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:cba27072348f79b4db898f8a406e50d55fbba20a05e5f23651f9b95aabf0fd97
+oid sha256:40a5ecb73c9c8079e5768ea6c5b1a734d62e6f01e11b03a8f58f5b3e1a80b180
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c23bedb1b9209b6bfeffce3194b075c40f2f7c5ed7616e557e0e49138ad239b1
+oid sha256:f8fc16a39d47f78d8244d8ca7f77fa7c30eea1db467527d22dd7ab0202eda263
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7fc659c744de60894227bcb7cef98a0015c385d332d3d70eb6b5b67d455f3a2
+oid sha256:02df5de702970f89bffc766f587a5ab06f0bf7775467ff82e9b5e6ecaca528e6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93d93485fcb13fb9bdcac44829d41f7b165abbd0afccf15df9b1172b566ecb5d
+oid sha256:82eec574c6d2b594de81d0aa2200850ff18b41285e76047d1bcb717570fc48ac
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17d3894bc6867faed4e0a634af43e56029ce9fae775220273aad60f26250953
+oid sha256:7dfc20f3095c59ac08d984d286d10bf3952e62fffee9d1e83fdb4749652745b0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5eb1e49caed45a2634591aff628b0d0aded49fcb8bd43feb67fe3fba4b64e0e
+oid sha256:568a76300f833b3ecb64b58aafcdd2a188960ef706f7f8f76b5daf9d8ac825c6
 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": 0.08786293864250183,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.111716621253406,
+  "best_metric": 0.01978439837694168,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.223433242506812,
   "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": 32.274,
       "eval_steps_per_second": 4.164,
       "step": 25
+    },
+    {
+      "epoch": 1.1553133514986376,
+      "grad_norm": 2.960618734359741,
+      "learning_rate": 5e-05,
+      "loss": 0.0719,
+      "step": 26
+    },
+    {
+      "epoch": 1.1989100817438691,
+      "grad_norm": 3.1005544662475586,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0936,
+      "step": 27
+    },
+    {
+      "epoch": 1.2425068119891007,
+      "grad_norm": 0.5020301938056946,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0441,
+      "step": 28
+    },
+    {
+      "epoch": 1.2861035422343323,
+      "grad_norm": 0.7082467675209045,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0199,
+      "step": 29
+    },
+    {
+      "epoch": 1.3297002724795641,
+      "grad_norm": 1.5583200454711914,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0518,
+      "step": 30
+    },
+    {
+      "epoch": 1.3732970027247957,
+      "grad_norm": 1.1485878229141235,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0447,
+      "step": 31
+    },
+    {
+      "epoch": 1.4168937329700273,
+      "grad_norm": 2.684978723526001,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0235,
+      "step": 32
+    },
+    {
+      "epoch": 1.4604904632152589,
+      "grad_norm": 1.4292771816253662,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0502,
+      "step": 33
+    },
+    {
+      "epoch": 1.5040871934604905,
+      "grad_norm": 1.1590442657470703,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0307,
+      "step": 34
+    },
+    {
+      "epoch": 1.547683923705722,
+      "grad_norm": 0.2641136348247528,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0102,
+      "step": 35
+    },
+    {
+      "epoch": 1.5912806539509536,
+      "grad_norm": 0.37619253993034363,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0247,
+      "step": 36
+    },
+    {
+      "epoch": 1.6348773841961854,
+      "grad_norm": 0.25651946663856506,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0083,
+      "step": 37
+    },
+    {
+      "epoch": 1.6784741144414168,
+      "grad_norm": 0.3186868727207184,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0105,
+      "step": 38
+    },
+    {
+      "epoch": 1.7220708446866486,
+      "grad_norm": 0.41207724809646606,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0213,
+      "step": 39
+    },
+    {
+      "epoch": 1.76566757493188,
+      "grad_norm": 0.31666725873947144,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0038,
+      "step": 40
+    },
+    {
+      "epoch": 1.8092643051771118,
+      "grad_norm": 0.5484305620193481,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0148,
+      "step": 41
+    },
+    {
+      "epoch": 1.8528610354223434,
+      "grad_norm": 0.44189968705177307,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0101,
+      "step": 42
+    },
+    {
+      "epoch": 1.896457765667575,
+      "grad_norm": 0.6846371293067932,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.017,
+      "step": 43
+    },
+    {
+      "epoch": 1.9400544959128065,
+      "grad_norm": 0.29374387860298157,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.011,
+      "step": 44
+    },
+    {
+      "epoch": 2.005449591280654,
+      "grad_norm": 0.2908608913421631,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0082,
+      "step": 45
+    },
+    {
+      "epoch": 2.0490463215258856,
+      "grad_norm": 0.12878499925136566,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.007,
+      "step": 46
+    },
+    {
+      "epoch": 2.092643051771117,
+      "grad_norm": 0.14788788557052612,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0041,
+      "step": 47
+    },
+    {
+      "epoch": 2.136239782016349,
+      "grad_norm": 0.35576820373535156,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0119,
+      "step": 48
+    },
+    {
+      "epoch": 2.1798365122615806,
+      "grad_norm": 0.337051659822464,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0099,
+      "step": 49
+    },
+    {
+      "epoch": 2.223433242506812,
+      "grad_norm": 0.5203828811645508,
+      "learning_rate": 0.0,
+      "loss": 0.0171,
+      "step": 50
+    },
+    {
+      "epoch": 2.223433242506812,
+      "eval_loss": 0.01978439837694168,
+      "eval_runtime": 4.8057,
+      "eval_samples_per_second": 32.253,
+      "eval_steps_per_second": 4.162,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null