Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d0423f52cfc74fda840f1776401f7f2ea4f8d7370bc595c1e98c7fb160f56f7
+oid sha256:9508d091197193e5710fcf027890d8ca8b0f489a0c4d8e369e7c61dbe7b831f6
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:920a1ee3003ffc30690c623daa11b4cda5094fb3cb9a518c3ea8243684717799
+oid sha256:b55f91f95005237d9d005b436232efea4ae30b74ed29afa4bf4f33f58f942a42
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e812507e644ec93e4c7b7cffbb43658e5139436a135cbe47df93ef31233b48ea
+oid sha256:ef584324ad59dc19162413d7d9491a16d6eca245bf0608a49b5fac00b71a4912
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f852c26d504cc16890b686857089657127b61751b415e35156453ae758ad8598
+oid sha256:99b1d8f61d439c0c7019e9040d9bbfbabe5b790cc64b983b34941c486a06ab79
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c053e3abfc2b77bb41080d0d09efb1800265511ebb7d73a332783883ac8a5ca
+oid sha256:cc79a73dc78240ba98b9864474e881d207eddb1092c4958a170bfa9cf26ee873
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cf63a83cf8b4904451f60379a7607e539dba5e8d2a42256d7dcbbace25140e9
+oid sha256:255e6e1a7339911de9d19cc9ae45ff459db2522562961653fdca3f18bb913101
 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": 11.924177169799805,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7722007722007722,
+  "best_metric": 11.9196138381958,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.5444015444015444,
   "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": 280.597,
       "eval_steps_per_second": 35.875,
       "step": 25
+    },
+    {
+      "epoch": 0.803088803088803,
+      "grad_norm": 0.07824923098087311,
+      "learning_rate": 5e-05,
+      "loss": 11.9248,
+      "step": 26
+    },
+    {
+      "epoch": 0.833976833976834,
+      "grad_norm": 0.1009729653596878,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.9261,
+      "step": 27
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 0.12158763408660889,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.9224,
+      "step": 28
+    },
+    {
+      "epoch": 0.8957528957528957,
+      "grad_norm": 0.14848434925079346,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.9251,
+      "step": 29
+    },
+    {
+      "epoch": 0.9266409266409267,
+      "grad_norm": 0.15349432826042175,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.9235,
+      "step": 30
+    },
+    {
+      "epoch": 0.9575289575289575,
+      "grad_norm": 0.1826583743095398,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.9222,
+      "step": 31
+    },
+    {
+      "epoch": 0.9884169884169884,
+      "grad_norm": 0.16778188943862915,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9317,
+      "step": 32
+    },
+    {
+      "epoch": 1.0193050193050193,
+      "grad_norm": 0.1833105981349945,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 19.424,
+      "step": 33
+    },
+    {
+      "epoch": 1.05019305019305,
+      "grad_norm": 0.0869530737400055,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 12.095,
+      "step": 34
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 0.11778981238603592,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.902,
+      "step": 35
+    },
+    {
+      "epoch": 1.111969111969112,
+      "grad_norm": 0.1222325935959816,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 12.3136,
+      "step": 36
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.14096081256866455,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.603,
+      "step": 37
+    },
+    {
+      "epoch": 1.1737451737451738,
+      "grad_norm": 0.15266837179660797,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.896,
+      "step": 38
+    },
+    {
+      "epoch": 1.2046332046332047,
+      "grad_norm": 0.15551863610744476,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.6295,
+      "step": 39
+    },
+    {
+      "epoch": 1.2355212355212355,
+      "grad_norm": 0.19857841730117798,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 12.065,
+      "step": 40
+    },
+    {
+      "epoch": 1.2664092664092665,
+      "grad_norm": 0.13945285975933075,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.2033,
+      "step": 41
+    },
+    {
+      "epoch": 1.2972972972972974,
+      "grad_norm": 0.09375537186861038,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 12.0239,
+      "step": 42
+    },
+    {
+      "epoch": 1.3281853281853282,
+      "grad_norm": 0.11622730642557144,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 13.0858,
+      "step": 43
+    },
+    {
+      "epoch": 1.359073359073359,
+      "grad_norm": 0.13087835907936096,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.6548,
+      "step": 44
+    },
+    {
+      "epoch": 1.3899613899613898,
+      "grad_norm": 0.17029710114002228,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.7197,
+      "step": 45
+    },
+    {
+      "epoch": 1.420849420849421,
+      "grad_norm": 0.14172868430614471,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.5624,
+      "step": 46
+    },
+    {
+      "epoch": 1.4517374517374517,
+      "grad_norm": 0.16212929785251617,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.9965,
+      "step": 47
+    },
+    {
+      "epoch": 1.4826254826254825,
+      "grad_norm": 0.19312851130962372,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 12.248,
+      "step": 48
+    },
+    {
+      "epoch": 1.5135135135135136,
+      "grad_norm": 0.13117873668670654,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.6341,
+      "step": 49
+    },
+    {
+      "epoch": 1.5444015444015444,
+      "grad_norm": 0.09648028761148453,
+      "learning_rate": 0.0,
+      "loss": 13.4304,
+      "step": 50
+    },
+    {
+      "epoch": 1.5444015444015444,
+      "eval_loss": 11.9196138381958,
+      "eval_runtime": 0.7842,
+      "eval_samples_per_second": 279.277,
+      "eval_steps_per_second": 35.707,
+      "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": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null