Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7429bb8f46095ae76f3c0b5dcddaed326a6378e86e760812e3005b3577f716af
+oid sha256:fb5c8b8408c70824a93ebd516e9dda3e560bb90490441ed85aee0de8fe71b578
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e51b65662080c4ccbb6aa073985909e02ebdc161692002f5fdbbd49c0b512fbf
+oid sha256:5bdb0571136ef8c513868d048502e7989c2388081b5f7e2e1d3383a51ec148be
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:decb4994fb99760e5782c92c17638680d5b1564b3ab5f3a06c9743426d7dea31
+oid sha256:6234f755a3a9d3c277d676efeccec449266704af4cf5d9d2abba5e78c2a8b03d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a0ed30041e186a908a4e945a625812f32a8d1be40a403189137cf720b69787
+oid sha256:22abbd129d577b0046935f5476206737937fc728af5b3a76ff5786cf8d635ecc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9c33165936ef0f5c61fe4aac187e7e1ac3a2d1d08f18ca97b0036b0b1219314
+oid sha256:68028256b92df8c57572ea42262ec233b5cef8f2cc3a5c0fe0832a8d6492fcf6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56819b2ff03e421d4089b4ebff3662c5169d7258f284d301da8a1c2270ab23a0
+oid sha256:0f3d979410d3bcaa322ac1d0170ea013551b375f593197757d3c543db32175b2
 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": 2.6552484035491943,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.174140182847192,
+  "best_metric": 2.5222702026367188,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.348280365694384,
   "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": 24.29,
       "eval_steps_per_second": 3.039,
       "step": 25
+    },
+    {
+      "epoch": 0.18110579016107967,
+      "grad_norm": 10.78183650970459,
+      "learning_rate": 5e-05,
+      "loss": 2.7925,
+      "step": 26
+    },
+    {
+      "epoch": 0.18807139747496734,
+      "grad_norm": 10.190346717834473,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.4493,
+      "step": 27
+    },
+    {
+      "epoch": 0.19503700478885502,
+      "grad_norm": 11.52568244934082,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.3815,
+      "step": 28
+    },
+    {
+      "epoch": 0.2020026121027427,
+      "grad_norm": 7.325039863586426,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.3123,
+      "step": 29
+    },
+    {
+      "epoch": 0.20896821941663038,
+      "grad_norm": 6.588929176330566,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.3014,
+      "step": 30
+    },
+    {
+      "epoch": 0.21593382673051806,
+      "grad_norm": 7.719417572021484,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.2622,
+      "step": 31
+    },
+    {
+      "epoch": 0.22289943404440574,
+      "grad_norm": 9.654048919677734,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.2692,
+      "step": 32
+    },
+    {
+      "epoch": 0.22986504135829341,
+      "grad_norm": 9.051423072814941,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.3102,
+      "step": 33
+    },
+    {
+      "epoch": 0.2368306486721811,
+      "grad_norm": 8.692105293273926,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.3599,
+      "step": 34
+    },
+    {
+      "epoch": 0.24379625598606877,
+      "grad_norm": 19.115230560302734,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.9567,
+      "step": 35
+    },
+    {
+      "epoch": 0.2507618632999565,
+      "grad_norm": 26.625967025756836,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.6196,
+      "step": 36
+    },
+    {
+      "epoch": 0.25772747061384416,
+      "grad_norm": 24.278709411621094,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.0971,
+      "step": 37
+    },
+    {
+      "epoch": 0.26469307792773183,
+      "grad_norm": 18.138113021850586,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.3459,
+      "step": 38
+    },
+    {
+      "epoch": 0.2716586852416195,
+      "grad_norm": 7.01446008682251,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.5923,
+      "step": 39
+    },
+    {
+      "epoch": 0.2786242925555072,
+      "grad_norm": 5.951314926147461,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.3039,
+      "step": 40
+    },
+    {
+      "epoch": 0.28558989986939487,
+      "grad_norm": 5.891165256500244,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.2985,
+      "step": 41
+    },
+    {
+      "epoch": 0.29255550718328255,
+      "grad_norm": 6.349960803985596,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.3085,
+      "step": 42
+    },
+    {
+      "epoch": 0.2995211144971702,
+      "grad_norm": 7.006208896636963,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.2457,
+      "step": 43
+    },
+    {
+      "epoch": 0.3064867218110579,
+      "grad_norm": 6.453885555267334,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.1739,
+      "step": 44
+    },
+    {
+      "epoch": 0.3134523291249456,
+      "grad_norm": 7.156106948852539,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.2258,
+      "step": 45
+    },
+    {
+      "epoch": 0.32041793643883326,
+      "grad_norm": 9.0035982131958,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.2745,
+      "step": 46
+    },
+    {
+      "epoch": 0.32738354375272094,
+      "grad_norm": 15.360855102539062,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.721,
+      "step": 47
+    },
+    {
+      "epoch": 0.3343491510666086,
+      "grad_norm": 18.129810333251953,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.7609,
+      "step": 48
+    },
+    {
+      "epoch": 0.3413147583804963,
+      "grad_norm": 22.803747177124023,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.5381,
+      "step": 49
+    },
+    {
+      "epoch": 0.348280365694384,
+      "grad_norm": 27.541250228881836,
+      "learning_rate": 0.0,
+      "loss": 3.4004,
+      "step": 50
+    },
+    {
+      "epoch": 0.348280365694384,
+      "eval_loss": 2.5222702026367188,
+      "eval_runtime": 39.798,
+      "eval_samples_per_second": 24.298,
+      "eval_steps_per_second": 3.04,
+      "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": 2.629578157719552e+17,
+  "total_flos": 5.259156315439104e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null