Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72921007d98c6506d65cca6e90aa810a5eb6aaa2e2a567dcc775dd0a574b4bff
+oid sha256:79b20c2483718f2ed6f0e8bb037b950bb37b33d06077c0888fc9299fdf53c6c9
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb65e43956dbf1e70ed6930f15f027933bed5c581f076f24d526c3e7294e14a9
+oid sha256:086f9b2d58d9a0dbef93a6b02c90ae3e4de17563bb212b8955e4aeb33f0aa800
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b0c8dca925c16028ac8479044a49c3499e5ac806aa5abce062731099ba8c252
+oid sha256:3de3f04e0d7b7702b6ffefbfffac2d2805cdc37c248c262b19bfd4b28fb43df3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24397156868425334788a33367d0d24381fa35eaf4e90fb133b802baff4b4218
+oid sha256:16b6b55d41465e81ebe0031be264a9293627314e6cb84300dbbcceec95c2263b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:973e012bfc309e37549a3d8a64f5e20a99842e9487c8260fe50517e8a4755f39
+oid sha256:de96a4e5613a0ea7069e0b2aa32c3925d9594fa0e6e81eb3e0090d5eb4b3e9e0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cf8f65913212d6876f75c262140d1f63a32579caeb96b118eb50ec9a4cdc843
+oid sha256:aada736d8cc1d8ace03b79ab876e0e133073ada59192a9da8f5f53006ec59607
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0861386060714722,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2077922077922078,
+  "best_metric": 1.05935800075531,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4155844155844156,
   "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": 31.015,
       "eval_steps_per_second": 3.901,
       "step": 25
+    },
+    {
+      "epoch": 0.2161038961038961,
+      "grad_norm": 0.23987476527690887,
+      "learning_rate": 5e-05,
+      "loss": 0.9859,
+      "step": 26
+    },
+    {
+      "epoch": 0.22441558441558443,
+      "grad_norm": 0.36977705359458923,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9489,
+      "step": 27
+    },
+    {
+      "epoch": 0.23272727272727273,
+      "grad_norm": 0.28386303782463074,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.8192,
+      "step": 28
+    },
+    {
+      "epoch": 0.24103896103896105,
+      "grad_norm": 0.28928664326667786,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.8652,
+      "step": 29
+    },
+    {
+      "epoch": 0.24935064935064935,
+      "grad_norm": 0.4036184549331665,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.0874,
+      "step": 30
+    },
+    {
+      "epoch": 0.25766233766233765,
+      "grad_norm": 0.4978172481060028,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.3074,
+      "step": 31
+    },
+    {
+      "epoch": 0.265974025974026,
+      "grad_norm": 0.5747013688087463,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.3194,
+      "step": 32
+    },
+    {
+      "epoch": 0.2742857142857143,
+      "grad_norm": 0.4833392798900604,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.2504,
+      "step": 33
+    },
+    {
+      "epoch": 0.2825974025974026,
+      "grad_norm": 0.573775589466095,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.2703,
+      "step": 34
+    },
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 0.5862915515899658,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.1775,
+      "step": 35
+    },
+    {
+      "epoch": 0.2992207792207792,
+      "grad_norm": 0.483033686876297,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.9526,
+      "step": 36
+    },
+    {
+      "epoch": 0.30753246753246755,
+      "grad_norm": 0.6226116418838501,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.984,
+      "step": 37
+    },
+    {
+      "epoch": 0.31584415584415587,
+      "grad_norm": 0.2604388892650604,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8811,
+      "step": 38
+    },
+    {
+      "epoch": 0.32415584415584414,
+      "grad_norm": 0.19333459436893463,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.9441,
+      "step": 39
+    },
+    {
+      "epoch": 0.33246753246753247,
+      "grad_norm": 0.201664999127388,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.9568,
+      "step": 40
+    },
+    {
+      "epoch": 0.3407792207792208,
+      "grad_norm": 0.20325258374214172,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7732,
+      "step": 41
+    },
+    {
+      "epoch": 0.3490909090909091,
+      "grad_norm": 0.2257876992225647,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8841,
+      "step": 42
+    },
+    {
+      "epoch": 0.3574025974025974,
+      "grad_norm": 0.3107191026210785,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.307,
+      "step": 43
+    },
+    {
+      "epoch": 0.3657142857142857,
+      "grad_norm": 0.3348431885242462,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2376,
+      "step": 44
+    },
+    {
+      "epoch": 0.37402597402597404,
+      "grad_norm": 0.35244983434677124,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.3097,
+      "step": 45
+    },
+    {
+      "epoch": 0.38233766233766237,
+      "grad_norm": 0.3649301826953888,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.1649,
+      "step": 46
+    },
+    {
+      "epoch": 0.39064935064935064,
+      "grad_norm": 0.412195086479187,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.1256,
+      "step": 47
+    },
+    {
+      "epoch": 0.39896103896103896,
+      "grad_norm": 0.4812576174736023,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.0379,
+      "step": 48
+    },
+    {
+      "epoch": 0.4072727272727273,
+      "grad_norm": 0.43518587946891785,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7584,
+      "step": 49
+    },
+    {
+      "epoch": 0.4155844155844156,
+      "grad_norm": 0.9060344696044922,
+      "learning_rate": 0.0,
+      "loss": 1.162,
+      "step": 50
+    },
+    {
+      "epoch": 0.4155844155844156,
+      "eval_loss": 1.05935800075531,
+      "eval_runtime": 26.4737,
+      "eval_samples_per_second": 30.634,
+      "eval_steps_per_second": 3.853,
+      "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": 3.000827034772439e+17,
+  "total_flos": 6.010979195163771e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null