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:d4b9abd4b9c868b89baa7d7ffb0ff4e9a470d39b06d7977c6437af703f5afef1
+oid sha256:9cd6cf8e1e7c8159a6780ea796a54a32f3f2804f9fa984addba7a9b8a2ca65f8
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f974cfb5bc7cc66d4524101fb824128ac29f56185ded9ec4ff4176ed4817916d
+oid sha256:c03918266442181720319d44d2a8355503e9af4a395b1a4e844e71a7b14205e0
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:455592f5f9c8b0df7901f7143b9156bdd7169879b2ad646d9292600a5d095626
+oid sha256:b22140468b57bbde4ff18c099d75349fc8c2026ee6d9ad45f6f5b7e23c76d23d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96c82f7d11261cc5c31ed275a040fec6cc7d5ec3a1352e898e442c26290409f1
+oid sha256:5cc09a1bb04c58613a9e0e19f3e1b96d4659fd58af5f149ce419e0c473292d32
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30982398c1f92eeabe8d4d46c6d5ac3901721ae36214c575999f6bb82ba82d54
+oid sha256:579a15298c2eecb3895047e5c1c552ee56db393d082c11db27f5297e8a67baf7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8684254873c1ddaa587b77466adf1c05c8f2216c9fdd4ce828db1f7ba9cfcb11
+oid sha256:51a1f948c41f73d66ddb005de941fe1444d25e26972fe80c81bbbe9abc4e820b
 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": 11.931558609008789,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1334668001334668,
+  "best_metric": 11.931137084960938,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2669336002669336,
   "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": 379.831,
       "eval_steps_per_second": 47.554,
       "step": 25
+    },
+    {
+      "epoch": 0.13880547213880548,
+      "grad_norm": 0.020508192479610443,
+      "learning_rate": 5e-05,
+      "loss": 11.9312,
+      "step": 26
+    },
+    {
+      "epoch": 0.14414414414414414,
+      "grad_norm": 0.02420317381620407,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.9317,
+      "step": 27
+    },
+    {
+      "epoch": 0.1494828161494828,
+      "grad_norm": 0.023656731471419334,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.9307,
+      "step": 28
+    },
+    {
+      "epoch": 0.1548214881548215,
+      "grad_norm": 0.02386278659105301,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.9311,
+      "step": 29
+    },
+    {
+      "epoch": 0.16016016016016016,
+      "grad_norm": 0.022931382060050964,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.9318,
+      "step": 30
+    },
+    {
+      "epoch": 0.16549883216549882,
+      "grad_norm": 0.022951658815145493,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.9314,
+      "step": 31
+    },
+    {
+      "epoch": 0.1708375041708375,
+      "grad_norm": 0.02454853057861328,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9315,
+      "step": 32
+    },
+    {
+      "epoch": 0.17617617617617617,
+      "grad_norm": 0.023593643680214882,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.9313,
+      "step": 33
+    },
+    {
+      "epoch": 0.18151484818151484,
+      "grad_norm": 0.025214286521077156,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.9313,
+      "step": 34
+    },
+    {
+      "epoch": 0.18685352018685353,
+      "grad_norm": 0.02529080957174301,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.9315,
+      "step": 35
+    },
+    {
+      "epoch": 0.1921921921921922,
+      "grad_norm": 0.026581237092614174,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.9314,
+      "step": 36
+    },
+    {
+      "epoch": 0.19753086419753085,
+      "grad_norm": 0.02596159279346466,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.9312,
+      "step": 37
+    },
+    {
+      "epoch": 0.20286953620286954,
+      "grad_norm": 0.025232110172510147,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.931,
+      "step": 38
+    },
+    {
+      "epoch": 0.2082082082082082,
+      "grad_norm": 0.03222332522273064,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.93,
+      "step": 39
+    },
+    {
+      "epoch": 0.21354688021354687,
+      "grad_norm": 0.028676046058535576,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.9311,
+      "step": 40
+    },
+    {
+      "epoch": 0.21888555221888556,
+      "grad_norm": 0.02865523286163807,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.9302,
+      "step": 41
+    },
+    {
+      "epoch": 0.22422422422422422,
+      "grad_norm": 0.029142210260033607,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.9309,
+      "step": 42
+    },
+    {
+      "epoch": 0.22956289622956288,
+      "grad_norm": 0.028110573068261147,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.9313,
+      "step": 43
+    },
+    {
+      "epoch": 0.23490156823490158,
+      "grad_norm": 0.025929946452379227,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.931,
+      "step": 44
+    },
+    {
+      "epoch": 0.24024024024024024,
+      "grad_norm": 0.03023443929851055,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.9303,
+      "step": 45
+    },
+    {
+      "epoch": 0.2455789122455789,
+      "grad_norm": 0.029193932190537453,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.9314,
+      "step": 46
+    },
+    {
+      "epoch": 0.2509175842509176,
+      "grad_norm": 0.027724456042051315,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.9312,
+      "step": 47
+    },
+    {
+      "epoch": 0.25625625625625625,
+      "grad_norm": 0.026069508865475655,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.9313,
+      "step": 48
+    },
+    {
+      "epoch": 0.2615949282615949,
+      "grad_norm": 0.026789134368300438,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.9321,
+      "step": 49
+    },
+    {
+      "epoch": 0.2669336002669336,
+      "grad_norm": 0.02489320933818817,
+      "learning_rate": 0.0,
+      "loss": 11.9326,
+      "step": 50
+    },
+    {
+      "epoch": 0.2669336002669336,
+      "eval_loss": 11.931137084960938,
+      "eval_runtime": 3.2883,
+      "eval_samples_per_second": 383.781,
+      "eval_steps_per_second": 48.049,
+      "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": 522224467968.0,
+  "total_flos": 1044123156480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null