Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:810f793a7a09aec097ba11fd2ed583598061306cbc44d9854bdd21c803e84f43
+oid sha256:389d447219c804285fae84d69d52fdb353ccada6e496c7186c34f57b4b3f5550
 size 78207176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:669fb24e30061fe0229eba690c791e3d2d3d478f617f0075e8583673d958416c
+oid sha256:52a2541272ce7fea90d87550a71aa247d9ee0a80aacdc1099f55d83d19c45ee9
 size 40177764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1c01f24f1ea1200b2c870be081fada257d22c3cdf6eec230d9a94ba89b146ed
+oid sha256:22c54f3482cff1a197e1753823b303d3a8651f4e9ca36ee89603e5a2f6115309
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7305309772491455,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.28328611898017,
+  "best_metric": 1.7026445865631104,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.56657223796034,
   "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": 108.538,
       "eval_steps_per_second": 13.84,
       "step": 25
+    },
+    {
+      "epoch": 0.29461756373937675,
+      "grad_norm": 0.21514885127544403,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.7355,
+      "step": 26
+    },
+    {
+      "epoch": 0.3059490084985836,
+      "grad_norm": 0.2080201953649521,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.5752,
+      "step": 27
+    },
+    {
+      "epoch": 0.31728045325779036,
+      "grad_norm": 0.197081059217453,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.5707,
+      "step": 28
+    },
+    {
+      "epoch": 0.3286118980169972,
+      "grad_norm": 0.2009827047586441,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.5871,
+      "step": 29
+    },
+    {
+      "epoch": 0.33994334277620397,
+      "grad_norm": 0.2195533812046051,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.6545,
+      "step": 30
+    },
+    {
+      "epoch": 0.35127478753541075,
+      "grad_norm": 0.23961254954338074,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.7495,
+      "step": 31
+    },
+    {
+      "epoch": 0.3626062322946176,
+      "grad_norm": 0.18581852316856384,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.6507,
+      "step": 32
+    },
+    {
+      "epoch": 0.37393767705382436,
+      "grad_norm": 0.20042315125465393,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.6437,
+      "step": 33
+    },
+    {
+      "epoch": 0.38526912181303113,
+      "grad_norm": 0.20618341863155365,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.6764,
+      "step": 34
+    },
+    {
+      "epoch": 0.39660056657223797,
+      "grad_norm": 0.20008434355258942,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.7011,
+      "step": 35
+    },
+    {
+      "epoch": 0.40793201133144474,
+      "grad_norm": 0.23139382898807526,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.6504,
+      "step": 36
+    },
+    {
+      "epoch": 0.4192634560906516,
+      "grad_norm": 0.25248095393180847,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.6017,
+      "step": 37
+    },
+    {
+      "epoch": 0.43059490084985835,
+      "grad_norm": 0.24187323451042175,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.7711,
+      "step": 38
+    },
+    {
+      "epoch": 0.44192634560906513,
+      "grad_norm": 0.27244117856025696,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.8675,
+      "step": 39
+    },
+    {
+      "epoch": 0.45325779036827196,
+      "grad_norm": 0.2246805727481842,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.8444,
+      "step": 40
+    },
+    {
+      "epoch": 0.46458923512747874,
+      "grad_norm": 0.2878750264644623,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.7995,
+      "step": 41
+    },
+    {
+      "epoch": 0.47592067988668557,
+      "grad_norm": 0.2895854711532593,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.7724,
+      "step": 42
+    },
+    {
+      "epoch": 0.48725212464589235,
+      "grad_norm": 0.34377485513687134,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.7968,
+      "step": 43
+    },
+    {
+      "epoch": 0.4985835694050991,
+      "grad_norm": 0.36949583888053894,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.7625,
+      "step": 44
+    },
+    {
+      "epoch": 0.509915014164306,
+      "grad_norm": 0.16927896440029144,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.5636,
+      "step": 45
+    },
+    {
+      "epoch": 0.5212464589235127,
+      "grad_norm": 0.16003383696079254,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.4856,
+      "step": 46
+    },
+    {
+      "epoch": 0.5325779036827195,
+      "grad_norm": 0.14991965889930725,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.6608,
+      "step": 47
+    },
+    {
+      "epoch": 0.5439093484419264,
+      "grad_norm": 0.19233012199401855,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.6948,
+      "step": 48
+    },
+    {
+      "epoch": 0.5552407932011332,
+      "grad_norm": 0.18915553390979767,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.5136,
+      "step": 49
+    },
+    {
+      "epoch": 0.56657223796034,
+      "grad_norm": 0.2019452601671219,
+      "learning_rate": 0.0,
+      "loss": 1.5715,
+      "step": 50
+    },
+    {
+      "epoch": 0.56657223796034,
+      "eval_loss": 1.7026445865631104,
+      "eval_runtime": 1.3716,
+      "eval_samples_per_second": 108.633,
+      "eval_steps_per_second": 13.853,
+      "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": 618044011315200.0,
+  "total_flos": 1236088022630400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null