Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5609fc529a27d9029b91cbc1b6497a9f6481f3a1c180872608d28578468175b1
+oid sha256:03c4489852ce3f749c9d8e603e867176bba85bcb212dba0dc425a6ffed14990f
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:797695502e8e2360d028bb82c1f225c0abe7e4cb6deeb4f5e1c5dda05381c7a6
+oid sha256:b08a0b8daac4a5d1df32b47a81d859d72b5807ce4fdb7ad924757a5ca784bb86
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c1430c9d12a1d23e8e302b7d18d4a4a9c4a6d9b8a704442e85759e1c8af6c1
+oid sha256:14248276d72f4dd98c9849d8d54a4a93183633b55757a76e949b9c60ec0872ea
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8947b26818f2b48cdab60ac49e6850ac5a45983ddbc2e966334b654b665b5c81
+oid sha256:f5dd4aef7f4fbae7c037e914c7735463bbaa5c3acfaeb1ac32b922a442a8cc90
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c02a3b615456816eafc7b2eae64c142b795e81886f3f5a6ae469c9925735b4b2
+oid sha256:379f3d49970108e5b914aca890b8b88dd6aa26961d9f0c9a59d96989acdb034f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5086913c80ff6b019645ad90ab852cd887c7fcab5d8728794f65402e55991b67
+oid sha256:c0a46fa0dbae053bdcec3e3a5d9494dcbf84811793f22e6af38007809a18de18
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:344fc18df9c84f214bc47e69d1bbde70d66cf3ec6caeac9cd529dfb5814c4b9a
+oid sha256:051dee7dfbeecb34b46e8409ffafec324501f465585234624669bc8c9e863ae4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6713114976882935,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.9149828440716736,
+  "best_metric": 1.6244957447052002,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 1.2222645825390774,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 35.12,
       "eval_steps_per_second": 9.131,
       "step": 75
+    },
+    {
+      "epoch": 0.9271826153259627,
+      "grad_norm": 1.0527911186218262,
+      "learning_rate": 2.3444344707738015e-05,
+      "loss": 2.1647,
+      "step": 76
+    },
+    {
+      "epoch": 0.9393823865802516,
+      "grad_norm": 1.0965566635131836,
+      "learning_rate": 2.2400865784401e-05,
+      "loss": 1.8203,
+      "step": 77
+    },
+    {
+      "epoch": 0.9515821578345406,
+      "grad_norm": 1.1224842071533203,
+      "learning_rate": 2.1393033535713093e-05,
+      "loss": 1.8365,
+      "step": 78
+    },
+    {
+      "epoch": 0.9637819290888295,
+      "grad_norm": 1.083632469177246,
+      "learning_rate": 2.0421950011441354e-05,
+      "loss": 1.5104,
+      "step": 79
+    },
+    {
+      "epoch": 0.9759817003431186,
+      "grad_norm": 1.1941848993301392,
+      "learning_rate": 1.9488677077162295e-05,
+      "loss": 1.4217,
+      "step": 80
+    },
+    {
+      "epoch": 0.9881814715974075,
+      "grad_norm": 1.4089711904525757,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 1.4428,
+      "step": 81
+    },
+    {
+      "epoch": 1.0026686999618757,
+      "grad_norm": 1.9810051918029785,
+      "learning_rate": 1.77396025983391e-05,
+      "loss": 1.5342,
+      "step": 82
+    },
+    {
+      "epoch": 1.0148684712161646,
+      "grad_norm": 0.940060555934906,
+      "learning_rate": 1.6925713641057904e-05,
+      "loss": 1.7435,
+      "step": 83
+    },
+    {
+      "epoch": 1.0270682424704536,
+      "grad_norm": 1.0035717487335205,
+      "learning_rate": 1.6153458356909176e-05,
+      "loss": 1.9253,
