Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59b72f27586bf62d300d93fda0b47c803754d131e219256030ed9ee1c8588f4d
+oid sha256:5650d236ca7ce3c80baae342c91c15e4da40a0b3015fedd3f567ee044d5577e5
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b491f9d02c526ddb9a40c04b87329a889c0f47a7ce97e146ac027e9b59b28ea
+oid sha256:c6a4c258e7caa9f5baa3634ecfc9c6e91e06df3be96d1eed5719c5a74fff2a15
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:419bc404d533540190a83d9ccb67653c34516b43b45585fa7aea495c775f02af
+oid sha256:2823175e52b8f4261103a266a962266abf3b857c89f832ef330f22052fd733e0
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32f90e5a3038868f9c6012c79de8a38bd0f0ff492d38420d01fdb386de991f70
+oid sha256:e3e6b24a88b042328fb2611208f478539a6c4c8fa42995c8d7f55c5896dca3b7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35c9638a53e0015e4dcf2ba71508396b9e405d19352e7143e8fa521c2de20bd4
+oid sha256:6fb0a5e742354e8eec3156d0a0ffadf1d8b1b0e12e27992795e15cfcaaad14db
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4da96f9a90f53d90de6684c11e6f60b2a6823749a7ec40949d5a7bce6048bedf
+oid sha256:2f19aec6c1dbbc596258db64220e337fb14777392ac1c54fd0575b88565ecf43
 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": 0.4028291404247284,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.17006802721088435,
+  "best_metric": 0.3844531178474426,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3401360544217687,
   "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": 67.69,
       "eval_steps_per_second": 8.478,
       "step": 25
+    },
+    {
+      "epoch": 0.17687074829931973,
+      "grad_norm": 2.9347524642944336,
+      "learning_rate": 5e-05,
+      "loss": 0.3897,
+      "step": 26
+    },
+    {
+      "epoch": 0.1836734693877551,
+      "grad_norm": 1.8317487239837646,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3737,
+      "step": 27
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 1.3707479238510132,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.361,
+      "step": 28
+    },
+    {
+      "epoch": 0.19727891156462585,
+      "grad_norm": 2.5283937454223633,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3784,
+      "step": 29
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 4.494095325469971,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.451,
+      "step": 30
+    },
+    {
+      "epoch": 0.2108843537414966,
+      "grad_norm": 2.8817901611328125,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.3921,
+      "step": 31
+    },
+    {
+      "epoch": 0.21768707482993196,
+      "grad_norm": 3.1406774520874023,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.401,
+      "step": 32
+    },
+    {
+      "epoch": 0.22448979591836735,
+      "grad_norm": 0.7519339323043823,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.3626,
+      "step": 33
+    },
+    {
+      "epoch": 0.23129251700680273,
+      "grad_norm": 1.8915636539459229,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3582,
+      "step": 34
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 1.8647130727767944,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3819,
+      "step": 35
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "grad_norm": 2.3185150623321533,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3671,
+      "step": 36
+    },
+    {
+      "epoch": 0.25170068027210885,
+      "grad_norm": 1.58749520778656,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3764,
+      "step": 37
+    },
+    {
+      "epoch": 0.2585034013605442,
+      "grad_norm": 1.3564950227737427,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3626,
+      "step": 38
+    },
+    {
+      "epoch": 0.2653061224489796,
+      "grad_norm": 1.6234629154205322,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3539,
+      "step": 39
+    },
+    {
+      "epoch": 0.272108843537415,
+      "grad_norm": 0.8268040418624878,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.3548,
+      "step": 40
+    },
+    {
+      "epoch": 0.2789115646258503,
+      "grad_norm": 1.4466538429260254,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.3619,
+      "step": 41
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 1.0540509223937988,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3516,
+      "step": 42
+    },
+    {
+      "epoch": 0.2925170068027211,
+      "grad_norm": 1.3594141006469727,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.3627,
+      "step": 43
+    },
+    {
+      "epoch": 0.29931972789115646,
+      "grad_norm": 1.4748440980911255,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3641,
+      "step": 44
+    },
+    {
+      "epoch": 0.30612244897959184,
+      "grad_norm": 1.318192481994629,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.3571,
+      "step": 45
+    },
+    {
+      "epoch": 0.3129251700680272,
+      "grad_norm": 1.4911541938781738,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.3601,
+      "step": 46
+    },
+    {
+      "epoch": 0.3197278911564626,
+      "grad_norm": 1.3058550357818604,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3694,
+      "step": 47
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 1.2018486261367798,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.36,
+      "step": 48
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 1.4444513320922852,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.376,
+      "step": 49
+    },
+    {
+      "epoch": 0.3401360544217687,
+      "grad_norm": 1.5461527109146118,
+      "learning_rate": 0.0,
+      "loss": 0.3788,
+      "step": 50
+    },
+    {
+      "epoch": 0.3401360544217687,
+      "eval_loss": 0.3844531178474426,
+      "eval_runtime": 14.6207,
+      "eval_samples_per_second": 67.712,
+      "eval_steps_per_second": 8.481,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null