Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ef144a5772fd420fec3b699f929f6fd0df5f3b8916c557449bed8dd3b24f082
+oid sha256:e1303ecd553b55be3acd6bf141a3c6288220489e45f3652fddba7a253dffdb60
 size 1204200

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34a7538dd9cd3105ef5b0352a8bb2b04e835186d688012b78e416589354bdacd
+oid sha256:6f0ed3d3eac3918eb30074f5f0102a5d1f03c6b5694fbcad7dcf3d2fd4e1e9b5
 size 2558458

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f0335b1c222bfd1b57cc290d07c52fd598e48d80ea2c40960859220dad66b03
+oid sha256:1978fea88b8a880f104b72fd0829be61eb101af8c50325655e0d855cb4451775
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b0fdacedfb245722e833c9574873019cadf524e122849884c005336604518c0
+oid sha256:1d50b8c296cebd239c66d96d9440fa1536e9e283b9a184391c2478c02d95278f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:005144ca2d0b226ebf9ea934937f68e66e5c48080758af300c71de94e0a75832
+oid sha256:4a1d8f461d473a4a62ad763e88601cfc015a3c3bf0959993bea7d286cf24079c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f87c00708a68a175d4a30086e4a7ebd637889360caeacc6472e8024f2e80dd7
+oid sha256:cdde3682c4a825583519b9a32f50694016967abacd3f5339c832e9f20322e99e
 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": 11.755112648010254,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.014036072706856622,
+  "best_metric": 11.720179557800293,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.028072145413713244,
   "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": 170.01,
       "eval_steps_per_second": 21.253,
       "step": 25
+    },
+    {
+      "epoch": 0.014597515615130886,
+      "grad_norm": 1.398974061012268,
+      "learning_rate": 5e-05,
+      "loss": 11.8343,
+      "step": 26
+    },
+    {
+      "epoch": 0.015158958523405151,
+      "grad_norm": 1.5043359994888306,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.7449,
+      "step": 27
+    },
+    {
+      "epoch": 0.015720401431679416,
+      "grad_norm": 1.8410756587982178,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.7265,
+      "step": 28
+    },
+    {
+      "epoch": 0.01628184433995368,
+      "grad_norm": 1.659067153930664,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.7217,
+      "step": 29
+    },
+    {
+      "epoch": 0.016843287248227947,
+      "grad_norm": 1.1002304553985596,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.7432,
+      "step": 30
+    },
+    {
+      "epoch": 0.01740473015650221,
+      "grad_norm": 1.1968733072280884,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.7378,
+      "step": 31
+    },
+    {
+      "epoch": 0.017966173064776474,
+      "grad_norm": 1.057620644569397,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.742,
+      "step": 32
+    },
+    {
+      "epoch": 0.01852761597305074,
+      "grad_norm": 1.080743670463562,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.7437,
+      "step": 33
+    },
+    {
+      "epoch": 0.019089058881325005,
+      "grad_norm": 1.1043583154678345,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.7329,
+      "step": 34
+    },
+    {
+      "epoch": 0.01965050178959927,
+      "grad_norm": 1.0628371238708496,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.7246,
+      "step": 35
+    },
+    {
+      "epoch": 0.020211944697873536,
+      "grad_norm": 1.0919686555862427,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.7271,
+      "step": 36
+    },
+    {
+      "epoch": 0.0207733876061478,
+      "grad_norm": 1.1903443336486816,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.7213,
+      "step": 37
+    },
+    {
+      "epoch": 0.021334830514422063,
+      "grad_norm": 0.9018011689186096,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.7787,
+      "step": 38
+    },
+    {
+      "epoch": 0.02189627342269633,
+      "grad_norm": 1.1237108707427979,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.7984,
+      "step": 39
+    },
+    {
+      "epoch": 0.022457716330970594,
+      "grad_norm": 1.689167857170105,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.695,
+      "step": 40
+    },
+    {
+      "epoch": 0.02301915923924486,
+      "grad_norm": 1.6919984817504883,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.6956,
+      "step": 41
+    },
+    {
+      "epoch": 0.023580602147519125,
+      "grad_norm": 1.2629735469818115,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.7071,
+      "step": 42
+    },
+    {
+      "epoch": 0.024142045055793388,
+      "grad_norm": 0.9501758813858032,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.7307,
+      "step": 43
+    },
+    {
+      "epoch": 0.024703487964067655,
+      "grad_norm": 0.9177296161651611,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.7405,
+      "step": 44
+    },
+    {
+      "epoch": 0.02526493087234192,
+      "grad_norm": 1.065750241279602,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.7187,
+      "step": 45
+    },
+    {
+      "epoch": 0.025826373780616182,
+      "grad_norm": 1.078781247138977,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.7146,
+      "step": 46
+    },
+    {
+      "epoch": 0.02638781668889045,
+      "grad_norm": 1.0444191694259644,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.7233,
+      "step": 47
+    },
+    {
+      "epoch": 0.026949259597164713,
+      "grad_norm": 0.9315354824066162,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.7313,
+      "step": 48
+    },
+    {
+      "epoch": 0.027510702505438977,
+      "grad_norm": 0.9638807773590088,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.7381,
+      "step": 49
+    },
+    {
+      "epoch": 0.028072145413713244,
+      "grad_norm": 1.1096824407577515,
+      "learning_rate": 0.0,
+      "loss": 11.7157,
+      "step": 50
+    },
+    {
+      "epoch": 0.028072145413713244,
+      "eval_loss": 11.720179557800293,
+      "eval_runtime": 71.1233,
+      "eval_samples_per_second": 168.707,
+      "eval_steps_per_second": 21.09,
+      "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": 275966226071552.0,
+  "total_flos": 550104860721152.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null