Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46ba79448bebf3c85f2400b7b292b3f5c74c7c614d1bfb503ce9af17de2093d8
+oid sha256:f15a35de81f891ebdb5ae5d54d0440032572bb85c4223311cb68c3bb36fa4dd1
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cecf83af62c7602e42e23b35b97f710f38954d939b1737ae3ab70d19513e1b2
+oid sha256:fc3eb3a8318e135a0337d95ccf767157a5129e4b77de540748d7b4d9d49486d6
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fdb726d9a8de61d4a64e8e83303ec8e5fcb07cb60f72b0613aaf598d13e7d11
+oid sha256:9486404057b5c0abc5885205115de02525e14ec38b2cb9c31a3dcc95c95e2114
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7006373d75caa4ff68cca0ff6764da9bea6a5a36c847ee0c5750b40f4ca8389f
+oid sha256:f4eea78290503c1343156af5addde3d4e35f80bc02bb8ebb4b46d32d96354315
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c70115380d55638dd2e273dcf9c4226c7c2ea7c60401b8b2c6d989824b79473
+oid sha256:2031c213de101e16f5ad50d5e4f686d45a7c0663e8beb00901464783e4e4335e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a10c20374db094c98bac87a88832db137b897ab4f4f2c5ba46cf4c1a7ab681
+oid sha256:af725fb99b2deb7109069c44ce9ac3f973de8d9ca2deb2e0765a79d751ae409a
 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": 0.518934965133667,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06278449223041908,
+  "best_metric": 0.492282509803772,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12556898446083817,
   "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": 14.78,
       "eval_steps_per_second": 1.851,
       "step": 25
+    },
+    {
+      "epoch": 0.06529587191963585,
+      "grad_norm": 9.209891319274902,
+      "learning_rate": 5e-05,
+      "loss": 0.3203,
+      "step": 26
+    },
+    {
+      "epoch": 0.06780725160885262,
+      "grad_norm": 14.673049926757812,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4129,
+      "step": 27
+    },
+    {
+      "epoch": 0.07031863129806938,
+      "grad_norm": 14.608511924743652,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4394,
+      "step": 28
+    },
+    {
+      "epoch": 0.07283001098728614,
+      "grad_norm": 11.686541557312012,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4547,
+      "step": 29
+    },
+    {
+      "epoch": 0.0753413906765029,
+      "grad_norm": 9.099536895751953,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4592,
+      "step": 30
+    },
+    {
+      "epoch": 0.07785277036571966,
+      "grad_norm": 9.882477760314941,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4395,
+      "step": 31
+    },
+    {
+      "epoch": 0.08036415005493643,
+      "grad_norm": 9.75089168548584,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.4752,
+      "step": 32
+    },
+    {
+      "epoch": 0.0828755297441532,
+      "grad_norm": 14.58424186706543,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4783,
+      "step": 33
+    },
+    {
+      "epoch": 0.08538690943336996,
+      "grad_norm": 17.86821746826172,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5316,
+      "step": 34
+    },
+    {
+      "epoch": 0.08789828912258672,
+      "grad_norm": 18.498552322387695,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.5342,
+      "step": 35
+    },
+    {
+      "epoch": 0.09040966881180348,
+      "grad_norm": 24.58167839050293,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.5721,
+      "step": 36
+    },
+    {
+      "epoch": 0.09292104850102025,
+      "grad_norm": 27.7944393157959,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7302,
+      "step": 37
+    },
+    {
+      "epoch": 0.095432428190237,
+      "grad_norm": 29.117172241210938,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5114,
+      "step": 38
+    },
+    {
+      "epoch": 0.09794380787945378,
+      "grad_norm": 5.468899726867676,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.32,
+      "step": 39
+    },
+    {
+      "epoch": 0.10045518756867054,
+      "grad_norm": 7.967328071594238,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4181,
+      "step": 40
+    },
+    {
+      "epoch": 0.1029665672578873,
+      "grad_norm": 7.048090934753418,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.447,
+      "step": 41
+    },
+    {
+      "epoch": 0.10547794694710406,
+      "grad_norm": 7.55548095703125,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4456,
+      "step": 42
+    },
+    {
+      "epoch": 0.10798932663632083,
+      "grad_norm": 7.440658092498779,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4538,
+      "step": 43
+    },
+    {
+      "epoch": 0.11050070632553759,
+      "grad_norm": 8.213162422180176,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4458,
+      "step": 44
+    },
+    {
+      "epoch": 0.11301208601475436,
+      "grad_norm": 11.403858184814453,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4657,
+      "step": 45
+    },
+    {
+      "epoch": 0.11552346570397112,
+      "grad_norm": 13.041141510009766,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4781,
+      "step": 46
+    },
+    {
+      "epoch": 0.11803484539318788,
+      "grad_norm": 12.925886154174805,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.5108,
+      "step": 47
+    },
+    {
+      "epoch": 0.12054622508240465,
+      "grad_norm": 20.79706573486328,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6018,
+      "step": 48
+    },
+    {
+      "epoch": 0.1230576047716214,
+      "grad_norm": 30.63442039489746,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.6667,
+      "step": 49
+    },
+    {
+      "epoch": 0.12556898446083817,
+      "grad_norm": 26.500112533569336,
+      "learning_rate": 0.0,
+      "loss": 0.6593,
+      "step": 50
+    },
+    {
+      "epoch": 0.12556898446083817,
+      "eval_loss": 0.492282509803772,
+      "eval_runtime": 182.685,
+      "eval_samples_per_second": 14.686,
+      "eval_steps_per_second": 1.839,
+      "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": 2.843207511740252e+17,
+  "total_flos": 5.68818318635434e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null