Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cbb2db5c241a4553aa1fecfe60ceca22d6083bd9140b66a530b6781b682517e
+oid sha256:8af414ea4566ce9e557b07e5c418d7c9ff37d01c29d557bde538ed5c255c733c
 size 445688440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:582adbaeb4e63b43da432aa9342338950ae288202a1f5bc8eb34b806ba72c792
+oid sha256:027352818ad370e4f115af586e5d2b57b283031d240b62934785e50c6c4e27f9
 size 891559354

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98bed804501c83a443212e698c81e2f59ae0593a94cbdae7c3c0926caa0ddda1
+oid sha256:d210f1b4508e0b14718aee8b474a75ef33e570d2742ab3213d64f0c8d649c4d0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f894f3bd0e6a7480a458b8103fd23e2f686650d9c5c430b236007af640eab3
+oid sha256:3eefb425294e5b1fb3776d7739e56463038021f05e6bdb62010a56abbef2a7d5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d49ee717dd8279a6e72085f7bf4733c9edf8d69e2fa0e890fbad97bee16a7720
+oid sha256:486130ae337c3a862a90c41b0ef19134915cd67ce9f9cc4459bdbfb9d2b1a8e2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ea27066bf16d8be6a42b4d79014f645d6346e018cc0dfd87577f4cd12227571
+oid sha256:8e04d7b5c25e34a533abb24d633d6127ac51ab955d6bdabfdb43138f75172de6
 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": 1.7844452857971191,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.039012971813127864,
+  "best_metric": 1.713279128074646,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.07802594362625573,
   "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": 15.185,
       "eval_steps_per_second": 1.899,
       "step": 25
+    },
+    {
+      "epoch": 0.04057349068565298,
+      "grad_norm": 11.710362434387207,
+      "learning_rate": 5e-05,
+      "loss": 2.1715,
+      "step": 26
+    },
+    {
+      "epoch": 0.042134009558178094,
+      "grad_norm": 14.576261520385742,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.0575,
+      "step": 27
+    },
+    {
+      "epoch": 0.043694528430703206,
+      "grad_norm": 13.412975311279297,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.9133,
+      "step": 28
+    },
+    {
+      "epoch": 0.045255047303228324,
+      "grad_norm": 11.340127944946289,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.819,
+      "step": 29
+    },
+    {
+      "epoch": 0.046815566175753436,
+      "grad_norm": 11.435134887695312,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.8139,
+      "step": 30
+    },
+    {
+      "epoch": 0.048376085048278554,
+      "grad_norm": 10.115267753601074,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.7239,
+      "step": 31
+    },
+    {
+      "epoch": 0.049936603920803666,
+      "grad_norm": 7.939040660858154,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.5591,
+      "step": 32
+    },
+    {
+      "epoch": 0.051497122793328784,
+      "grad_norm": 8.323566436767578,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.5233,
+      "step": 33
+    },
+    {
+      "epoch": 0.053057641665853895,
+      "grad_norm": 8.962291717529297,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.6057,
+      "step": 34
+    },
+    {
+      "epoch": 0.054618160538379014,
+      "grad_norm": 11.388747215270996,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.3288,
+      "step": 35
+    },
+    {
+      "epoch": 0.056178679410904125,
+      "grad_norm": 9.159733772277832,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.467,
+      "step": 36
+    },
+    {
+      "epoch": 0.05773919828342924,
+      "grad_norm": 18.99442481994629,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.8765,
+      "step": 37
+    },
+    {
+      "epoch": 0.059299717155954355,
+      "grad_norm": 25.547096252441406,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.1997,
+      "step": 38
+    },
+    {
+      "epoch": 0.06086023602847947,
+      "grad_norm": 7.026412487030029,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.0025,
+      "step": 39
+    },
+    {
+      "epoch": 0.062420754901004585,
+      "grad_norm": 7.772118091583252,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.0808,
+      "step": 40
+    },
+    {
+      "epoch": 0.0639812737735297,
+      "grad_norm": 6.68425989151001,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.8221,
+      "step": 41
+    },
+    {
+      "epoch": 0.06554179264605481,
+      "grad_norm": 6.783787250518799,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.8117,
+      "step": 42
+    },
+    {
+      "epoch": 0.06710231151857993,
+      "grad_norm": 8.404589653015137,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.8148,
+      "step": 43
+    },
+    {
+      "epoch": 0.06866283039110505,
+      "grad_norm": 6.892530918121338,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.6587,
+      "step": 44
+    },
+    {
+      "epoch": 0.07022334926363016,
+      "grad_norm": 6.792155742645264,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.6503,
+      "step": 45
+    },
+    {
+      "epoch": 0.07178386813615527,
+      "grad_norm": 8.016270637512207,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.515,
+      "step": 46
+    },
+    {
+      "epoch": 0.07334438700868039,
+      "grad_norm": 10.944890975952148,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.457,
+      "step": 47
+    },
+    {
+      "epoch": 0.0749049058812055,
+      "grad_norm": 9.899993896484375,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.4708,
+      "step": 48
+    },
+    {
+      "epoch": 0.07646542475373061,
+      "grad_norm": 12.46395492553711,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.5409,
+      "step": 49
+    },
+    {
+      "epoch": 0.07802594362625573,
+      "grad_norm": 30.2358341217041,
+      "learning_rate": 0.0,
+      "loss": 2.1207,
+      "step": 50
+    },
+    {
+      "epoch": 0.07802594362625573,
+      "eval_loss": 1.713279128074646,
+      "eval_runtime": 284.2744,
+      "eval_samples_per_second": 15.186,
+      "eval_steps_per_second": 1.9,
+      "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": 5.468644419043328e+17,
+  "total_flos": 1.0937288838086656e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null