Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96de827f5589c227588fcb4a74e07b01e23d062b00723ad3b32772bd73a1516d
+oid sha256:0b5794a8115c99c9a8276a23b749df150d3e1ed64290adbbf49a20a121c6ea28
 size 78207176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cc296ad3b05ffbcc7cdffce947aa4925378c0f6acd6949c1583e990c77aec35
+oid sha256:5b662aa6c63dd8a263ae28e7df4357a09d7b5fd314a12efc617df5cfd4c5c5d9
 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": 1.7306195497512817,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.28328611898017,
+  "best_metric": 1.7024426460266113,
+  "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": 108.767,
       "eval_steps_per_second": 13.87,
       "step": 25
+    },
+    {
+      "epoch": 0.29461756373937675,
+      "grad_norm": 0.21815790235996246,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.7345,
+      "step": 26
+    },
+    {
+      "epoch": 0.3059490084985836,
+      "grad_norm": 0.2108701467514038,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.5752,
+      "step": 27
+    },
+    {
+      "epoch": 0.31728045325779036,
+      "grad_norm": 0.2015771120786667,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.5707,
+      "step": 28
+    },
+    {
+      "epoch": 0.3286118980169972,
+      "grad_norm": 0.20463882386684418,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.587,
+      "step": 29
+    },
+    {
+      "epoch": 0.33994334277620397,
+      "grad_norm": 0.22213023900985718,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.6546,
+      "step": 30
+    },
+    {
+      "epoch": 0.35127478753541075,
+      "grad_norm": 0.24201658368110657,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.7489,
+      "step": 31
+    },
+    {
+      "epoch": 0.3626062322946176,
+      "grad_norm": 0.18713782727718353,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.6503,
+      "step": 32
+    },
+    {
+      "epoch": 0.37393767705382436,
+      "grad_norm": 0.20224328339099884,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.6441,
+      "step": 33
+    },
+    {
+      "epoch": 0.38526912181303113,
+      "grad_norm": 0.20836849510669708,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.6769,
+      "step": 34
+    },
+    {
+      "epoch": 0.39660056657223797,
+      "grad_norm": 0.20321877300739288,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.7013,
+      "step": 35
+    },
+    {
+      "epoch": 0.40793201133144474,
+      "grad_norm": 0.23479226231575012,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.6496,
+      "step": 36
+    },
+    {
+      "epoch": 0.4192634560906516,
+      "grad_norm": 0.2573692500591278,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.6024,
+      "step": 37
+    },
+    {
+      "epoch": 0.43059490084985835,
+      "grad_norm": 0.24458742141723633,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.7716,
+      "step": 38
+    },
+    {
+      "epoch": 0.44192634560906513,
+      "grad_norm": 0.2757667899131775,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.867,
+      "step": 39
+    },
+    {
+      "epoch": 0.45325779036827196,
+      "grad_norm": 0.22761981189250946,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.8444,
+      "step": 40
+    },
+    {
+      "epoch": 0.46458923512747874,
+      "grad_norm": 0.2908417284488678,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.7983,
+      "step": 41
+    },
+    {
+      "epoch": 0.47592067988668557,
+      "grad_norm": 0.29157117009162903,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.7737,
+      "step": 42
+    },
+    {
+      "epoch": 0.48725212464589235,
+      "grad_norm": 0.3470527231693268,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.7958,
+      "step": 43
+    },
+    {
+      "epoch": 0.4985835694050991,
+      "grad_norm": 0.37411051988601685,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.762,
+      "step": 44
+    },
+    {
+      "epoch": 0.509915014164306,
+      "grad_norm": 0.1717747300863266,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.5636,
+      "step": 45
+    },
+    {
+      "epoch": 0.5212464589235127,
+      "grad_norm": 0.16150543093681335,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.4846,
+      "step": 46
+    },
+    {
+      "epoch": 0.5325779036827195,
+      "grad_norm": 0.1521836221218109,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.661,
+      "step": 47
+    },
+    {
+      "epoch": 0.5439093484419264,
+      "grad_norm": 0.19446030259132385,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.6943,
+      "step": 48
+    },
+    {
+      "epoch": 0.5552407932011332,
+      "grad_norm": 0.19089248776435852,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.5123,
+      "step": 49
+    },
+    {
+      "epoch": 0.56657223796034,
+      "grad_norm": 0.2053840011358261,
+      "learning_rate": 0.0,
+      "loss": 1.5716,
+      "step": 50
+    },
+    {
+      "epoch": 0.56657223796034,
+      "eval_loss": 1.7024426460266113,
+      "eval_runtime": 1.3758,
+      "eval_samples_per_second": 108.303,
+      "eval_steps_per_second": 13.81,
+      "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