Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ee13b68c72ac82b939f137f07c187c225085c419cb37ed81de70d73c5b85db8
+oid sha256:e8dcb9945fd2ecc339300d7eb65ec9e47082058be8e3ebbce1272014eafb2c77
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:787303e72528e1b922ff5b0bf77965d05cd9cac478fc8ca4ede73063a31c7666
+oid sha256:be6915a12df2e73267355ab954d70640023a55c33da733775466ca551d1c6422
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b77c9d47ea30804af8abdf97e234b3ce675408997c26a3369c21a3f7fd2966e1
+oid sha256:4112ee8a6422fdbd6e1694f9b1995795231aac521ab49e0d6779f6e817558ada
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63cfe7778d3f25d272ac353d8fd1683074ead18023bf70c53002f9a53ba9bd93
+oid sha256:acef140ba4152eb4a38c728bc2fb1a2ed40c789ab0bf8a1e0470ff59ce722fcc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70be848a07a334d1802d971c2a8cafc8d3965f7ecb76fb786a64268734cf3d4c
+oid sha256:fcc5806ca90feb608fbd18278e484c5701038240bb6d44841334b3f4595e0dd9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbba49e5010f367ff352c28f457f27a59799207923c1592e723aca0f144e50a4
+oid sha256:568c36d169057949eae8d99f612d9d37d3a243fd3f5417e617ff85dd15be5121
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d5f446d81df8b8e6d5d3423a874831fec3d08bffbe4980db71b54ceb3e7bd4
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.12913550436496735,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 1.2903225806451613,
+  "best_metric": 0.12861138582229614,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 1.7204301075268817,
   "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": 76.128,
       "eval_steps_per_second": 9.516,
       "step": 75
+    },
+    {
+      "epoch": 1.3075268817204302,
+      "grad_norm": 0.28724661469459534,
+      "learning_rate": 1.4938160786375572e-05,
+      "loss": 0.0693,
+      "step": 76
+    },
+    {
+      "epoch": 1.324731182795699,
+      "grad_norm": 0.30966466665267944,
+      "learning_rate": 1.3778739760445552e-05,
+      "loss": 0.0818,
+      "step": 77
+    },
+    {
+      "epoch": 1.3419354838709676,
+      "grad_norm": 0.30045086145401,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 0.0787,
+      "step": 78
+    },
+    {
+      "epoch": 1.3591397849462366,
+      "grad_norm": 0.32244807481765747,
+      "learning_rate": 1.157994445715706e-05,
+      "loss": 0.0848,
+      "step": 79
+    },
+    {
+      "epoch": 1.3763440860215055,
+      "grad_norm": 0.314584881067276,
+      "learning_rate": 1.0542974530180327e-05,
+      "loss": 0.0883,
+      "step": 80
+    },
+    {
+      "epoch": 1.3935483870967742,
+      "grad_norm": 0.34502357244491577,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0882,
+      "step": 81
+    },
+    {
+      "epoch": 1.410752688172043,
+      "grad_norm": 0.43789923191070557,
+      "learning_rate": 8.599558442598998e-06,
+      "loss": 0.1093,
+      "step": 82
+    },
+    {
+      "epoch": 1.4279569892473118,
+      "grad_norm": 0.5525321364402771,
+      "learning_rate": 7.695237378953223e-06,
+      "loss": 0.1309,
+      "step": 83
+    },
+    {
+      "epoch": 1.4451612903225808,
+      "grad_norm": 0.28792673349380493,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 0.0488,
+      "step": 84
+    },
+    {
+      "epoch": 1.4623655913978495,
+      "grad_norm": 0.20269066095352173,
+      "learning_rate": 6.026312439675552e-06,
+      "loss": 0.0516,
+      "step": 85
+    },
+    {
+      "epoch": 1.4795698924731182,
+      "grad_norm": 0.2444780319929123,
+      "learning_rate": 5.263533508961827e-06,
+      "loss": 0.0632,
+      "step": 86
+    },
+    {
+      "epoch": 1.4967741935483871,
+      "grad_norm": 0.27078327536582947,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 0.0694,
+      "step": 87
+    },
+    {
+      "epoch": 1.513978494623656,
+      "grad_norm": 0.2688973844051361,
+      "learning_rate": 3.885512251130763e-06,
+      "loss": 0.0732,
+      "step": 88
+    },
+    {
+      "epoch": 1.5311827956989248,
+      "grad_norm": 0.29662248492240906,
+      "learning_rate": 3.271776770026963e-06,
+      "loss": 0.0768,
+      "step": 89
+    },
+    {
+      "epoch": 1.5483870967741935,
+      "grad_norm": 0.34857553243637085,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 0.0868,
+      "step": 90
+    },
+    {
+      "epoch": 1.5655913978494622,
+      "grad_norm": 0.3253614008426666,
+      "learning_rate": 2.1982109232821178e-06,
+      "loss": 0.0789,
+      "step": 91
+    },
+    {
+      "epoch": 1.5827956989247312,
+      "grad_norm": 0.3459737002849579,
+      "learning_rate": 1.7395544861325718e-06,
+      "loss": 0.085,
+      "step": 92
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.3518889248371124,
+      "learning_rate": 1.333670137599713e-06,
+      "loss": 0.095,
+      "step": 93
+    },
+    {
+      "epoch": 1.6172043010752688,
+      "grad_norm": 0.44837722182273865,
+      "learning_rate": 9.810017062595322e-07,
+      "loss": 0.1058,
+      "step": 94
+    },
+    {
+      "epoch": 1.6344086021505375,
+      "grad_norm": 0.4785314202308655,
+      "learning_rate": 6.819348298638839e-07,
+      "loss": 0.113,
+      "step": 95
+    },
+    {
+      "epoch": 1.6516129032258065,
+      "grad_norm": 0.21725249290466309,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 0.0481,
+      "step": 96
+    },
+    {
+      "epoch": 1.6688172043010754,
+      "grad_norm": 0.16432440280914307,
+      "learning_rate": 2.458548727494292e-07,
+      "loss": 0.0433,
+      "step": 97
+    },
+    {
+      "epoch": 1.686021505376344,
+      "grad_norm": 0.21126870810985565,
+      "learning_rate": 1.0931863906127327e-07,
+      "loss": 0.0511,
+      "step": 98
+    },
+    {
+      "epoch": 1.7032258064516128,
+      "grad_norm": 0.2568517327308655,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 0.069,
+      "step": 99
+    },
+    {
+      "epoch": 1.7204301075268817,
+      "grad_norm": 0.3253111243247986,
+      "learning_rate": 0.0,
+      "loss": 0.0793,
+      "step": 100
+    },
+    {
+      "epoch": 1.7204301075268817,
+      "eval_loss": 0.12861138582229614,
+      "eval_runtime": 5.1532,
+      "eval_samples_per_second": 76.069,
+      "eval_steps_per_second": 9.509,
+      "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": 2.384195670245376e+17,
+  "total_flos": 3.178927560327168e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null