Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33619e35b9f63cfd95faf72d153b11018ec13ebfc3bc99f2f8530acc3e1f746b
+oid sha256:e43958689607d9c1cc451bd5c080ee22405bef690635bd976a72207074a0ed37
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a1c8d30d3d7d12cec33478b6654a083a37b41d1383a21fcd4d76d773cfa0091
+oid sha256:53db73db1667510dbe40336b7cca7368cb751704a37ddb6896fc633cbd0beb18
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:673aa49bd42fdca2bd68ef0b300c4d1d7761e8b15050332419b355897a95daa6
+oid sha256:ddddae5d3786d1118997192bed9a1bc3d9a652a61d12de95e281c03bb410109b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74e770685c6ec368384be54eed142de6b33c6c657e495aa7cc92858738ec3d60
+oid sha256:7ff4c13f2ab9b6be5fb819cebc5c29377e07e327b43ada42f1517d0901aca100
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4196d5516b0f30d9eefb5fb7050704103051a8d52131880c4f1785ff55fea411
+oid sha256:97be5c979e789af671de7c4c7c1aec5edbed3aaeb4dae521709b1e2629c13df2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aec020e2308c4eb998139f5baa922e14cc6ba0ee7182f58c50c4255b1ffb6584
+oid sha256:5426e3be471fd6240764f89b6e341529d190c7d9c19666db6520f3a36e6f3ca4
 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": 0.7228643894195557,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2737850787132101,
+  "best_metric": 0.7085694074630737,
+  "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": 31.569,
       "eval_steps_per_second": 3.953,
       "step": 25
+    },
+    {
+      "epoch": 0.28473648186173856,
+      "grad_norm": 0.20670099556446075,
+      "learning_rate": 5e-05,
+      "loss": 0.58,
+      "step": 26
+    },
+    {
+      "epoch": 0.29568788501026694,
+      "grad_norm": 0.35974618792533875,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.6536,
+      "step": 27
+    },
+    {
+      "epoch": 0.3066392881587953,
+      "grad_norm": 0.2486371546983719,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.6827,
+      "step": 28
+    },
+    {
+      "epoch": 0.31759069130732376,
+      "grad_norm": 0.23610734939575195,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.6706,
+      "step": 29
+    },
+    {
+      "epoch": 0.32854209445585214,
+      "grad_norm": 0.2577800154685974,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7499,
+      "step": 30
+    },
+    {
+      "epoch": 0.3394934976043806,
+      "grad_norm": 0.22855328023433685,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7138,
+      "step": 31
+    },
+    {
+      "epoch": 0.35044490075290896,
+      "grad_norm": 0.2566169500350952,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7411,
+      "step": 32
+    },
+    {
+      "epoch": 0.3613963039014374,
+      "grad_norm": 0.2585206627845764,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.7747,
+      "step": 33
+    },
+    {
+      "epoch": 0.3723477070499658,
+      "grad_norm": 0.26253750920295715,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7487,
+      "step": 34
+    },
+    {
+      "epoch": 0.38329911019849416,
+      "grad_norm": 0.28885534405708313,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7874,
+      "step": 35
+    },
+    {
+      "epoch": 0.3942505133470226,
+      "grad_norm": 0.334803968667984,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7935,
+      "step": 36
+    },
+    {
+      "epoch": 0.405201916495551,
+      "grad_norm": 0.4043166935443878,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.712,
+      "step": 37
+    },
+    {
+      "epoch": 0.4161533196440794,
+      "grad_norm": 0.15596741437911987,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5926,
+      "step": 38
+    },
+    {
+      "epoch": 0.4271047227926078,
+      "grad_norm": 0.14685985445976257,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6451,
+      "step": 39
+    },
+    {
+      "epoch": 0.4380561259411362,
+      "grad_norm": 0.1911505162715912,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6359,
+      "step": 40
+    },
+    {
+      "epoch": 0.4490075290896646,
+      "grad_norm": 0.20567315816879272,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6526,
+      "step": 41
+    },
+    {
+      "epoch": 0.459958932238193,
+      "grad_norm": 0.17049774527549744,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7154,
+      "step": 42
+    },
+    {
+      "epoch": 0.47091033538672145,
+      "grad_norm": 0.18450334668159485,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6847,
+      "step": 43
+    },
+    {
+      "epoch": 0.48186173853524983,
+      "grad_norm": 0.2177756428718567,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.743,
+      "step": 44
+    },
+    {
+      "epoch": 0.4928131416837782,
+      "grad_norm": 0.21047337353229523,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7845,
+      "step": 45
+    },
+    {
+      "epoch": 0.5037645448323066,
+      "grad_norm": 0.226828470826149,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.748,
+      "step": 46
+    },
+    {
+      "epoch": 0.5147159479808351,
+      "grad_norm": 0.22788920998573303,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7197,
+      "step": 47
+    },
+    {
+      "epoch": 0.5256673511293635,
+      "grad_norm": 0.2771904468536377,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7575,
+      "step": 48
+    },
+    {
+      "epoch": 0.5366187542778919,
+      "grad_norm": 0.31342819333076477,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8068,
+      "step": 49
+    },
+    {
+      "epoch": 0.5475701574264202,
+      "grad_norm": 0.4300288259983063,
+      "learning_rate": 0.0,
+      "loss": 0.7112,
+      "step": 50
+    },
+    {
+      "epoch": 0.5475701574264202,
+      "eval_loss": 0.7085694074630737,
+      "eval_runtime": 19.4794,
+      "eval_samples_per_second": 31.572,
+      "eval_steps_per_second": 3.953,
+      "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": 2.9859068337822106e+17,
+  "total_flos": 5.969948642440643e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null