Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11808e938e721c8782d94348f7b578dad660ba642b2301e9f9fdc57e712ec86b
+oid sha256:53e6a32d8ce118c218a16b4309f0e17485b0ef5ddcbd6354ea452c7e9b4a5aed
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1f8ac84db5b7e73a6d9d7d84a9b7a9e7f2e471925fea5b9f5d8b9b79ca6a8bb
+oid sha256:81e6a2f0317fbe3c4515b59be3348a438d81697983b0a806e4d0ec3f9c52500a
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f3654ad1193fe115c9eaa0dfc64bbb0031fb8aa5e1958c9ae8a82595c77f67a
+oid sha256:170b884d8d6679e53808db9e6be138c5bdbf5789f68030b2524387949bce61d6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:788dcac7896f1c54f26255ec9ac730b0ad66b624f43cc775d20ddf1f28eeede5
+oid sha256:d366c58a8406546f4edee634b18c799f24f7ec08f1a82455148049ba4ec6312c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52fec3d4105ff15bcbe8238b8c4850bd8b1bc69c79223d33bc75dfd51008a916
+oid sha256:9916f4bf49365bbb4c9be273a7b291e44a1c3c9edbd46a02b9041091dad02736
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2191655c8ef3abbf49f4dc330b49dba92e36052c2b309f2b512e1afb749194f
+oid sha256:1b455fb509dadc37b8231fe0a72ab981f6b411d360bc2deb3da9a797368fd748
 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": 0.4360552430152893,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.4210526315789473,
+  "best_metric": 0.41843298077583313,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.8421052631578947,
   "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": 34.586,
       "eval_steps_per_second": 4.323,
       "step": 25
+    },
+    {
+      "epoch": 1.4771929824561403,
+      "grad_norm": 46.89820098876953,
+      "learning_rate": 5e-05,
+      "loss": 0.3863,
+      "step": 26
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 46.987098693847656,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3617,
+      "step": 27
+    },
+    {
+      "epoch": 1.5894736842105264,
+      "grad_norm": 36.37738037109375,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.361,
+      "step": 28
+    },
+    {
+      "epoch": 1.6456140350877193,
+      "grad_norm": 70.0005111694336,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.424,
+      "step": 29
+    },
+    {
+      "epoch": 1.7017543859649122,
+      "grad_norm": 54.46710205078125,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4385,
+      "step": 30
+    },
+    {
+      "epoch": 1.7578947368421054,
+      "grad_norm": 60.80137252807617,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4423,
+      "step": 31
+    },
+    {
+      "epoch": 1.8140350877192981,
+      "grad_norm": 63.3051872253418,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.4325,
+      "step": 32
+    },
+    {
+      "epoch": 1.8701754385964913,
+      "grad_norm": 49.14182662963867,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5068,
+      "step": 33
+    },
+    {
+      "epoch": 1.9263157894736842,
+      "grad_norm": 48.0538444519043,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.4234,
+      "step": 34
+    },
+    {
+      "epoch": 1.9824561403508771,
+      "grad_norm": 37.64308166503906,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.4885,
+      "step": 35
+    },
+    {
+      "epoch": 2.056140350877193,
+      "grad_norm": 28.763765335083008,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4181,
+      "step": 36
+    },
+    {
+      "epoch": 2.112280701754386,
+      "grad_norm": 28.13519287109375,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4015,
+      "step": 37
+    },
+    {
+      "epoch": 2.168421052631579,
+      "grad_norm": 28.94443130493164,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4183,
+      "step": 38
+    },
+    {
+      "epoch": 2.2245614035087717,
+      "grad_norm": 28.30132484436035,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3597,
+      "step": 39
+    },
+    {
+      "epoch": 2.280701754385965,
+      "grad_norm": 22.59032440185547,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.279,
+      "step": 40
+    },
+    {
+      "epoch": 2.336842105263158,
+      "grad_norm": 26.12000274658203,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.3607,
+      "step": 41
+    },
+    {
+      "epoch": 2.3929824561403508,
+      "grad_norm": 29.88742446899414,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4606,
+      "step": 42
+    },
+    {
+      "epoch": 2.449122807017544,
+      "grad_norm": 30.775476455688477,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.3881,
+      "step": 43
+    },
+    {
+      "epoch": 2.5052631578947366,
+      "grad_norm": 28.79802131652832,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3378,
+      "step": 44
+    },
+    {
+      "epoch": 2.56140350877193,
+      "grad_norm": 37.421512603759766,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4234,
+      "step": 45
+    },
+    {
+      "epoch": 2.617543859649123,
+      "grad_norm": 29.71128273010254,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4379,
+      "step": 46
+    },
+    {
+      "epoch": 2.6736842105263157,
+      "grad_norm": 41.081417083740234,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3715,
+      "step": 47
+    },
+    {
+      "epoch": 2.729824561403509,
+      "grad_norm": 36.28976821899414,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3086,
+      "step": 48
+    },
+    {
+      "epoch": 2.7859649122807015,
+      "grad_norm": 20.267520904541016,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2753,
+      "step": 49
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 37.44823455810547,
+      "learning_rate": 0.0,
+      "loss": 0.4355,
+      "step": 50
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "eval_loss": 0.41843298077583313,
+      "eval_runtime": 3.4685,
+      "eval_samples_per_second": 34.597,
+      "eval_steps_per_second": 4.325,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null