Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58561f88933f8131c5ca903f01ae22739189f02e94f2350104b4d65af2d6100a
+oid sha256:0f43e00ccdd570f996bebebe8b2df42746b006b27e164cf95069af1efcefed49
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:139a10988a6e9ca9bacd1fbba43e97ac63b01a98d7a7a611197ff07146ccf89f
+oid sha256:ff891972c879a6ee2d3fe086e2b4fee1e336bf8069802ee939a1a19ac2b928e7
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6571f36b4d979b6e9cb819eb60ae0b75616a9a07a5e4fa7bb2451b51fe35227
+oid sha256:01901992d4bb69d254125cb1af3b1776723e7950e1b88d032a1cf8ee0fdf7b98
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcbefdb9764827550f137f99765389929e461b2c851ab1f84bf24db0b639586d
+oid sha256:b958c31e602322deaad73d4f2ffb998154c4640b797d3bf7f3ed1351f37fed3c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ba5989efe0eeca6b81e951cd3d6b221785cdda1698c5c74f6382bce3da828ad
+oid sha256:3367a6ecee3eedc1b347bfddefe3f1ce53e399fe510e97cbbd2d037118c8a9f5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d4d3b3b9d7e81c2b3b3be49098de754260746b225bed26f541724022dbebc3
+oid sha256:9f65e1fae122c2b785d2b697e9ef0a132ac857e0d2767009114aed0ca96677cd
 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": 1.424196720123291,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006994474365251451,
+  "best_metric": 1.3699287176132202,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.013988948730502902,
   "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": 83.108,
       "eval_steps_per_second": 10.389,
       "step": 25
+    },
+    {
+      "epoch": 0.007274253339861509,
+      "grad_norm": 0.4121569097042084,
+      "learning_rate": 5e-05,
+      "loss": 2.0963,
+      "step": 26
+    },
+    {
+      "epoch": 0.007554032314471567,
+      "grad_norm": 1.4843387603759766,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9371,
+      "step": 27
+    },
+    {
+      "epoch": 0.007833811289081626,
+      "grad_norm": 0.6254419684410095,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.6501,
+      "step": 28
+    },
+    {
+      "epoch": 0.008113590263691683,
+      "grad_norm": 0.8778519034385681,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.8644,
+      "step": 29
+    },
+    {
+      "epoch": 0.008393369238301742,
+      "grad_norm": 0.7816627025604248,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.0246,
+      "step": 30
+    },
+    {
+      "epoch": 0.0086731482129118,
+      "grad_norm": 0.9954394698143005,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.1687,
+      "step": 31
+    },
+    {
+      "epoch": 0.008952927187521859,
+      "grad_norm": 0.9548348188400269,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.219,
+      "step": 32
+    },
+    {
+      "epoch": 0.009232706162131916,
+      "grad_norm": 1.2620952129364014,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.1794,
+      "step": 33
+    },
+    {
+      "epoch": 0.009512485136741973,
+      "grad_norm": 1.0139468908309937,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.2746,
+      "step": 34
+    },
+    {
+      "epoch": 0.009792264111352032,
+      "grad_norm": 1.1678214073181152,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.5503,
+      "step": 35
+    },
+    {
+      "epoch": 0.01007204308596209,
+      "grad_norm": 1.3892196416854858,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.7002,
+      "step": 36
+    },
+    {
+      "epoch": 0.010351822060572148,
+      "grad_norm": 1.8984113931655884,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.9451,
+      "step": 37
+    },
+    {
+      "epoch": 0.010631601035182205,
+      "grad_norm": 0.5597782135009766,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.2111,
+      "step": 38
+    },
+    {
+      "epoch": 0.010911380009792264,
+      "grad_norm": 0.8374670743942261,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.7816,
+      "step": 39
+    },
+    {
+      "epoch": 0.011191158984402321,
+      "grad_norm": 0.7428615689277649,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.6842,
+      "step": 40
+    },
+    {
+      "epoch": 0.01147093795901238,
+      "grad_norm": 0.6815183758735657,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.2802,
+      "step": 41
+    },
+    {
+      "epoch": 0.011750716933622438,
+      "grad_norm": 0.8600313067436218,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.6241,
+      "step": 42
+    },
+    {
+      "epoch": 0.012030495908232497,
+      "grad_norm": 0.8320652842521667,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.5642,
+      "step": 43
+    },
+    {
+      "epoch": 0.012310274882842554,
+      "grad_norm": 0.804832398891449,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2987,
+      "step": 44
+    },
+    {
+      "epoch": 0.012590053857452613,
+      "grad_norm": 0.8696397542953491,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.4127,
+      "step": 45
+    },
+    {
+      "epoch": 0.01286983283206267,
+      "grad_norm": 1.23816978931427,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.2822,
+      "step": 46
+    },
+    {
+      "epoch": 0.013149611806672729,
+      "grad_norm": 1.4849238395690918,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.195,
+      "step": 47
+    },
+    {
+      "epoch": 0.013429390781282786,
+      "grad_norm": 1.1128456592559814,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.6807,
+      "step": 48
+    },
+    {
+      "epoch": 0.013709169755892845,
+      "grad_norm": 1.8592028617858887,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.7832,
+      "step": 49
+    },
+    {
+      "epoch": 0.013988948730502902,
+      "grad_norm": 2.0527429580688477,
+      "learning_rate": 0.0,
+      "loss": 1.8282,
+      "step": 50
+    },
+    {
+      "epoch": 0.013988948730502902,
+      "eval_loss": 1.3699287176132202,
+      "eval_runtime": 289.4463,
+      "eval_samples_per_second": 83.193,
+      "eval_steps_per_second": 10.399,
+      "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": 5.367213800292352e+16,
+  "total_flos": 1.0741049715379405e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null