Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5afbf71e12edb90622cabc52d0874d38529e6374428481b54b4a6cf4e6c5fbb3
+oid sha256:e1c8d3a636ba2f1b0940c5891dd6c5b632d43c653411590b146cfdfd527e1238
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83ee5cd651dd1bb20fb82c002179b114a34cd13650dd07853747c9edead3034b
+oid sha256:0f8f2c84b4a679b239318b5473f08a506a7e5f04d83676709f992cfccf323eb1
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24902234f8eb71e8a5693989bfc9f7befc000020a5e274aba470a6eea1c48225
+oid sha256:9cb157ecc82d366ff65ed43044084bec042cd353aa2c5fd59715719d82432c52
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45d38d6da46b5e80bfa0d694297057d8d46e6a0a78737af184e4d38c43215675
+oid sha256:970d2a52770f7a6e4d953f92d56d4e953900b570f45d0a24ac3adfb27eb13feb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b11a25d5589b7d71f4dcac232027c8e273134d866f0da96c47c92312f1855cd8
+oid sha256:50ff61a9b16a2d39042d84e6e555f63aff7a47b1c539dc5bea609f9c00000645
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee74d05ad4ce546bf8ab67be171d2f479833a3f1dd92d8d7c323a0f2f40f7908
+oid sha256:fd1459bb325a42e2370dd7649cab93e414db337c0f087f18c054f99412be5826
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8770236968994141,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.8620689655172413,
+  "best_metric": 0.8296974301338196,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.7241379310344827,
   "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": 47.523,
       "eval_steps_per_second": 6.093,
       "step": 25
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 0.5288706421852112,
+      "learning_rate": 5e-05,
+      "loss": 0.8239,
+      "step": 26
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 0.5527832508087158,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.8806,
+      "step": 27
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.7218241095542908,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9175,
+      "step": 28
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.44543588161468506,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.736,
+      "step": 29
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 0.40811803936958313,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8053,
+      "step": 30
+    },
+    {
+      "epoch": 1.0689655172413792,
+      "grad_norm": 0.4515950381755829,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8298,
+      "step": 31
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 0.5151574015617371,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.924,
+      "step": 32
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 0.4836006462574005,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.7411,
+      "step": 33
+    },
+    {
+      "epoch": 1.1724137931034484,
+      "grad_norm": 0.5116979479789734,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8224,
+      "step": 34
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 0.543500542640686,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.824,
+      "step": 35
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "grad_norm": 0.6314417719841003,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8329,
+      "step": 36
+    },
+    {
+      "epoch": 1.2758620689655173,
+      "grad_norm": 0.3729710280895233,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7086,
+      "step": 37
+    },
+    {
+      "epoch": 1.3103448275862069,
+      "grad_norm": 0.4598703980445862,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7906,
+      "step": 38
+    },
+    {
+      "epoch": 1.3448275862068966,
+      "grad_norm": 0.5059497356414795,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.7268,
+      "step": 39
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.48165661096572876,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8421,
+      "step": 40
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 0.5090142488479614,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7836,
+      "step": 41
+    },
+    {
+      "epoch": 1.4482758620689655,
+      "grad_norm": 0.5581346750259399,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7805,
+      "step": 42
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "grad_norm": 0.6325652599334717,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8853,
+      "step": 43
+    },
+    {
+      "epoch": 1.5172413793103448,
+      "grad_norm": 0.3990720212459564,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7517,
+      "step": 44
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 0.45109397172927856,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7909,
+      "step": 45
+    },
+    {
+      "epoch": 1.5862068965517242,
+      "grad_norm": 0.512504518032074,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8714,
+      "step": 46
+    },
+    {
+      "epoch": 1.6206896551724137,
+      "grad_norm": 0.4838815927505493,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.8317,
+      "step": 47
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 0.526544451713562,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7849,
+      "step": 48
+    },
+    {
+      "epoch": 1.6896551724137931,
+      "grad_norm": 0.6029788255691528,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.901,
+      "step": 49
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 0.6109845042228699,
+      "learning_rate": 0.0,
+      "loss": 0.8062,
+      "step": 50
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "eval_loss": 0.8296974301338196,
+      "eval_runtime": 4.1199,
+      "eval_samples_per_second": 47.331,
+      "eval_steps_per_second": 6.068,
+      "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": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null