Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31a7d5fdd1388a98c30ce2b92bd7ce8c07eddd25429f3aaa19d1ad7a7ff0a1a7
+oid sha256:322446fceea7434a1d0aec1fbdae463800845e61b5fc496a6f29107ef923597a
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f146b42314babbf272c18a6a0a1e229d15716e312c551a8d093fd3ebbd7b1df9
+oid sha256:e32493c11e2ed8832ccff1b8e75e8b36cdf2187532b9e02992da034929d7d5c3
 size 1001863522

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bb9bd59dcd9b44e59614c1c8232046e7e9e1caebaf83fb1b0670f88f193cd6d
+oid sha256:3ac71e0a6d37590f86702f57756bcc6089ddb66aca98ada7648886b821e077ff
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8ceb091103656fa4a13353c7f9c5fa1c6f42ee087495b52b0ff54267fb28bc0
+oid sha256:3ba2cdbdb6293fb31f7f4fede33ca73dc38122266d3e85f522d32ad1578ae0aa
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4efdf6725885638b7d7ac22ea73d216339a42d524de3a299f6169334b40a2e4
+oid sha256:ce6bbcd5f162de43842a5fecd578d661c51f6c5b72989cb41d0b2a7dd294a417
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ad43da04f664a4b1afc5e2ec8bc883b432560b2810cd33fcf9c580425140814
+oid sha256:b3424bd02637399d5363b70d815fe76ef0dfba23947d849b6b1788f256f81466
 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": 0.4165385067462921,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.11074197120708748,
+  "best_metric": 0.3082202076911926,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.22148394241417496,
   "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": 11.952,
       "eval_steps_per_second": 1.501,
       "step": 25
+    },
+    {
+      "epoch": 0.11517165005537099,
+      "grad_norm": 75.84956359863281,
+      "learning_rate": 5e-05,
+      "loss": 8.2554,
+      "step": 26
+    },
+    {
+      "epoch": 0.11960132890365449,
+      "grad_norm": 28.34756851196289,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 6.9377,
+      "step": 27
+    },
+    {
+      "epoch": 0.12403100775193798,
+      "grad_norm": 58.43377685546875,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 7.3211,
+      "step": 28
+    },
+    {
+      "epoch": 0.12846068660022147,
+      "grad_norm": 70.48342895507812,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 8.1274,
+      "step": 29
+    },
+    {
+      "epoch": 0.132890365448505,
+      "grad_norm": 36.33397674560547,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 5.5569,
+      "step": 30
+    },
+    {
+      "epoch": 0.13732004429678848,
+      "grad_norm": 27.151063919067383,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 5.5113,
+      "step": 31
+    },
+    {
+      "epoch": 0.14174972314507198,
+      "grad_norm": 44.36494064331055,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 5.6198,
+      "step": 32
+    },
+    {
+      "epoch": 0.1461794019933555,
+      "grad_norm": 26.758596420288086,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 5.536,
+      "step": 33
+    },
+    {
+      "epoch": 0.150609080841639,
+      "grad_norm": 17.586759567260742,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 5.0683,
+      "step": 34
+    },
+    {
+      "epoch": 0.15503875968992248,
+      "grad_norm": 32.076446533203125,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 5.0719,
+      "step": 35
+    },
+    {
+      "epoch": 0.15946843853820597,
+      "grad_norm": 74.89476013183594,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 4.8337,
+      "step": 36
+    },
+    {
+      "epoch": 0.1638981173864895,
+      "grad_norm": 31.926136016845703,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.6355,
+      "step": 37
+    },
+    {
+      "epoch": 0.16832779623477298,
+      "grad_norm": 23.79403305053711,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.9566,
+      "step": 38
+    },
+    {
+      "epoch": 0.17275747508305647,
+      "grad_norm": 48.75263977050781,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 6.8026,
+      "step": 39
+    },
+    {
+      "epoch": 0.17718715393134,
+      "grad_norm": 47.51777648925781,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 7.0032,
+      "step": 40
+    },
+    {
+      "epoch": 0.18161683277962348,
+      "grad_norm": 38.380916595458984,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 6.4569,
+      "step": 41
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "grad_norm": 39.794124603271484,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 5.3289,
+      "step": 42
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 24.938093185424805,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 5.3438,
+      "step": 43
+    },
+    {
+      "epoch": 0.19490586932447398,
+      "grad_norm": 22.430749893188477,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 5.4512,
+      "step": 44
+    },
+    {
+      "epoch": 0.19933554817275748,
+      "grad_norm": 22.097654342651367,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 5.5461,
+      "step": 45
+    },
+    {
+      "epoch": 0.20376522702104097,
+      "grad_norm": 18.900991439819336,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 4.7573,
+      "step": 46
+    },
+    {
+      "epoch": 0.2081949058693245,
+      "grad_norm": 14.95788860321045,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 5.2978,
+      "step": 47
+    },
+    {
+      "epoch": 0.21262458471760798,
+      "grad_norm": 27.965768814086914,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 5.752,
+      "step": 48
+    },
+    {
+      "epoch": 0.21705426356589147,
+      "grad_norm": 39.07429504394531,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 4.222,
+      "step": 49
+    },
+    {
+      "epoch": 0.22148394241417496,
+      "grad_norm": 23.545461654663086,
+      "learning_rate": 0.0,
+      "loss": 3.5723,
+      "step": 50
+    },
+    {
+      "epoch": 0.22148394241417496,
+      "eval_loss": 0.3082202076911926,
+      "eval_runtime": 127.0071,
+      "eval_samples_per_second": 11.976,
+      "eval_steps_per_second": 1.504,
+      "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": 5.102842054443008e+17,
+  "total_flos": 1.0205684108886016e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null