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:e86b5b449f4b4afbaaa598390fe17a0b84e1bbab24a04761b26b7feb605776d2
+oid sha256:ead231b8233a3bcfbb68d837c903bab1f3aa50b382f97d9bf58c92e4d865faad
 size 859909312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1494e072186e6d6d39242fc445142b904beb897dd62286d2744c65cc26532052
+oid sha256:0839f857ac8933ef51864c364a1240f68edd039ca6607e75590c89c4478d461c
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bd0fcfd7b63af729823824600fa0c4988f34d2a16c267f5b25faffd5b2d40c7
+oid sha256:91cf3bec7b20617ed53a55fb43692770b9d7113acf2027def70e3771d15c1015
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5481a7ab84b3420a130c753fec2fd924fa9c0972c98e21bbb41b2d9269277ec1
+oid sha256:2dfa378c38c77cb8e3d1b0403ca37211204d58855cab3cab1699e6290d02ad1d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae157acb227364bb5e4940f89508c562f7882235bfdfdd9c91355fbdaaf1e73a
+oid sha256:6b3a490557ac6f2fa71604394fd41ddbf1d376f8f88205bab366915b5ea3b7ee
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfbb7474076bab87aaed3ab5e5b3a5f0a1d481fd72a1a7132d245b13e55ec463
+oid sha256:3157799b34d02643bce5b0ab606395ed69b481a894522b038aa23a14c9de43f5
 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": 0.508665144443512,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.023515579071134628,
+  "best_metric": 0.48065781593322754,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.047031158142269255,
   "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": 22.699,
       "eval_steps_per_second": 2.84,
       "step": 25
+    },
+    {
+      "epoch": 0.024456202233980012,
+      "grad_norm": 0.8437718152999878,
+      "learning_rate": 5e-05,
+      "loss": 0.5489,
+      "step": 26
+    },
+    {
+      "epoch": 0.025396825396825397,
+      "grad_norm": 0.8871003985404968,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5273,
+      "step": 27
+    },
+    {
+      "epoch": 0.02633744855967078,
+      "grad_norm": 0.8110382556915283,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4564,
+      "step": 28
+    },
+    {
+      "epoch": 0.027278071722516166,
+      "grad_norm": 0.8688730001449585,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4854,
+      "step": 29
+    },
+    {
+      "epoch": 0.02821869488536155,
+      "grad_norm": 1.044745922088623,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5399,
+      "step": 30
+    },
+    {
+      "epoch": 0.02915931804820694,
+      "grad_norm": 0.9957165122032166,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4804,
+      "step": 31
+    },
+    {
+      "epoch": 0.030099941211052323,
+      "grad_norm": 1.0578233003616333,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5136,
+      "step": 32
+    },
+    {
+      "epoch": 0.031040564373897708,
+      "grad_norm": 1.0405433177947998,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4951,
+      "step": 33
+    },
+    {
+      "epoch": 0.031981187536743096,
+      "grad_norm": 1.1319266557693481,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.4955,
+      "step": 34
+    },
+    {
+      "epoch": 0.03292181069958848,
+      "grad_norm": 1.1135867834091187,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.5042,
+      "step": 35
+    },
+    {
+      "epoch": 0.033862433862433865,
+      "grad_norm": 1.0377700328826904,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4832,
+      "step": 36
+    },
+    {
+      "epoch": 0.03480305702527925,
+      "grad_norm": 1.257242202758789,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4273,
+      "step": 37
+    },
+    {
+      "epoch": 0.035743680188124634,
+      "grad_norm": 0.8728300333023071,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4586,
+      "step": 38
+    },
+    {
+      "epoch": 0.03668430335097002,
+      "grad_norm": 0.7657201886177063,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4409,
+      "step": 39
+    },
+    {
+      "epoch": 0.0376249265138154,
+      "grad_norm": 0.9262546300888062,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4937,
+      "step": 40
+    },
+    {
+      "epoch": 0.03856554967666079,
+      "grad_norm": 0.8848750591278076,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.489,
+      "step": 41
+    },
+    {
+      "epoch": 0.03950617283950617,
+      "grad_norm": 0.8872339129447937,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4796,
+      "step": 42
+    },
+    {
+      "epoch": 0.04044679600235156,
+      "grad_norm": 0.9265215992927551,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4922,
+      "step": 43
+    },
+    {
+      "epoch": 0.04138741916519694,
+      "grad_norm": 0.9621391892433167,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4666,
+      "step": 44
+    },
+    {
+      "epoch": 0.042328042328042326,
+      "grad_norm": 0.9457005262374878,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4935,
+      "step": 45
+    },
+    {
+      "epoch": 0.04326866549088771,
+      "grad_norm": 0.9700300097465515,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4628,
+      "step": 46
+    },
+    {
+      "epoch": 0.044209288653733095,
+      "grad_norm": 1.1647878885269165,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4651,
+      "step": 47
+    },
+    {
+      "epoch": 0.045149911816578486,
+      "grad_norm": 1.135780692100525,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4648,
+      "step": 48
+    },
+    {
+      "epoch": 0.04609053497942387,
+      "grad_norm": 1.0905580520629883,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4625,
+      "step": 49
+    },
+    {
+      "epoch": 0.047031158142269255,
+      "grad_norm": 1.2157825231552124,
+      "learning_rate": 0.0,
+      "loss": 0.4432,
+      "step": 50
+    },
+    {
+      "epoch": 0.047031158142269255,
+      "eval_loss": 0.48065781593322754,
+      "eval_runtime": 408.5813,
+      "eval_samples_per_second": 17.529,
+      "eval_steps_per_second": 2.193,
+      "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": 2.829012279754752e+17,
+  "total_flos": 5.658024559509504e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null