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:e9ce9d7d556d944a13bc0a8b1174f5e9c38055f187effcca0ee8700db664fa8c
+oid sha256:8ecf41bc2b8271e27bfd5d339d6c7ee68051d72a674e6db2cf104e7c311c5b2e
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8e0c327a7267a4dec0845b5227f580e4aabf3478507a70b7a494cbf09946cfe
+oid sha256:e0d424354bf784c11e57c0750d50396efdd3646b1f3b14dd724d5d542be62df6
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b5a7c83cd196dc022f9b42452a20fb6a3cf11a02085927512dcd951ec15c556
+oid sha256:a1d6cb539e77a8d7a569ec46d32ca000c2152c02e278f90d096a3f1a307c6e00
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a8a167f3e7d986ec5cab2d5abf2f288a365c76aec0cad44c9720f6463757587
+oid sha256:d9b8e131e3057254e87cf89e0a50b80fbd61c756937a10c0f8fad89363db9fda
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b13dde4c8e3e89bb192b409bf9b5c12233b45b5b62194a7e46e6f547e079409
+oid sha256:8ee41d3c686e927266f15dbfb14b8917d743055b5713b8384e68f6e95b7de2ef
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a139921cbc946c293a69034987c6540381d9ee326168f4c396da67e9aa6a86f
+oid sha256:8a2bccdd3d374ffd59393ef928eec17ea6592724b002dcea2168fe086d15cdc7
 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": 0.0011129876365885139,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1597444089456869,
+  "best_metric": 0.0007530274451710284,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3194888178913738,
   "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": 114.948,
       "eval_steps_per_second": 14.382,
       "step": 25
+    },
+    {
+      "epoch": 0.16613418530351437,
+      "grad_norm": 0.07889246195554733,
+      "learning_rate": 5e-05,
+      "loss": 0.0019,
+      "step": 26
+    },
+    {
+      "epoch": 0.17252396166134185,
+      "grad_norm": 0.05853520333766937,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0016,
+      "step": 27
+    },
+    {
+      "epoch": 0.17891373801916932,
+      "grad_norm": 0.012233099900186062,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0006,
+      "step": 28
+    },
+    {
+      "epoch": 0.1853035143769968,
+      "grad_norm": 0.011350907385349274,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0005,
+      "step": 29
+    },
+    {
+      "epoch": 0.19169329073482427,
+      "grad_norm": 0.026074178516864777,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0007,
+      "step": 30
+    },
+    {
+      "epoch": 0.19808306709265175,
+      "grad_norm": 0.021880803629755974,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0003,
+      "step": 31
+    },
+    {
+      "epoch": 0.20447284345047922,
+      "grad_norm": 0.008851868100464344,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0003,
+      "step": 32
+    },
+    {
+      "epoch": 0.2108626198083067,
+      "grad_norm": 0.008047765120863914,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0002,
+      "step": 33
+    },
+    {
+      "epoch": 0.21725239616613418,
+      "grad_norm": 0.02266853302717209,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0006,
+      "step": 34
+    },
+    {
+      "epoch": 0.22364217252396165,
+      "grad_norm": 0.015060832723975182,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0005,
+      "step": 35
+    },
+    {
+      "epoch": 0.23003194888178913,
+      "grad_norm": 0.0252712219953537,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0003,
+      "step": 36
+    },
+    {
+      "epoch": 0.2364217252396166,
+      "grad_norm": 0.07228560000658035,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0007,
+      "step": 37
+    },
+    {
+      "epoch": 0.24281150159744408,
+      "grad_norm": 0.051049910485744476,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0009,
+      "step": 38
+    },
+    {
+      "epoch": 0.24920127795527156,
+      "grad_norm": 0.01329121831804514,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0007,
+      "step": 39
+    },
+    {
+      "epoch": 0.25559105431309903,
+      "grad_norm": 0.024605846032500267,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0008,
+      "step": 40
+    },
+    {
+      "epoch": 0.26198083067092653,
+      "grad_norm": 0.04892455041408539,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0007,
+      "step": 41
+    },
+    {
+      "epoch": 0.268370607028754,
+      "grad_norm": 0.008584716357290745,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0005,
+      "step": 42
+    },
+    {
+      "epoch": 0.2747603833865815,
+      "grad_norm": 0.023672640323638916,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0003,
+      "step": 43
+    },
+    {
+      "epoch": 0.28115015974440893,
+      "grad_norm": 0.06465290486812592,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0005,
+      "step": 44
+    },
+    {
+      "epoch": 0.28753993610223644,
+      "grad_norm": 0.022327011451125145,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0006,
+      "step": 45
+    },
+    {
+      "epoch": 0.2939297124600639,
+      "grad_norm": 0.05102255567908287,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0004,
+      "step": 46
+    },
+    {
+      "epoch": 0.3003194888178914,
+      "grad_norm": 0.0069334739819169044,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0002,
+      "step": 47
+    },
+    {
+      "epoch": 0.30670926517571884,
+      "grad_norm": 0.009662661701440811,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0004,
+      "step": 48
+    },
+    {
+      "epoch": 0.31309904153354634,
+      "grad_norm": 0.07340962439775467,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0021,
+      "step": 49
+    },
+    {
+      "epoch": 0.3194888178913738,
+      "grad_norm": 0.032447054982185364,
+      "learning_rate": 0.0,
+      "loss": 0.0014,
+      "step": 50
+    },
+    {
+      "epoch": 0.3194888178913738,
+      "eval_loss": 0.0007530274451710284,
+      "eval_runtime": 9.1809,
+      "eval_samples_per_second": 114.912,
+      "eval_steps_per_second": 14.378,
+      "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": 3.91521434075136e+16,
+  "total_flos": 7.83042868150272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null