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:d6afd68e536f41181424f8b072d48900297e38026ffb4b40ec39643adc03bb4c
+oid sha256:3ce0ed48073016d83519b1d7b089cc9c0a8154ecc9023e46213154e07ecb6463
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f35ff030e9691642fb430307ee8e6a1363a1569acb1bb7af14c9f4ee115893ec
+oid sha256:181eac9d3b707fe26ff441f8f913b07afe8881fd2e4cc9a1e12c98a2a3e69642
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e34531289256ac1921c95825c17a4ac3eefd4be8823ce2dd0b7155a1ddb5eb7
+oid sha256:af905e0c4084b3e679503ea0f174795dfe781381c6bd211ef3b079cfe3990465
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e3edaf4972f1a1a4e43a6c4d114bf1604d7c2fe401276dd8d5dd50100a3fc5d
+oid sha256:9ae711fd14526246396c12f5c04b04231eee3258a04e850fd443293c43d3bef9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b44b2466268671db87f866d49713532cafedf8b9814423ec9913c6bef7d0c72
+oid sha256:7c22dd5dbf90b1e59af30d495f842504963e0e6c57c0f46f6f8bffd0c1cbb090
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed4a8257beb81ba1e47515024b2bc4b403def30ec1d9b29afb18656c8d816688
+oid sha256:434f4fd1d69bfa012480e7e71d691d24eed81234ecdaabb5949b8bcebbb8f3af
 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": 0.4159088730812073,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02373887240356083,
+  "best_metric": 0.392264187335968,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04747774480712166,
   "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": 77.449,
       "eval_steps_per_second": 9.682,
       "step": 25
+    },
+    {
+      "epoch": 0.024688427299703265,
+      "grad_norm": 1.7106653451919556,
+      "learning_rate": 5e-05,
+      "loss": 0.4651,
+      "step": 26
+    },
+    {
+      "epoch": 0.025637982195845697,
+      "grad_norm": 1.322445273399353,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4095,
+      "step": 27
+    },
+    {
+      "epoch": 0.02658753709198813,
+      "grad_norm": 1.363024115562439,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4447,
+      "step": 28
+    },
+    {
+      "epoch": 0.027537091988130563,
+      "grad_norm": 1.0911495685577393,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4959,
+      "step": 29
+    },
+    {
+      "epoch": 0.028486646884272996,
+      "grad_norm": 1.0770279169082642,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4371,
+      "step": 30
+    },
+    {
+      "epoch": 0.02943620178041543,
+      "grad_norm": 1.1779959201812744,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4116,
+      "step": 31
+    },
+    {
+      "epoch": 0.030385756676557865,
+      "grad_norm": 1.0283995866775513,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3238,
+      "step": 32
+    },
+    {
+      "epoch": 0.031335311572700295,
+      "grad_norm": 1.1943073272705078,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4475,
+      "step": 33
+    },
+    {
+      "epoch": 0.03228486646884273,
+      "grad_norm": 1.43560791015625,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.4978,
+      "step": 34
+    },
+    {
+      "epoch": 0.03323442136498516,
+      "grad_norm": 1.288859486579895,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3934,
+      "step": 35
+    },
+    {
+      "epoch": 0.0341839762611276,
+      "grad_norm": 1.3092143535614014,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4076,
+      "step": 36
+    },
+    {
+      "epoch": 0.03513353115727003,
+      "grad_norm": 1.3240766525268555,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4086,
+      "step": 37
+    },
+    {
+      "epoch": 0.03608308605341246,
+      "grad_norm": 0.9453262686729431,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4139,
+      "step": 38
+    },
+    {
+      "epoch": 0.0370326409495549,
+      "grad_norm": 1.0400198698043823,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4421,
+      "step": 39
+    },
+    {
+      "epoch": 0.03798219584569733,
+      "grad_norm": 1.1390429735183716,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.3825,
+      "step": 40
+    },
+    {
+      "epoch": 0.038931750741839764,
+      "grad_norm": 1.109674334526062,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.418,
+      "step": 41
+    },
+    {
+      "epoch": 0.039881305637982194,
+      "grad_norm": 1.0239107608795166,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4396,
+      "step": 42
+    },
+    {
+      "epoch": 0.04083086053412463,
+      "grad_norm": 0.9508967399597168,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4177,
+      "step": 43
+    },
+    {
+      "epoch": 0.04178041543026706,
+      "grad_norm": 0.9765400290489197,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4324,
+      "step": 44
+    },
+    {
+      "epoch": 0.042729970326409496,
+      "grad_norm": 1.0129822492599487,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.3481,
+      "step": 45
+    },
+    {
+      "epoch": 0.04367952522255193,
+      "grad_norm": 1.1066875457763672,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4676,
+      "step": 46
+    },
+    {
+      "epoch": 0.04462908011869436,
+      "grad_norm": 0.9519398808479309,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4375,
+      "step": 47
+    },
+    {
+      "epoch": 0.0455786350148368,
+      "grad_norm": 1.2050330638885498,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3596,
+      "step": 48
+    },
+    {
+      "epoch": 0.04652818991097923,
+      "grad_norm": 1.1099382638931274,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4083,
+      "step": 49
+    },
+    {
+      "epoch": 0.04747774480712166,
+      "grad_norm": 1.1943883895874023,
+      "learning_rate": 0.0,
+      "loss": 0.4605,
+      "step": 50
+    },
+    {
+      "epoch": 0.04747774480712166,
+      "eval_loss": 0.392264187335968,
+      "eval_runtime": 91.633,
+      "eval_samples_per_second": 77.428,
+      "eval_steps_per_second": 9.68,
+      "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": 7.94731890081792e+16,
+  "total_flos": 1.589463780163584e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null