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:cb6863e7149a82e1fffe0ae2d0b121eeb03d0b0680425eb096b05893eec15639
+oid sha256:ddd6f05c6b80301405981b9ee9f7b97a688e662484f7324b154607149df54289
 size 194563400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7498bbf81143c9274e3f09bf5a7b2362bc68b01a1a1ba35af3d3db87cf568a74
+oid sha256:c731b90927097abf4f0a61c11e92fdee04c41e727055e679e0c1a039d18f3b08
 size 389352298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40011a2ffd14dd9789e6c6bb26d1472e3d56b4f30b369bbf3f6749bf7c105472
+oid sha256:29079388683279da5c852a714ec984280aa673772ea2978a5ef8fcc6bf0741ee
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda32176a07cf836bb39f2e5f0112184b6f1a97ce3a8eec1128301322bf539e4
+oid sha256:e27e25f0863b99fdb8e942c1ca8d1d2aa812f3c80ae430db0ff2e89b61abae6e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4ad24a6b4c454446ce854a5f5022696d0e3894b78896792b2a67fc77f7e7919
+oid sha256:54e06a2ac93befcc3d41da9f2f5d45b103d9523cb39b6e606945724914d5ec7b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c134ca3e29faddb4e04e8002c619a486cb7bb1f909a2509d5732d3dd4828fe4c
+oid sha256:c08e8a6a55ed6b094b94be16a67c70975779dde49c9537ec55014d2478ded00d
 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": 0.38506779074668884,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03388681802778719,
+  "best_metric": 0.34878861904144287,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06777363605557438,
   "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": 49.209,
       "eval_steps_per_second": 6.159,
       "step": 25
+    },
+    {
+      "epoch": 0.03524229074889868,
+      "grad_norm": 1.72467839717865,
+      "learning_rate": 5e-05,
+      "loss": 0.8527,
+      "step": 26
+    },
+    {
+      "epoch": 0.03659776347001017,
+      "grad_norm": 1.1683018207550049,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5788,
+      "step": 27
+    },
+    {
+      "epoch": 0.037953236191121655,
+      "grad_norm": 0.9099482297897339,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5694,
+      "step": 28
+    },
+    {
+      "epoch": 0.03930870891223314,
+      "grad_norm": 0.6733741164207458,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4685,
+      "step": 29
+    },
+    {
+      "epoch": 0.04066418163334463,
+      "grad_norm": 0.49673986434936523,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4127,
+      "step": 30
+    },
+    {
+      "epoch": 0.042019654354456114,
+      "grad_norm": 0.6410134434700012,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4818,
+      "step": 31
+    },
+    {
+      "epoch": 0.04337512707556761,
+      "grad_norm": 0.5478073358535767,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.4067,
+      "step": 32
+    },
+    {
+      "epoch": 0.044730599796679094,
+      "grad_norm": 0.5715470910072327,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.3379,
+      "step": 33
+    },
+    {
+      "epoch": 0.04608607251779058,
+      "grad_norm": 0.12999820709228516,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0825,
+      "step": 34
+    },
+    {
+      "epoch": 0.047441545238902066,
+      "grad_norm": 0.07671059668064117,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0155,
+      "step": 35
+    },
+    {
+      "epoch": 0.04879701796001355,
+      "grad_norm": 0.041638992726802826,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.019,
+      "step": 36
+    },
+    {
+      "epoch": 0.05015249068112504,
+      "grad_norm": 0.3261185884475708,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3185,
+      "step": 37
+    },
+    {
+      "epoch": 0.05150796340223653,
+      "grad_norm": 0.9712899923324585,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6303,
+      "step": 38
+    },
+    {
+      "epoch": 0.05286343612334802,
+      "grad_norm": 0.6599809527397156,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6388,
+      "step": 39
+    },
+    {
+      "epoch": 0.054218908844459505,
+      "grad_norm": 0.6416831016540527,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5922,
+      "step": 40
+    },
+    {
+      "epoch": 0.05557438156557099,
+      "grad_norm": 0.5625379681587219,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.4985,
+      "step": 41
+    },
+    {
+      "epoch": 0.05692985428668248,
+      "grad_norm": 0.5052372813224792,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4821,
+      "step": 42
+    },
+    {
+      "epoch": 0.058285327007793965,
+      "grad_norm": 0.48581060767173767,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4703,
+      "step": 43
+    },
+    {
+      "epoch": 0.05964079972890546,
+      "grad_norm": 0.43107783794403076,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.381,
+      "step": 44
+    },
+    {
+      "epoch": 0.060996272450016945,
+      "grad_norm": 0.43108266592025757,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.3847,
+      "step": 45
+    },
+    {
+      "epoch": 0.06235174517112843,
+      "grad_norm": 0.34979385137557983,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.276,
+      "step": 46
+    },
+    {
+      "epoch": 0.06370721789223992,
+      "grad_norm": 0.03745098039507866,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0183,
+      "step": 47
+    },
+    {
+      "epoch": 0.0650626906133514,
+      "grad_norm": 0.03093818388879299,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0133,
+      "step": 48
+    },
+    {
+      "epoch": 0.06641816333446289,
+      "grad_norm": 0.0694834515452385,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0597,
+      "step": 49
+    },
+    {
+      "epoch": 0.06777363605557438,
+      "grad_norm": 0.46889737248420715,
+      "learning_rate": 0.0,
+      "loss": 0.3722,
+      "step": 50
+    },
+    {
+      "epoch": 0.06777363605557438,
+      "eval_loss": 0.34878861904144287,
+      "eval_runtime": 100.9258,
+      "eval_samples_per_second": 49.244,
+      "eval_steps_per_second": 6.163,
+      "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": 1.1718929936285696e+17,
+  "total_flos": 2.3416719345608294e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null