Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57f1c0b5d1d82055f88db188700602c17f2b055c2c94e52a19cb8ed7bc150843
+oid sha256:584eb3c87625da59bedbe0d4f4252aaf5ccd2c3893744dba1d9fe4acf1bb9a81
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015fd2ac24bbf7b4793e02ef38b2337cc8eaac7e91433e405a0dd5dbd012ca89
+oid sha256:254fcec862c34384bbe9be095967c63e47cef2fd1e62001adc04ce7dfb753858
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfe0178594cc7eabfd8156bdce9c34520bbc5384f2412a0a20958372ca69897f
+oid sha256:17599926345bf9187a009803538cee0e683def6914e6f71e22a4e0ea200b6d9c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb2ec85a6363c55d477fbfcc5d3ea2f5cf888d5077239a6c880d6ac923ccf2c1
+oid sha256:8ddb265032c4e0808667e124161f03d27d2ab4c8708aec9aa5b6855b86f8092a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25c6d36cf76e3a255b6cac005988d4268d44623af160e7cd25131b125c94df43
+oid sha256:b1db0fa56fd37065d42fea920674d055f08efd97f275656e896c5cc9a1e9c5ab
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73a95f893479a297e6580762adf31d2aba6aef81e7fb7ca41aa8c52bf815fdcb
+oid sha256:ac9821cf27a8f40b4f06c99d881e89a31983c5bbc1634ba38c536f9c837d5d76
 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": 10.369590759277344,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.78125,
+  "best_metric": 10.36829948425293,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.5625,
   "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": 464.331,
       "eval_steps_per_second": 58.041,
       "step": 25
+    },
+    {
+      "epoch": 0.8125,
+      "grad_norm": 0.04869234934449196,
+      "learning_rate": 5e-05,
+      "loss": 10.37,
+      "step": 26
+    },
+    {
+      "epoch": 0.84375,
+      "grad_norm": 0.04844861850142479,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3704,
+      "step": 27
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.04071667417883873,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.37,
+      "step": 28
+    },
+    {
+      "epoch": 0.90625,
+      "grad_norm": 0.04985747113823891,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3696,
+      "step": 29
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.04165804758667946,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3702,
+      "step": 30
+    },
+    {
+      "epoch": 0.96875,
+      "grad_norm": 0.041387688368558884,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3697,
+      "step": 31
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.0426969900727272,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3677,
+      "step": 32
+    },
+    {
+      "epoch": 1.03125,
+      "grad_norm": 0.048314694315195084,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3689,
+      "step": 33
+    },
+    {
+      "epoch": 1.0625,
+      "grad_norm": 0.05188485607504845,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.369,
+      "step": 34
+    },
+    {
+      "epoch": 1.09375,
+      "grad_norm": 0.04773072525858879,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3689,
+      "step": 35
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 0.04484302178025246,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3688,
+      "step": 36
+    },
+    {
+      "epoch": 1.15625,
+      "grad_norm": 0.04816482588648796,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3687,
+      "step": 37
+    },
+    {
+      "epoch": 1.1875,
+      "grad_norm": 0.045386429876089096,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3693,
+      "step": 38
+    },
+    {
+      "epoch": 1.21875,
+      "grad_norm": 0.042508915066719055,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3683,
+      "step": 39
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.046760160475969315,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3677,
+      "step": 40
+    },
+    {
+      "epoch": 1.28125,
+      "grad_norm": 0.054309193044900894,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3679,
+      "step": 41
+    },
+    {
+      "epoch": 1.3125,
+      "grad_norm": 0.05351242050528526,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3689,
+      "step": 42
+    },
+    {
+      "epoch": 1.34375,
+      "grad_norm": 0.053058575838804245,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3694,
+      "step": 43
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 0.04718147963285446,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3692,
+      "step": 44
+    },
+    {
+      "epoch": 1.40625,
+      "grad_norm": 0.047716692090034485,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3697,
+      "step": 45
+    },
+    {
+      "epoch": 1.4375,
+      "grad_norm": 0.05036978796124458,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3681,
+      "step": 46
+    },
+    {
+      "epoch": 1.46875,
+      "grad_norm": 0.0434553399682045,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3686,
+      "step": 47
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.04664258286356926,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3672,
+      "step": 48
+    },
+    {
+      "epoch": 1.53125,
+      "grad_norm": 0.05585478991270065,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3681,
+      "step": 49
+    },
+    {
+      "epoch": 1.5625,
+      "grad_norm": 0.0510258823633194,
+      "learning_rate": 0.0,
+      "loss": 10.3685,
+      "step": 50
+    },
+    {
+      "epoch": 1.5625,
+      "eval_loss": 10.36829948425293,
+      "eval_runtime": 0.4594,
+      "eval_samples_per_second": 470.157,
+      "eval_steps_per_second": 58.77,
+      "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": 22306216083456.0,
+  "total_flos": 44438686924800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null