Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f3f2cf3c31cadf85597fca70a05acd3d16e8b12436a4e29c1e3526c2b74a510
+oid sha256:dc541a5e2f6ab287dd5d927da237acf49a2f6908fcdea5a3b379204e1ed0bee1
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f4ae0bcffe0e5e3abfb00eff5efdaa8a4def12905ce06b546f7e18e85d97aea
+oid sha256:629035f3e0bd246235b65cad3b10985653da1336b672feeca886ffc9bccf8f6a
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc1e0c46f7cc398eb709b5b42be327e0069c02655e1ea9d3c16c76a27082e171
+oid sha256:866f0ca7c21ec1de02e8b9c8d45c57949cc748e928a153ca00a8a16c3b0eb509
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bdd78fe906447f17032bd815de3c140be039e53d6258105cedb8a6a1dbe0cac
+oid sha256:d7230e2597a940419eeb593cb0c975c1a05245336ce6acea1d6e29a5e65c28c4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22f8c8915d06da34ce0300622dd39175278a247ce95817cbfdff05d31f30ca11
+oid sha256:003aaeef11ba104326e83e6951d5b601dfe0655126637fa3cb97117eb5090a38
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a72192f3113935c1c4aae52c380552e8a6e783c0333940e3151e98e0f0b2b88b
+oid sha256:fdaf19a804ba736ce26a5ae9784dbc359de22139dfe22b10ecf9c53c6e4ffa90
 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": 1.246433138847351,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5012531328320802,
+  "best_metric": 1.202621579170227,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.0025062656641603,
   "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": 33.904,
       "eval_steps_per_second": 4.326,
       "step": 25
+    },
+    {
+      "epoch": 0.5213032581453634,
+      "grad_norm": 22.65152931213379,
+      "learning_rate": 5e-05,
+      "loss": 20.6473,
+      "step": 26
+    },
+    {
+      "epoch": 0.5413533834586466,
+      "grad_norm": 15.269755363464355,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 20.1124,
+      "step": 27
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 11.2027006149292,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 19.4812,
+      "step": 28
+    },
+    {
+      "epoch": 0.581453634085213,
+      "grad_norm": 10.389817237854004,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 19.5182,
+      "step": 29
+    },
+    {
+      "epoch": 0.6015037593984962,
+      "grad_norm": 11.606437683105469,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 19.2824,
+      "step": 30
+    },
+    {
+      "epoch": 0.6215538847117794,
+      "grad_norm": 10.24315357208252,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 18.6898,
+      "step": 31
+    },
+    {
+      "epoch": 0.6416040100250626,
+      "grad_norm": 11.810291290283203,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 19.2295,
+      "step": 32
+    },
+    {
+      "epoch": 0.6616541353383458,
+      "grad_norm": 12.391736030578613,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 18.7425,
+      "step": 33
+    },
+    {
+      "epoch": 0.681704260651629,
+      "grad_norm": 11.576544761657715,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 18.2593,
+      "step": 34
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 10.067651748657227,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 18.5798,
+      "step": 35
+    },
+    {
+      "epoch": 0.7218045112781954,
+      "grad_norm": 10.310379981994629,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 18.5488,
+      "step": 36
+    },
+    {
+      "epoch": 0.7418546365914787,
+      "grad_norm": 11.977128982543945,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 19.958,
+      "step": 37
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 11.227585792541504,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 20.1358,
+      "step": 38
+    },
+    {
+      "epoch": 0.7819548872180451,
+      "grad_norm": 12.250752449035645,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 19.6867,
+      "step": 39
+    },
+    {
+      "epoch": 0.8020050125313283,
+      "grad_norm": 10.369344711303711,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 19.6549,
+      "step": 40
+    },
+    {
+      "epoch": 0.8220551378446115,
+      "grad_norm": 10.211109161376953,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 19.1544,
+      "step": 41
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 10.223684310913086,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 19.547,
+      "step": 42
+    },
+    {
+      "epoch": 0.8621553884711779,
+      "grad_norm": 9.276268005371094,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 18.4639,
+      "step": 43
+    },
+    {
+      "epoch": 0.8822055137844611,
+      "grad_norm": 9.275793075561523,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 18.9127,
+      "step": 44
+    },
+    {
+      "epoch": 0.9022556390977443,
+      "grad_norm": 8.820109367370605,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 18.035,
+      "step": 45
+    },
+    {
+      "epoch": 0.9223057644110275,
+      "grad_norm": 9.497257232666016,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 18.3713,
+      "step": 46
+    },
+    {
+      "epoch": 0.9423558897243107,
+      "grad_norm": 9.700572967529297,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 19.0926,
+      "step": 47
+    },
+    {
+      "epoch": 0.9624060150375939,
+      "grad_norm": 10.158452987670898,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 18.515,
+      "step": 48
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "grad_norm": 14.737983703613281,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 18.3978,
+      "step": 49
+    },
+    {
+      "epoch": 1.0025062656641603,
+      "grad_norm": 9.30565071105957,
+      "learning_rate": 0.0,
+      "loss": 19.3901,
+      "step": 50
+    },
+    {
+      "epoch": 1.0025062656641603,
+      "eval_loss": 1.202621579170227,
+      "eval_runtime": 9.9541,
+      "eval_samples_per_second": 33.855,
+      "eval_steps_per_second": 4.32,
+      "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": 2.829013890367488e+17,
+  "total_flos": 5.658027780734976e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null