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:b9958677d822a74081551e0f85a233c1700f4bd4e21bb1131276e8839c0dac1a
+oid sha256:e5709aeefa693f7d5b93b7c49854fffea031f4318bcaaf89b4e8725366141ec3
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39af447e8ee3b88f5378037bec15dce3370626bf41d6872b2dd622e8d88c4b52
+oid sha256:2ae786c9f627e2523fed346d92f928c04a7aa4913ff7e8304fe52f309eced9de
 size 1001863522

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc7d5f81cc1567f8e0ffa0cab8835988dd15e7ecaeeac9139b16c8d96859ffca
+oid sha256:b474e5149b21f64a1ce0c5942810d1ace65abf10ebe5ee2b10eb7f5614c91f94
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ef3e09cdc45bd74f2d86972e74a57c56ea7533589ef2f7ab26b438ccb78f200
+oid sha256:d8cd03d1e0bf00d787a45dba164e732e4b07efa0c8134bfaa649d7c7ba50c9c7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9e6f39983e1f416171a756b503a109fed1e35e906c834d01839ab332909c641
+oid sha256:24e754ffa126a571d843e9b1c1f1d2ebc5e7c1ee0db360328af6d94b4f51714d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b88548de3fe89a2a72d298b03763bf6032778780e5330229294c7f07b9421e64
+oid sha256:7bde6f0d7dc60d5465bc71ebf9276915461cb7742722ce104dcdc397e2e84228
 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": 0.09957851469516754,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6015037593984962,
+  "best_metric": 0.09947212040424347,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.2045112781954888,
   "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": 20.691,
       "eval_steps_per_second": 2.586,
       "step": 25
+    },
+    {
+      "epoch": 0.6255639097744361,
+      "grad_norm": 0.02670644409954548,
+      "learning_rate": 5e-05,
+      "loss": 0.0999,
+      "step": 26
+    },
+    {
+      "epoch": 0.649624060150376,
+      "grad_norm": 0.02877388522028923,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0983,
+      "step": 27
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 0.031500719487667084,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.096,
+      "step": 28
+    },
+    {
+      "epoch": 0.6977443609022557,
+      "grad_norm": 0.048165999352931976,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0958,
+      "step": 29
+    },
+    {
+      "epoch": 0.7218045112781954,
+      "grad_norm": 0.09344542026519775,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0965,
+      "step": 30
+    },
+    {
+      "epoch": 0.7458646616541353,
+      "grad_norm": 0.12452530115842819,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0986,
+      "step": 31
+    },
+    {
+      "epoch": 0.7699248120300752,
+      "grad_norm": 0.12313531339168549,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.1015,
+      "step": 32
+    },
+    {
+      "epoch": 0.793984962406015,
+      "grad_norm": 0.1442219614982605,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.105,
+      "step": 33
+    },
+    {
+      "epoch": 0.8180451127819549,
+      "grad_norm": 0.06111603602766991,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1014,
+      "step": 34
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.027853839099407196,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0995,
+      "step": 35
+    },
+    {
+      "epoch": 0.8661654135338346,
+      "grad_norm": 0.13428233563899994,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1005,
+      "step": 36
+    },
+    {
+      "epoch": 0.8902255639097745,
+      "grad_norm": 0.12706559896469116,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.1006,
+      "step": 37
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.15370112657546997,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1004,
+      "step": 38
+    },
+    {
+      "epoch": 0.9383458646616541,
+      "grad_norm": 0.1685517281293869,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.1,
+      "step": 39
+    },
+    {
+      "epoch": 0.9624060150375939,
+      "grad_norm": 0.06856564432382584,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0956,
+      "step": 40
+    },
+    {
+      "epoch": 0.9864661654135338,
+      "grad_norm": 0.1981419026851654,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.097,
+      "step": 41
+    },
+    {
+      "epoch": 1.0120300751879698,
+      "grad_norm": 0.07202955335378647,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1529,
+      "step": 42
+    },
+    {
+      "epoch": 1.0360902255639097,
+      "grad_norm": 0.030848056077957153,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.101,
+      "step": 43
+    },
+    {
+      "epoch": 1.0601503759398496,
+      "grad_norm": 0.03846440464258194,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1012,
+      "step": 44
+    },
+    {
+      "epoch": 1.0842105263157895,
+      "grad_norm": 0.036180026829242706,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1004,
+      "step": 45
+    },
+    {
+      "epoch": 1.1082706766917294,
+      "grad_norm": 0.025751329958438873,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0993,
+      "step": 46
+    },
+    {
+      "epoch": 1.132330827067669,
+      "grad_norm": 0.06255143880844116,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0998,
+      "step": 47
+    },
+    {
+      "epoch": 1.156390977443609,
+      "grad_norm": 0.04273088276386261,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0987,
+      "step": 48
+    },
+    {
+      "epoch": 1.1804511278195489,
+      "grad_norm": 0.02951870672404766,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0958,
+      "step": 49
+    },
+    {
+      "epoch": 1.2045112781954888,
+      "grad_norm": 0.03614836931228638,
+      "learning_rate": 0.0,
+      "loss": 0.0964,
+      "step": 50
+    },
+    {
+      "epoch": 1.2045112781954888,
+      "eval_loss": 0.09947212040424347,
+      "eval_runtime": 13.5385,
+      "eval_samples_per_second": 20.682,
+      "eval_steps_per_second": 2.585,
+      "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": 5.102844201926656e+17,
+  "total_flos": 1.0205688403853312e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null