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:cc08387ec37e3e553c3bad87bf3484f66dcd953b175a76e28ebfd0399cbd95c5
+oid sha256:327b0b894d02efa593ae55b77355e02b7dcb9c0f15437a404599c614373e7643
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e297d02b83f6d2ec1eab7596e6c7c28416ad1825a17e3b007cabc0c40ef7ab5d
+oid sha256:aeef93860aba55ac3a89720bea8da8e5fb801f5b29c00d98e0d3122614883ab0
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4650b6365d36ea5a97da9076755816a8743dea9b1df42a060a5480c630cf2b33
+oid sha256:156823cadeaf8eb14a3a1c0327004f533d4bcb7ac30bced256b8b982731d071f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72beccfb45d90088ad39485e7d9f5be911a1fd01feb48cd75f999cb36579cf2a
+oid sha256:109dd10dcd4d5c2b5cdc2df0ecffdd8f89f7335a7a34e41955890d9c65d15df5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f96ff6e4ca48fbb69be89f015f4e9d59ac757173ed8978c5f9f7d3c401ce85b9
+oid sha256:5c614d9809d3ded2af01be5bb4abc214078a873c03ae7d4d5e71226672bda71c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfe44df4ed466cc6e0814b3db985d41fa4fba6fc602dd678ae4cc3f36c4d2a5a
+oid sha256:ad8d9a0390aa7292ea05617ef25cfcc91767fa9e5a6e478b2552900f1cae9ae4
 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": 2.1359996795654297,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.25316455696202533,
+  "best_metric": 2.106477975845337,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5063291139240507,
   "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": 39.087,
       "eval_steps_per_second": 4.937,
       "step": 25
+    },
+    {
+      "epoch": 0.26329113924050634,
+      "grad_norm": 0.19945096969604492,
+      "learning_rate": 5e-05,
+      "loss": 2.0451,
+      "step": 26
+    },
+    {
+      "epoch": 0.27341772151898736,
+      "grad_norm": 0.2540655732154846,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.9992,
+      "step": 27
+    },
+    {
+      "epoch": 0.28354430379746837,
+      "grad_norm": 0.2860367000102997,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.0668,
+      "step": 28
+    },
+    {
+      "epoch": 0.2936708860759494,
+      "grad_norm": 0.3126712739467621,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.0629,
+      "step": 29
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 0.32378825545310974,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.052,
+      "step": 30
+    },
+    {
+      "epoch": 0.3139240506329114,
+      "grad_norm": 0.3288367688655853,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.0242,
+      "step": 31
+    },
+    {
+      "epoch": 0.3240506329113924,
+      "grad_norm": 0.32187196612358093,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.0959,
+      "step": 32
+    },
+    {
+      "epoch": 0.3341772151898734,
+      "grad_norm": 0.35805830359458923,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.0974,
+      "step": 33
+    },
+    {
+      "epoch": 0.34430379746835443,
+      "grad_norm": 0.3363867402076721,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.1789,
+      "step": 34
+    },
+    {
+      "epoch": 0.35443037974683544,
+      "grad_norm": 0.395484983921051,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.1939,
+      "step": 35
+    },
+    {
+      "epoch": 0.36455696202531646,
+      "grad_norm": 0.42597419023513794,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.2411,
+      "step": 36
+    },
+    {
+      "epoch": 0.37468354430379747,
+      "grad_norm": 0.5309949517250061,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.3354,
+      "step": 37
+    },
+    {
+      "epoch": 0.3848101265822785,
+      "grad_norm": 0.22626985609531403,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.082,
+      "step": 38
+    },
+    {
+      "epoch": 0.3949367088607595,
+      "grad_norm": 0.250396728515625,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.977,
+      "step": 39
+    },
+    {
+      "epoch": 0.4050632911392405,
+      "grad_norm": 0.25913822650909424,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.9699,
+      "step": 40
+    },
+    {
+      "epoch": 0.4151898734177215,
+      "grad_norm": 0.2661059498786926,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.9801,
+      "step": 41
+    },
+    {
+      "epoch": 0.4253164556962025,
+      "grad_norm": 0.2748521566390991,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.0372,
+      "step": 42
+    },
+    {
+      "epoch": 0.43544303797468353,
+      "grad_norm": 0.2798287868499756,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.0676,
+      "step": 43
+    },
+    {
+      "epoch": 0.44556962025316454,
+      "grad_norm": 0.2933082580566406,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.0416,
+      "step": 44
+    },
+    {
+      "epoch": 0.45569620253164556,
+      "grad_norm": 0.3150334656238556,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.0815,
+      "step": 45
+    },
+    {
+      "epoch": 0.46582278481012657,
+      "grad_norm": 0.3428869843482971,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.1586,
+      "step": 46
+    },
+    {
+      "epoch": 0.4759493670886076,
+      "grad_norm": 0.3866429030895233,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.2278,
+      "step": 47
+    },
+    {
+      "epoch": 0.4860759493670886,
+      "grad_norm": 0.43105289340019226,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.2092,
+      "step": 48
+    },
+    {
+      "epoch": 0.4962025316455696,
+      "grad_norm": 0.5243375301361084,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.3611,
+      "step": 49
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "grad_norm": 0.6422505378723145,
+      "learning_rate": 0.0,
+      "loss": 2.3794,
+      "step": 50
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "eval_loss": 2.106477975845337,
+      "eval_runtime": 17.0015,
+      "eval_samples_per_second": 39.114,
+      "eval_steps_per_second": 4.941,
+      "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": 2.8137864274169037e+17,
+  "total_flos": 5.625815332741448e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null