba14604
+oid sha256:29fe034ec6beb2e116200edb695369f53f956ee00a0c54d79af11343b875c454
 size 559894228

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b8eda32853cbd4a237342d189b145da6e2c8a68dc0ffae163df5b4eacbfe64a
+oid sha256:08939710e1b1c99602c61e1e2dd8ea92c92f7c3524e62dfe91c7da0dbd0e0214
 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": 0.2792419195175171,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0010282987824942415,
+  "best_metric": 0.20316138863563538,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.002056597564988483,
   "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": 7.295,
       "eval_steps_per_second": 0.912,
       "step": 25
+    },
+    {
+      "epoch": 0.0010694307337940111,
+      "grad_norm": 4.635091781616211,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.3612,
+      "step": 26
+    },
+    {
+      "epoch": 0.0011105626850937808,
+      "grad_norm": 2.413482904434204,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.2537,
+      "step": 27
+    },
+    {
+      "epoch": 0.0011516946363935505,
+      "grad_norm": 2.4534168243408203,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.2547,
+      "step": 28
+    },
+    {
+      "epoch": 0.0011928265876933201,
+      "grad_norm": 4.514098644256592,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.3676,
+      "step": 29
+    },
+    {
+      "epoch": 0.0012339585389930898,
+      "grad_norm": 5.916527271270752,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.5274,
+      "step": 30
+    },
+    {
+      "epoch": 0.0012750904902928595,
+      "grad_norm": 5.45999813079834,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.4659,
+      "step": 31
+    },
+    {
+      "epoch": 0.0013162224415926291,
+      "grad_norm": 4.046067237854004,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.311,
+      "step": 32
+    },
+    {
+      "epoch": 0.0013573543928923988,
+      "grad_norm": 0.2217586785554886,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.2055,
+      "step": 33
+    },
+    {
+      "epoch": 0.0013984863441921685,
+      "grad_norm": 2.0084125995635986,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.262,
+      "step": 34
+    },
+    {
+      "epoch": 0.0014396182954919381,
+      "grad_norm": 2.1569504737854004,
+      "learning_rate": 5e-05,
+      "loss": 0.2769,
+      "step": 35
+    },
+    {
+      "epoch": 0.0014807502467917078,
+      "grad_norm": 2.107754945755005,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.2857,
+      "step": 36
+    },
+    {
+      "epoch": 0.0015218821980914775,
+      "grad_norm": 0.5223035216331482,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.1738,
+      "step": 37
+    },
+    {
+      "epoch": 0.0015630141493912471,
+      "grad_norm": 0.17265839874744415,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.2089,
+      "step": 38
+    },
+    {
+      "epoch": 0.0016041461006910168,
+      "grad_norm": 0.9179982542991638,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.2048,
+      "step": 39
+    },
+    {
+      "epoch": 0.0016452780519907865,
+      "grad_norm": 0.45841121673583984,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2062,
+      "step": 40
+    },
+    {
+      "epoch": 0.0016864100032905561,
+      "grad_norm": 0.1439216583967209,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.2099,
+      "step": 41
+    },
+    {
+      "epoch": 0.0017275419545903258,
+      "grad_norm": 0.22398719191551208,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.2121,
+      "step": 42
+    },
+    {
+      "epoch": 0.0017686739058900955,
+      "grad_norm": 0.5332353711128235,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.2314,
+      "step": 43
+    },
+    {
+      "epoch": 0.0018098058571898651,
+      "grad_norm": 0.13061563670635223,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2174,
+      "step": 44
+    },
+    {
+      "epoch": 0.0018509378084896348,
+      "grad_norm": 0.3310577869415283,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.21,
+      "step": 45
+    },
+    {
+      "epoch": 0.0018920697597894045,
+      "grad_norm": 1.527039885520935,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.1943,
+      "step": 46
+    },
+    {
+      "epoch": 0.0019332017110891741,
+      "grad_norm": 0.961459755897522,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.1982,
+      "step": 47
+    },
+    {
+      "epoch": 0.0019743336623889436,
+      "grad_norm": 0.12971656024456024,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.1915,
+      "step": 48
+    },
+    {
+      "epoch": 0.0020154656136887133,
+      "grad_norm": 0.8849334120750427,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.2229,
+      "step": 49
+    },
+    {
+      "epoch": 0.002056597564988483,
+      "grad_norm": 0.23174209892749786,
+      "learning_rate": 0.0,
+      "loss": 0.2113,
+      "step": 50
+    },
+    {
+      "epoch": 0.002056597564988483,
+      "eval_loss": 0.20316138863563538,
+      "eval_runtime": 5612.293,
+      "eval_samples_per_second": 7.296,
+      "eval_steps_per_second": 0.912,
+      "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": 7.01237683027968e+16,
+  "total_flos": 1.402475366055936e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null