Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f3847173319f1921b62140cb97aeb38035e112c4dcec41b3bfae0ee3efdb538
+oid sha256:35d8c306aed77998267c2146d8ec62b279771ca8a261a45ea7f7453b5b6af623
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b53f7d321482983df5fbed8a38328e0c726cfb92ff07eb640df28ff399a692d
+oid sha256:a008ec9fa3fda1af20d8df5c9fea1b56ed6f042ae1fe701b044df2dc135a6488
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:902305a20a9a42cfdc94e1967946751390ef05660917b664f253c08a95727282
+oid sha256:ae670c81a105ede004ed24c74062bd74578c14d1ad4b33c2df1beb96b739ac5f
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d933920f39eef47b92cd621d611e97e2dce1692f98fedd4cc4ed250a27009bb
+oid sha256:3e91c7095c9226124094a6fdcd9d18b125126c4a271422dbe34cf0e9543060aa
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a0ca6f7ff55b200a39489bd6b25018d7e829d522302a7b77cdb5bcf0f4efb06
+oid sha256:89c1690535c6b18e5b3898d361d6f2f441d25a2ee4be0ac103691e98b21d511a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7acf08b56200eef8ab5633a33fe1da705e0bdfcf63dd101391cff19aa6552ac
+oid sha256:fa33c046677b547ba5ce8cdbdcf6bc023f8cf01fbbbd5c720001f0e6ac3f4bb1
 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": 1.0387219190597534,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.21929824561403508,
+  "best_metric": 1.0097863674163818,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.43859649122807015,
   "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": 25.775,
       "eval_steps_per_second": 3.222,
       "step": 25
+    },
+    {
+      "epoch": 0.22807017543859648,
+      "grad_norm": 0.4981253743171692,
+      "learning_rate": 5e-05,
+      "loss": 0.8302,
+      "step": 26
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 0.39925092458724976,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9476,
+      "step": 27
+    },
+    {
+      "epoch": 0.24561403508771928,
+      "grad_norm": 0.41335299611091614,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.0122,
+      "step": 28
+    },
+    {
+      "epoch": 0.2543859649122807,
+      "grad_norm": 0.4298669397830963,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.0674,
+      "step": 29
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 0.38876697421073914,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.0279,
+      "step": 30
+    },
+    {
+      "epoch": 0.2719298245614035,
+      "grad_norm": 0.3731219172477722,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.0809,
+      "step": 31
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 0.39437374472618103,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.0325,
+      "step": 32
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 0.3963421583175659,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.0725,
+      "step": 33
+    },
+    {
+      "epoch": 0.2982456140350877,
+      "grad_norm": 0.4116675555706024,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.1263,
+      "step": 34
+    },
+    {
+      "epoch": 0.30701754385964913,
+      "grad_norm": 0.4274025857448578,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.1448,
+      "step": 35
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.4159688353538513,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.0796,
+      "step": 36
+    },
+    {
+      "epoch": 0.32456140350877194,
+      "grad_norm": 0.44033488631248474,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0841,
+      "step": 37
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.43039458990097046,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8525,
+      "step": 38
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 0.4210573136806488,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.9162,
+      "step": 39
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 0.37658628821372986,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.9426,
+      "step": 40
+    },
+    {
+      "epoch": 0.35964912280701755,
+      "grad_norm": 0.3321429193019867,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.9561,
+      "step": 41
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 0.38249334692955017,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9842,
+      "step": 42
+    },
+    {
+      "epoch": 0.37719298245614036,
+      "grad_norm": 0.3702194094657898,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.9499,
+      "step": 43
+    },
+    {
+      "epoch": 0.38596491228070173,
+      "grad_norm": 0.36360645294189453,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0246,
+      "step": 44
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 0.3688998222351074,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.0317,
+      "step": 45
+    },
+    {
+      "epoch": 0.40350877192982454,
+      "grad_norm": 0.3757031559944153,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.059,
+      "step": 46
+    },
+    {
+      "epoch": 0.41228070175438597,
+      "grad_norm": 0.3885948359966278,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.0664,
+      "step": 47
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.3880974054336548,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.0032,
+      "step": 48
+    },
+    {
+      "epoch": 0.4298245614035088,
+      "grad_norm": 0.4429730176925659,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.1307,
+      "step": 49
+    },
+    {
+      "epoch": 0.43859649122807015,
+      "grad_norm": 0.4293898940086365,
+      "learning_rate": 0.0,
+      "loss": 1.0734,
+      "step": 50
+    },
+    {
+      "epoch": 0.43859649122807015,
+      "eval_loss": 1.0097863674163818,
+      "eval_runtime": 29.7785,
+      "eval_samples_per_second": 25.79,
+      "eval_steps_per_second": 3.224,
+      "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": 1.114626154561536e+17,
+  "total_flos": 2.229252309123072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null