+      "step": 84
+    },
+    {
+      "epoch": 1.0392680137247428,
+      "grad_norm": 1.069605827331543,
+      "learning_rate": 1.5423681195707997e-05,
+      "loss": 1.7862,
+      "step": 85
+    },
+    {
+      "epoch": 1.0514677849790317,
+      "grad_norm": 1.121212124824524,
+      "learning_rate": 1.4737180158065644e-05,
+      "loss": 1.505,
+      "step": 86
+    },
+    {
+      "epoch": 1.0636675562333207,
+      "grad_norm": 1.131169080734253,
+      "learning_rate": 1.4094705922787687e-05,
+      "loss": 1.6766,
+      "step": 87
+    },
+    {
+      "epoch": 1.0758673274876096,
+      "grad_norm": 1.1634432077407837,
+      "learning_rate": 1.3496961026017687e-05,
+      "loss": 1.4677,
+      "step": 88
+    },
+    {
+      "epoch": 1.0880670987418986,
+      "grad_norm": 1.1550370454788208,
+      "learning_rate": 1.2944599093024267e-05,
+      "loss": 1.4571,
+      "step": 89
+    },
+    {
+      "epoch": 1.1002668699961875,
+      "grad_norm": 1.2418510913848877,
+      "learning_rate": 1.2438224123471442e-05,
+      "loss": 1.3787,
+      "step": 90
+    },
+    {
+      "epoch": 1.1124666412504765,
+      "grad_norm": 1.244449496269226,
+      "learning_rate": 1.1978389830953907e-05,
+      "loss": 1.3382,
+      "step": 91
+    },
+    {
+      "epoch": 1.1246664125047656,
+      "grad_norm": 1.207255482673645,
+      "learning_rate": 1.1565599037519316e-05,
+      "loss": 1.1813,
+      "step": 92
+    },
+    {
+      "epoch": 1.1368661837590546,
+      "grad_norm": 1.613624930381775,
+      "learning_rate": 1.1200303123839742e-05,
+      "loss": 1.3322,
+      "step": 93
+    },
+    {
+      "epoch": 1.1490659550133435,
+      "grad_norm": 1.5924932956695557,
+      "learning_rate": 1.088290153563358e-05,
+      "loss": 0.7849,
+      "step": 94
+    },
+    {
+      "epoch": 1.1612657262676325,
+      "grad_norm": 1.3866314888000488,
+      "learning_rate": 1.0613741346877497e-05,
+      "loss": 2.1158,
+      "step": 95
+    },
+    {
+      "epoch": 1.1734654975219214,
+      "grad_norm": 1.0334395170211792,
+      "learning_rate": 1.0393116880286118e-05,
+      "loss": 1.7684,
+      "step": 96
+    },
+    {
+      "epoch": 1.1856652687762104,
+      "grad_norm": 1.1649991273880005,
+      "learning_rate": 1.0221269385474488e-05,
+      "loss": 1.8588,
+      "step": 97
+    },
+    {
+      "epoch": 1.1978650400304995,
+      "grad_norm": 1.1444116830825806,
+      "learning_rate": 1.0098386775155147e-05,
+      "loss": 1.7781,
+      "step": 98
+    },
+    {
+      "epoch": 1.2100648112847885,
+      "grad_norm": 1.1716587543487549,
+      "learning_rate": 1.0024603419658329e-05,
+      "loss": 1.5944,
+      "step": 99
+    },
+    {
+      "epoch": 1.2222645825390774,
+      "grad_norm": 1.1668322086334229,
+      "learning_rate": 1e-05,
+      "loss": 1.5552,
+      "step": 100
+    },
+    {
+      "epoch": 1.2222645825390774,
+      "eval_loss": 1.6244957447052002,
+      "eval_runtime": 1.4265,
+      "eval_samples_per_second": 35.051,
+      "eval_steps_per_second": 9.113,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -587,12 +770,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.436086715973632e+17,
+  "total_flos": 1.1248115621298176e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null