Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9630f20ea778517de9e3be4ddca3d636721a37047c24f98e8d5036090f90959c
+oid sha256:9ab27626ae26f47b3704e86db9ef5cd730e011a488808e6e2f4cea837d0a5540
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04fa559c72deda0fbca1e49a43310c9fd8bc9ebdc287a6bcb62bbabe019765a7
+oid sha256:d1f23ffce9b0b9cd6c2cff0a380925d6749391ed32e12aa9899ffde20e17e463
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f26f07fe440aed428401b092bb09779eae5b2b47b84a7868af2bb8f9f386fa8
+oid sha256:78baf284e13a0eb4da5d5ca164d3d024ea209b44bd36e6db4179c8b2e26227f5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7590d822fa13826d2873d9b2de3a2a6ceb4d63ccd876c930c897e78cd47d18e4
+oid sha256:befd70b5118d59bc2ad45f50ea0047ed817178d79f0b43cb67747a89f465fed7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5372a4f6edc51db5e2a19febeb2af2fe788864edd02dc9ce3813f479c57eabe9
+oid sha256:3c1c85ec4389879112b83062bb80f70789054fb176e2c31bafb179ea9de5cb72
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf95aca4515233d49fd976581dc479c8f7873ce6f9404c8a96841c78824e7e5e
+oid sha256:c81dddd4266a10969a85ac0913b38c52b2b4d4eb0d56e2ea5a58e1efb15736d2
 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": 0.25045526027679443,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08462026655383964,
+  "best_metric": 0.23640887439250946,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.16924053310767928,
   "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": 29.478,
       "eval_steps_per_second": 3.688,
       "step": 25
+    },
+    {
+      "epoch": 0.08800507721599322,
+      "grad_norm": 15.82603645324707,
+      "learning_rate": 5e-05,
+      "loss": 0.2537,
+      "step": 26
+    },
+    {
+      "epoch": 0.09138988787814682,
+      "grad_norm": 10.225655555725098,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.2352,
+      "step": 27
+    },
+    {
+      "epoch": 0.0947746985403004,
+      "grad_norm": 4.388094902038574,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2326,
+      "step": 28
+    },
+    {
+      "epoch": 0.09815950920245399,
+      "grad_norm": 12.566032409667969,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.2413,
+      "step": 29
+    },
+    {
+      "epoch": 0.10154431986460757,
+      "grad_norm": 11.014392852783203,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2343,
+      "step": 30
+    },
+    {
+      "epoch": 0.10492913052676116,
+      "grad_norm": 12.923883438110352,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2361,
+      "step": 31
+    },
+    {
+      "epoch": 0.10831394118891474,
+      "grad_norm": 6.697196006774902,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.239,
+      "step": 32
+    },
+    {
+      "epoch": 0.11169875185106833,
+      "grad_norm": 9.340826034545898,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.2403,
+      "step": 33
+    },
+    {
+      "epoch": 0.11508356251322191,
+      "grad_norm": 9.99615478515625,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2349,
+      "step": 34
+    },
+    {
+      "epoch": 0.11846837317537551,
+      "grad_norm": 16.68816566467285,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2514,
+      "step": 35
+    },
+    {
+      "epoch": 0.12185318383752909,
+      "grad_norm": 17.61069679260254,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.2475,
+      "step": 36
+    },
+    {
+      "epoch": 0.12523799449968268,
+      "grad_norm": 8.036877632141113,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.2313,
+      "step": 37
+    },
+    {
+      "epoch": 0.12862280516183627,
+      "grad_norm": 13.201481819152832,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2361,
+      "step": 38
+    },
+    {
+      "epoch": 0.13200761582398984,
+      "grad_norm": 15.014155387878418,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2495,
+      "step": 39
+    },
+    {
+      "epoch": 0.13539242648614344,
+      "grad_norm": 17.984846115112305,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2513,
+      "step": 40
+    },
+    {
+      "epoch": 0.138777237148297,
+      "grad_norm": 10.511441230773926,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2369,
+      "step": 41
+    },
+    {
+      "epoch": 0.1421620478104506,
+      "grad_norm": 4.850277423858643,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2425,
+      "step": 42
+    },
+    {
+      "epoch": 0.14554685847260418,
+      "grad_norm": 11.52924633026123,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2344,
+      "step": 43
+    },
+    {
+      "epoch": 0.14893166913475778,
+      "grad_norm": 6.321855068206787,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2327,
+      "step": 44
+    },
+    {
+      "epoch": 0.15231647979691135,
+      "grad_norm": 8.48495101928711,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.2347,
+      "step": 45
+    },
+    {
+      "epoch": 0.15570129045906494,
+      "grad_norm": 11.105454444885254,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2467,
+      "step": 46
+    },
+    {
+      "epoch": 0.15908610112121854,
+      "grad_norm": 11.16732406616211,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.2401,
+      "step": 47
+    },
+    {
+      "epoch": 0.1624709117833721,
+      "grad_norm": 6.619392395019531,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2315,
+      "step": 48
+    },
+    {
+      "epoch": 0.1658557224455257,
+      "grad_norm": 16.427457809448242,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2402,
+      "step": 49
+    },
+    {
+      "epoch": 0.16924053310767928,
+      "grad_norm": 4.940228462219238,
+      "learning_rate": 0.0,
+      "loss": 0.2185,
+      "step": 50
+    },
+    {
+      "epoch": 0.16924053310767928,
+      "eval_loss": 0.23640887439250946,
+      "eval_runtime": 67.5292,
+      "eval_samples_per_second": 29.469,
+      "eval_steps_per_second": 3.687,
+      "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": 1.483568811343872e+17,
+  "total_flos": 2.967137622687744e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null