Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:519e5ec0f866a4ea9b6dfe3159b2a4f03eddb69966ba6bfd3d04c614fdaf6dcf
+oid sha256:24e9def3a1a38d19732ca5cf7f4c1f9bc181a03950aa784fe590a992d3fb2106
 size 435773944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f5a5630a32c9ce367cb6cadd3d1a9eecde2923030374bd606ce0ca5aa6f5473
+oid sha256:d253eca88e1900fa83801a8a939ecb79f2bb5f56d37f3c5e019573237d3f2a7a
 size 871934770

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fed30314f4327bf5df4f25c19da8f7788abde721f346645a5408bfd123f76c4
+oid sha256:acd3ec6ad374d744705ba3a421491671112136381ec3374e313b852c6bb03be0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3eca944e208fc5023e2bfc70a4cba42ed6f84f201cbafb88f58fa3605d12cbf
+oid sha256:16e31db72dfeff870effc29a6cdaadeb128dbd41d7841cc03a749d6c0bb8e6b6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74af8df348e55a395cd8296a6bc31024cc128a231ed4313d52c16461a9f321c0
+oid sha256:7e5aa5bed334525f1f153aca2f5689ff62bf37f01e4afa4b1d15ce4c5c3ed9b1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec8cedf0b1234f2be557b0344fe2f6557984df4f7ffd622871fd03140e065cb
+oid sha256:f05708b92aa75234beb37bf4168034ecb902ec548586d26d65d9fa120a06741f
 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": 0.025279613211750984,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03390692548953124,
+  "best_metric": 0.020438848063349724,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06781385097906248,
   "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": 27.766,
       "eval_steps_per_second": 3.471,
       "step": 25
+    },
+    {
+      "epoch": 0.03526320250911249,
+      "grad_norm": 0.3740287125110626,
+      "learning_rate": 5e-05,
+      "loss": 0.0167,
+      "step": 26
+    },
+    {
+      "epoch": 0.03661947952869374,
+      "grad_norm": 0.30993032455444336,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0169,
+      "step": 27
+    },
+    {
+      "epoch": 0.03797575654827499,
+      "grad_norm": 0.3844718337059021,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0158,
+      "step": 28
+    },
+    {
+      "epoch": 0.03933203356785624,
+      "grad_norm": 0.3056732416152954,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0124,
+      "step": 29
+    },
+    {
+      "epoch": 0.040688310587437486,
+      "grad_norm": 0.46882057189941406,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0295,
+      "step": 30
+    },
+    {
+      "epoch": 0.042044587607018735,
+      "grad_norm": 0.47933128476142883,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0223,
+      "step": 31
+    },
+    {
+      "epoch": 0.043400864626599985,
+      "grad_norm": 0.3894636631011963,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0163,
+      "step": 32
+    },
+    {
+      "epoch": 0.044757141646181234,
+      "grad_norm": 0.48748522996902466,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.03,
+      "step": 33
+    },
+    {
+      "epoch": 0.04611341866576248,
+      "grad_norm": 0.5438624620437622,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0283,
+      "step": 34
+    },
+    {
+      "epoch": 0.04746969568534373,
+      "grad_norm": 0.44844117760658264,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0278,
+      "step": 35
+    },
+    {
+      "epoch": 0.04882597270492498,
+      "grad_norm": 0.41513577103614807,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0196,
+      "step": 36
+    },
+    {
+      "epoch": 0.05018224972450623,
+      "grad_norm": 0.3627379834651947,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0118,
+      "step": 37
+    },
+    {
+      "epoch": 0.05153852674408748,
+      "grad_norm": 0.43544554710388184,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0275,
+      "step": 38
+    },
+    {
+      "epoch": 0.05289480376366873,
+      "grad_norm": 0.37630170583724976,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0214,
+      "step": 39
+    },
+    {
+      "epoch": 0.05425108078324998,
+      "grad_norm": 0.3092811405658722,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0107,
+      "step": 40
+    },
+    {
+      "epoch": 0.05560735780283123,
+      "grad_norm": 0.4349355697631836,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0108,
+      "step": 41
+    },
+    {
+      "epoch": 0.05696363482241248,
+      "grad_norm": 0.15674984455108643,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0062,
+      "step": 42
+    },
+    {
+      "epoch": 0.05831991184199373,
+      "grad_norm": 0.3282619118690491,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0108,
+      "step": 43
+    },
+    {
+      "epoch": 0.059676188861574976,
+      "grad_norm": 0.4003311097621918,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0231,
+      "step": 44
+    },
+    {
+      "epoch": 0.061032465881156225,
+      "grad_norm": 0.36832916736602783,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0218,
+      "step": 45
+    },
+    {
+      "epoch": 0.062388742900737475,
+      "grad_norm": 0.4607793390750885,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0355,
+      "step": 46
+    },
+    {
+      "epoch": 0.06374501992031872,
+      "grad_norm": 0.25370919704437256,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0056,
+      "step": 47
+    },
+    {
+      "epoch": 0.06510129693989998,
+      "grad_norm": 0.3585875928401947,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.019,
+      "step": 48
+    },
+    {
+      "epoch": 0.06645757395948122,
+      "grad_norm": 0.38194748759269714,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0152,
+      "step": 49
+    },
+    {
+      "epoch": 0.06781385097906248,
+      "grad_norm": 0.5131410956382751,
+      "learning_rate": 0.0,
+      "loss": 0.0307,
+      "step": 50
+    },
+    {
+      "epoch": 0.06781385097906248,
+      "eval_loss": 0.020438848063349724,
+      "eval_runtime": 179.7145,
+      "eval_samples_per_second": 27.638,
+      "eval_steps_per_second": 3.455,
+      "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": 3.411614392909824e+17,
+  "total_flos": 6.823228785819648e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null