Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a130cf097c25be3bc527d9597992ed1ae55a3ecff04738fd9bd39469f5474c7
+oid sha256:f8c2981a6d0acdb6a9f33e868656d33c8edd890e867aa80d9e050b74bda57fea
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be31adecbd50dbeaec55c5f329b845deef64fc69d89bdc8a1c2cc7a164cfdae5
+oid sha256:3456bcd455a85f05fadbf036f85295fa55ba86c65213ca7be2e765aa44abf73a
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89050bd4146c0da55942cdeec78ddd42bc376b83d8d41f50a96c7cd3e96812b8
+oid sha256:5346b2fcacfcede118e119a7779fe56a80aab626d410d6ea41dc163d233048cc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a232a966a37b24277b88cdc2719c0b87f55a371450a18732704f534afbf32cfd
+oid sha256:8280d2baacb3a3f336bc60e0922d43f23fc81e348d244bce634231d74609d8ba
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d64f0a30e03af600f1fded10f4f17cd89cc941f408ea56299377e32de80f72eb
+oid sha256:5d23bec2d2ec5294458693d914b3a162540a67da732cf0758bd3173ce17cb14e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:311d46903545a4647139933a06066b02b5259b55f2074857e81e4f98e3f4f273
+oid sha256:31fd7fafd1cb9bc086b5bda24049ea808651f18ec7472122ad94e9e6818baed2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5c305e4a92be904895c02f0f0a1da666e6e7555f6043a8f089990c87f4ce88
+oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6505181193351746,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.20217336365933788,
+  "best_metric": 0.6258954405784607,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.40434672731867577,
   "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": 14.32,
       "eval_steps_per_second": 3.723,
       "step": 25
+    },
+    {
+      "epoch": 0.2102602982057114,
+      "grad_norm": 0.5990607142448425,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 0.7604,
+      "step": 26
+    },
+    {
+      "epoch": 0.21834723275208492,
+      "grad_norm": 0.5680568218231201,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 0.7052,
+      "step": 27
+    },
+    {
+      "epoch": 0.22643416729845842,
+      "grad_norm": 0.4318358302116394,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 0.7392,
+      "step": 28
+    },
+    {
+      "epoch": 0.23452110184483194,
+      "grad_norm": 0.4534890353679657,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 0.7612,
+      "step": 29
+    },
+    {
+      "epoch": 0.24260803639120546,
+      "grad_norm": 0.41572484374046326,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 0.6753,
+      "step": 30
+    },
+    {
+      "epoch": 0.250694970937579,
+      "grad_norm": 0.391692578792572,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 0.7202,
+      "step": 31
+    },
+    {
+      "epoch": 0.25878190548395247,
+      "grad_norm": 0.4226691722869873,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 0.6996,
+      "step": 32
+    },
+    {
+      "epoch": 0.266868840030326,
+      "grad_norm": 0.43875357508659363,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 0.7064,
+      "step": 33
+    },
+    {
+      "epoch": 0.2749557745766995,
+      "grad_norm": 0.3757180869579315,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 0.6694,
+      "step": 34
+    },
+    {
+      "epoch": 0.28304270912307306,
+      "grad_norm": 0.41616472601890564,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 0.6895,
+      "step": 35
+    },
+    {
+      "epoch": 0.29112964366944655,
+      "grad_norm": 0.4041263461112976,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 0.6098,
+      "step": 36
+    },
+    {
+      "epoch": 0.29921657821582004,
+      "grad_norm": 0.39486125111579895,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 0.6039,
+      "step": 37
+    },
+    {
+      "epoch": 0.3073035127621936,
+      "grad_norm": 0.35433000326156616,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 0.5956,
+      "step": 38
+    },
+    {
+      "epoch": 0.3153904473085671,
+      "grad_norm": 0.3867066204547882,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 0.6729,
+      "step": 39
+    },
+    {
+      "epoch": 0.3234773818549406,
+      "grad_norm": 0.40773889422416687,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 0.6722,
+      "step": 40
+    },
+    {
+      "epoch": 0.3315643164013141,
+      "grad_norm": 0.36118409037590027,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 0.6863,
+      "step": 41
+    },
+    {
+      "epoch": 0.33965125094768767,
+      "grad_norm": 0.42860254645347595,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 0.7423,
+      "step": 42
+    },
+    {
+      "epoch": 0.34773818549406116,
+      "grad_norm": 0.3781806528568268,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 0.6734,
+      "step": 43
+    },
+    {
+      "epoch": 0.35582512004043465,
+      "grad_norm": 0.45583733916282654,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 0.7366,
+      "step": 44
+    },
+    {
+      "epoch": 0.3639120545868082,
+      "grad_norm": 0.42888590693473816,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 0.6791,
+      "step": 45
+    },
+    {
+      "epoch": 0.3719989891331817,
+      "grad_norm": 0.5353739261627197,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 0.6581,
+      "step": 46
+    },
+    {
+      "epoch": 0.38008592367955524,
+      "grad_norm": 0.6451358199119568,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 0.6297,
+      "step": 47
+    },
+    {
+      "epoch": 0.38817285822592873,
+      "grad_norm": 0.4006296396255493,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 0.614,
+      "step": 48
+    },
+    {
+      "epoch": 0.3962597927723022,
+      "grad_norm": 0.4140074849128723,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.5914,
+      "step": 49
+    },
+    {
+      "epoch": 0.40434672731867577,
+      "grad_norm": 0.3834184408187866,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 0.5771,
+      "step": 50
+    },
+    {
+      "epoch": 0.40434672731867577,
+      "eval_loss": 0.6258954405784607,
+      "eval_runtime": 3.5135,
+      "eval_samples_per_second": 14.231,
+      "eval_steps_per_second": 3.7,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null