Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:995d43ce16241ef0a7f4f311c4f85b62bae0c579f73a5e6429bbda551835094b
+oid sha256:2efbf9ab7ca4b17d31a4c0ce915a5d62069e4a44c894ed38e964a7c6e6b7e558
 size 119975656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1656a5e16d4397e534d820f7cbbb66b0372bc3f779fa008b69c868807779187e
+oid sha256:5cc60eb20f6ede9cc6c560d1376375210b3005ac4a45c7f2e3c9a0fef1f790f2
 size 240145026

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acafed5bd1083cde4535b730d1ffe50eebdd3f30f73e484d4666cdeb5426fed9
+oid sha256:6cc84fbf28e2cb61e08e829fab7e9fa89f1af474bd0e9f5dcbbdbac7ce16b756
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef7ecf65d7629bb5290e2eed5c1de43a6e1fc77db928cb2eba70bd444d096d39
+oid sha256:42c38421c527e78fe14fab9965b416ae50b7a55973326f9d4b21242f61597bc8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdcc15dd5cf6e0369fbf95eb399b910f23a11835b4a70acc12afa0778d3bb987
+oid sha256:28aff319f724b793a9786ed165b3c2b72d61a96a36b142eec5d1ccc79e771346
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a31e20c5be3ceb3e856878ac3ec05b7260539d063a82e197b4dd7fd7a9823334
+oid sha256:5a4c6c16cb4cd5277556f41dcf2eb481410cc17d4a03aaf1a45974505d18303f
 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": 0.6936268210411072,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0672834314550042,
+  "best_metric": 0.6819216012954712,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1345668629100084,
   "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": 92.391,
       "eval_steps_per_second": 11.549,
       "step": 25
+    },
+    {
+      "epoch": 0.06997476871320438,
+      "grad_norm": 0.13176329433918,
+      "learning_rate": 5e-05,
+      "loss": 0.6981,
+      "step": 26
+    },
+    {
+      "epoch": 0.07266610597140453,
+      "grad_norm": 0.14322075247764587,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.7009,
+      "step": 27
+    },
+    {
+      "epoch": 0.0753574432296047,
+      "grad_norm": 0.13809622824192047,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.6822,
+      "step": 28
+    },
+    {
+      "epoch": 0.07804878048780488,
+      "grad_norm": 0.1446419507265091,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7102,
+      "step": 29
+    },
+    {
+      "epoch": 0.08074011774600505,
+      "grad_norm": 0.1410524994134903,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7431,
+      "step": 30
+    },
+    {
+      "epoch": 0.08343145500420522,
+      "grad_norm": 0.13376262784004211,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.6725,
+      "step": 31
+    },
+    {
+      "epoch": 0.08612279226240538,
+      "grad_norm": 0.14629241824150085,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.6891,
+      "step": 32
+    },
+    {
+      "epoch": 0.08881412952060555,
+      "grad_norm": 0.1449364721775055,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.71,
+      "step": 33
+    },
+    {
+      "epoch": 0.09150546677880572,
+      "grad_norm": 0.14771750569343567,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6955,
+      "step": 34
+    },
+    {
+      "epoch": 0.0941968040370059,
+      "grad_norm": 0.1390102356672287,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.6994,
+      "step": 35
+    },
+    {
+      "epoch": 0.09688814129520605,
+      "grad_norm": 0.1551445871591568,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7036,
+      "step": 36
+    },
+    {
+      "epoch": 0.09957947855340622,
+      "grad_norm": 0.15887659788131714,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.6652,
+      "step": 37
+    },
+    {
+      "epoch": 0.1022708158116064,
+      "grad_norm": 0.12231530994176865,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6527,
+      "step": 38
+    },
+    {
+      "epoch": 0.10496215306980657,
+      "grad_norm": 0.11615988612174988,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6803,
+      "step": 39
+    },
+    {
+      "epoch": 0.10765349032800672,
+      "grad_norm": 0.12420918047428131,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7399,
+      "step": 40
+    },
+    {
+      "epoch": 0.1103448275862069,
+      "grad_norm": 0.12053780257701874,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7104,
+      "step": 41
+    },
+    {
+      "epoch": 0.11303616484440707,
+      "grad_norm": 0.12968841195106506,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7034,
+      "step": 42
+    },
+    {
+      "epoch": 0.11572750210260724,
+      "grad_norm": 0.12242884933948517,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.7071,
+      "step": 43
+    },
+    {
+      "epoch": 0.1184188393608074,
+      "grad_norm": 0.13350559771060944,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7081,
+      "step": 44
+    },
+    {
+      "epoch": 0.12111017661900757,
+      "grad_norm": 0.1338701695203781,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6732,
+      "step": 45
+    },
+    {
+      "epoch": 0.12380151387720774,
+      "grad_norm": 0.13425399363040924,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6586,
+      "step": 46
+    },
+    {
+      "epoch": 0.1264928511354079,
+      "grad_norm": 0.13831543922424316,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7092,
+      "step": 47
+    },
+    {
+      "epoch": 0.12918418839360807,
+      "grad_norm": 0.1482115238904953,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7062,
+      "step": 48
+    },
+    {
+      "epoch": 0.13187552565180824,
+      "grad_norm": 0.15125855803489685,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.6937,
+      "step": 49
+    },
+    {
+      "epoch": 0.1345668629100084,
+      "grad_norm": 0.19473306834697723,
+      "learning_rate": 0.0,
+      "loss": 0.6502,
+      "step": 50
+    },
+    {
+      "epoch": 0.1345668629100084,
+      "eval_loss": 0.6819216012954712,
+      "eval_runtime": 28.1846,
+      "eval_samples_per_second": 88.843,
+      "eval_steps_per_second": 11.105,
+      "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": 5.227878001357619e+16,
+  "total_flos": 1.0452536871039795e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null