Training in progress, step 43, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8abd5715448a8a1fac39804677b50c1e8a72ba4ef436240e8c5e587cf75a07c2
+oid sha256:8e264277991fc4e889fafc66bfc1047254385b24ff80f0aac1794179a80b2b67
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c36772a63afb995ff6a8f52c507cb04505a13298eba625be387a43c97b609bd
+oid sha256:725c7967e372751f013018368849dfae35346db6ed4b036d69604421454c8a3d
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5433ff1e9949be9de1546c90b457864d547bee64a7dc39705010bae1aec1ade5
+oid sha256:449ffd5edc0a9f10a9f7f607b211b3ac6ff28bbd1376679b6f472190381d9454
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:736787b25cc1a2b4028695d5cd33e84f4adc14b368bbe5f4972d774a51f01a26
+oid sha256:10efbe51ec315065adb3c371dd5cd5362662d193edf6d571eccf37d11eee5b1f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6430cd7c709cde9e44e9e2a983a6edec1f9154b0192eb0663158a6dd627d3969
+oid sha256:30af4525e4841f5cd4f93993cba1aff9445086f8c7a87772762d5f4fb0c3b541
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44b6e43d955f77c43dd8a623a3bf286a4a783a569d6bfcf5268db45b9bdc4cb6
+oid sha256:84bc1c7efd56469248a5ec9db1751fc1ba9e5a7e6013394e5f8415bc17cd350f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f73e6deadf3f08547d8bef9e9b3d87995c0c2ef87d51b8801270b8b2d32ac55
+oid sha256:d9ca16dc5125aa616f8880e7477dabd4029e096d950b1e4b31474d314c00eace
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.12850531935691833,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.7777777777777777,
+  "epoch": 3.057777777777778,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 43,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,132 @@
       "eval_samples_per_second": 61.281,
       "eval_steps_per_second": 15.933,
       "step": 25
+    },
+    {
+      "epoch": 1.8488888888888888,
+      "grad_norm": 0.7657303214073181,
+      "learning_rate": 4.307583240115024e-05,
+      "loss": 0.1534,
+      "step": 26
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 1.1523308753967285,
+      "learning_rate": 3.9789240471617385e-05,
+      "loss": 0.1398,
+      "step": 27
+    },
+    {
+      "epoch": 1.991111111111111,
+      "grad_norm": 0.6146386861801147,
+      "learning_rate": 3.659191132728971e-05,
+      "loss": 0.1803,
+      "step": 28
+    },
+    {
+      "epoch": 2.062222222222222,
+      "grad_norm": 5.423893451690674,
+      "learning_rate": 3.350260816694816e-05,
+      "loss": 0.8846,
+      "step": 29
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.7562944293022156,
+      "learning_rate": 3.0539460249945056e-05,
+      "loss": 0.185,
+      "step": 30
+    },
+    {
+      "epoch": 2.2044444444444444,
+      "grad_norm": 0.599077582359314,
+      "learning_rate": 2.7719856506501306e-05,
+      "loss": 0.1333,
+      "step": 31
+    },
+    {
+      "epoch": 2.2755555555555556,
+      "grad_norm": 0.5775408744812012,
+      "learning_rate": 2.5060343492549566e-05,
+      "loss": 0.1894,
+      "step": 32
+    },
+    {
+      "epoch": 2.3466666666666667,
+      "grad_norm": 0.893593966960907,
+      "learning_rate": 2.257652828796459e-05,
+      "loss": 0.1983,
+      "step": 33
+    },
+    {
+      "epoch": 2.417777777777778,
+      "grad_norm": 0.8925317525863647,
+      "learning_rate": 2.0282986908012567e-05,
+      "loss": 0.1313,
+      "step": 34
+    },
+    {
+      "epoch": 2.488888888888889,
+      "grad_norm": 0.6804959774017334,
+      "learning_rate": 1.819317876549771e-05,
+      "loss": 0.1761,
+      "step": 35
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.6663115620613098,
+      "learning_rate": 1.631936768557596e-05,
+      "loss": 0.2367,
+      "step": 36
+    },
+    {
+      "epoch": 2.631111111111111,
+      "grad_norm": 0.5432018637657166,
+      "learning_rate": 1.4672549936752506e-05,
+      "loss": 0.1042,
+      "step": 37
+    },
+    {
+      "epoch": 2.7022222222222223,
+      "grad_norm": 0.5868009328842163,
+      "learning_rate": 1.3262389700405744e-05,
+      "loss": 0.1132,
+      "step": 38
+    },
+    {
+      "epoch": 2.7733333333333334,
+      "grad_norm": 0.6464464068412781,
+      "learning_rate": 1.2097162357528127e-05,
+      "loss": 0.2215,
+      "step": 39
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "grad_norm": 0.779269814491272,
+      "learning_rate": 1.1183705925499948e-05,
+      "loss": 0.1072,
+      "step": 40
+    },
+    {
+      "epoch": 2.9155555555555557,
+      "grad_norm": 0.7263559699058533,
+      "learning_rate": 1.0527380929884324e-05,
+      "loss": 0.151,
+      "step": 41
+    },
+    {
+      "epoch": 2.986666666666667,
+      "grad_norm": 0.471716970205307,
+      "learning_rate": 1.013203894673168e-05,
+      "loss": 0.133,
+      "step": 42
+    },
+    {
+      "epoch": 3.057777777777778,
+      "grad_norm": 3.000406503677368,
+      "learning_rate": 1e-05,
+      "loss": 0.4811,
+      "step": 43
     }
   ],
   "logging_steps": 1,
@@ -221,12 +347,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.3494879120195584e+16,
+  "total_flos": 4.053927872744653e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null