Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28b3eaab441b1eeebcd690f379a7a0e526f743f21cf36bae91cdd61759b93192
+oid sha256:912440c7d788fbb291bc2e8b60c47a973bcc0ee18e1402c32fad385f7b3c468a
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3d7b38f32d7aa1ef984d293405a1557a551158aacc20d403f653743486f692a
+oid sha256:7f704069a84b76439368f72120c2a684331cfd0b70706080c1b5666e3484a7b9
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed7b47205fddf9e9db7f772c3d7446c1656678da8752530429dec32b37959d28
+oid sha256:5df77345f50ac68162c909d19c23df3ef1b52cdb17442d28d590b7b9f9c0777a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:945f80db19cb016e9c19a2b4d8e0693c83d40c61bfa7df7cc39bff93744302fa
+oid sha256:1ce5c82499837c4871e3731249d2cbdb7cd00f7216cf63b583d418e08141133c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74e3f5e7fe2740687cf41c61d8d6897a75c71ae36910a35e29235f72d66fa530
+oid sha256:9b6aecf297643ed6687c718fb41c7c9d97adfcfb2d9dc85601382cd91ba9918b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f9e67e06a2b17107068cbf4d10213d3ebef427f1710e1cdba30b33e1f83022a
+oid sha256:cf256a060351f79305171b202af0ee458b34835ef553661fcd7b7198670f564d
 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": 0.7244551777839661,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2737850787132101,
+  "best_metric": 0.7186086177825928,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5475701574264202,
   "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": 139.934,
       "eval_steps_per_second": 17.52,
       "step": 25
+    },
+    {
+      "epoch": 0.28473648186173856,
+      "grad_norm": 0.23188556730747223,
+      "learning_rate": 5e-05,
+      "loss": 0.6339,
+      "step": 26
+    },
+    {
+      "epoch": 0.29568788501026694,
+      "grad_norm": 0.3052370250225067,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.7263,
+      "step": 27
+    },
+    {
+      "epoch": 0.3066392881587953,
+      "grad_norm": 0.32998526096343994,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.6687,
+      "step": 28
+    },
+    {
+      "epoch": 0.31759069130732376,
+      "grad_norm": 0.3732319176197052,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.6641,
+      "step": 29
+    },
+    {
+      "epoch": 0.32854209445585214,
+      "grad_norm": 0.39839038252830505,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7225,
+      "step": 30
+    },
+    {
+      "epoch": 0.3394934976043806,
+      "grad_norm": 0.43337464332580566,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7562,
+      "step": 31
+    },
+    {
+      "epoch": 0.35044490075290896,
+      "grad_norm": 0.408007949590683,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7658,
+      "step": 32
+    },
+    {
+      "epoch": 0.3613963039014374,
+      "grad_norm": 0.43947532773017883,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.7477,
+      "step": 33
+    },
+    {
+      "epoch": 0.3723477070499658,
+      "grad_norm": 0.45250290632247925,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7523,
+      "step": 34
+    },
+    {
+      "epoch": 0.38329911019849416,
+      "grad_norm": 0.4638631045818329,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7515,
+      "step": 35
+    },
+    {
+      "epoch": 0.3942505133470226,
+      "grad_norm": 0.5080087780952454,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7318,
+      "step": 36
+    },
+    {
+      "epoch": 0.405201916495551,
+      "grad_norm": 0.582893967628479,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.6909,
+      "step": 37
+    },
+    {
+      "epoch": 0.4161533196440794,
+      "grad_norm": 0.22855021059513092,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5866,
+      "step": 38
+    },
+    {
+      "epoch": 0.4271047227926078,
+      "grad_norm": 0.20767220854759216,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6823,
+      "step": 39
+    },
+    {
+      "epoch": 0.4380561259411362,
+      "grad_norm": 0.23997880518436432,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.729,
+      "step": 40
+    },
+    {
+      "epoch": 0.4490075290896646,
+      "grad_norm": 0.26613447070121765,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7155,
+      "step": 41
+    },
+    {
+      "epoch": 0.459958932238193,
+      "grad_norm": 0.2961955666542053,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7087,
+      "step": 42
+    },
+    {
+      "epoch": 0.47091033538672145,
+      "grad_norm": 0.31900477409362793,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.7365,
+      "step": 43
+    },
+    {
+      "epoch": 0.48186173853524983,
+      "grad_norm": 0.3380311131477356,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7116,
+      "step": 44
+    },
+    {
+      "epoch": 0.4928131416837782,
+      "grad_norm": 0.3615745007991791,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7719,
+      "step": 45
+    },
+    {
+      "epoch": 0.5037645448323066,
+      "grad_norm": 0.4000967741012573,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.7679,
+      "step": 46
+    },
+    {
+      "epoch": 0.5147159479808351,
+      "grad_norm": 0.44231659173965454,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7702,
+      "step": 47
+    },
+    {
+      "epoch": 0.5256673511293635,
+      "grad_norm": 0.48174336552619934,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.747,
+      "step": 48
+    },
+    {
+      "epoch": 0.5366187542778919,
+      "grad_norm": 0.5735424160957336,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7402,
+      "step": 49
+    },
+    {
+      "epoch": 0.5475701574264202,
+      "grad_norm": 0.6842880249023438,
+      "learning_rate": 0.0,
+      "loss": 0.703,
+      "step": 50
+    },
+    {
+      "epoch": 0.5475701574264202,
+      "eval_loss": 0.7186086177825928,
+      "eval_runtime": 4.3958,
+      "eval_samples_per_second": 139.905,
+      "eval_steps_per_second": 17.517,
+      "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": 1.4783502046199808e+16,
+  "total_flos": 2.955777588540211e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null