Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e2580e5769e7e1adb6028f6ba06f863851d39cbdf90e2eeb239763aa5d2af53
+oid sha256:a080d537f62f470eccc60ed16f4ea91e3b39d5350203424ff165c17abbcec5d2
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df6d0582f2f5bacc8d198f7fdfe25a268592edcbb493ae94534972b183fdc356
+oid sha256:a64b73123db2508651f09618b5c29aa980c4a53d31eb8efe735e9d09addeb601
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b56ecbb0019b555079fa18e466c5c23e0cadd219670840340df46806c2945b58
+oid sha256:3ebc4ddc1efeac96780ce5903968074ecadce7881f18f5481e03c7eecfecf054
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b26e5fc1f5641507a0cdce630f9fb1d2edd70af94c5db707561bf99f67b343f
+oid sha256:cba87e08fadc311b170ac6dd12aa3e0a4c545a1ceba7a0982a85208cca768417
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1af51f33f74c86fc2cdd68de732d726817a5fc2cefd5664d8ac110c7144b3eb
+oid sha256:84c81774f3814271bab0adf4b4cca6e79ca6c231fdb6253c44c114e6d388816c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a70ed74d16dac201d697e4c8dea15e6c327eebe18cab69f112ab8e6cd340bb51
+oid sha256:d1ce3c69cfec74dfed3edfe3a9751d24984ae40f17102c62d823903084fe3409
 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": 1.025231957435608,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.13311148086522462,
+  "best_metric": 0.6133490204811096,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.26622296173044924,
   "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": 68.277,
       "eval_steps_per_second": 8.582,
       "step": 25
+    },
+    {
+      "epoch": 0.13843594009983362,
+      "grad_norm": 6.450296878814697,
+      "learning_rate": 5e-05,
+      "loss": 1.0312,
+      "step": 26
+    },
+    {
+      "epoch": 0.1437603993344426,
+      "grad_norm": 5.499378681182861,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.0271,
+      "step": 27
+    },
+    {
+      "epoch": 0.14908485856905157,
+      "grad_norm": 4.80499267578125,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.8741,
+      "step": 28
+    },
+    {
+      "epoch": 0.15440931780366057,
+      "grad_norm": 4.07858943939209,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.8599,
+      "step": 29
+    },
+    {
+      "epoch": 0.15973377703826955,
+      "grad_norm": 3.2893877029418945,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8015,
+      "step": 30
+    },
+    {
+      "epoch": 0.16505823627287852,
+      "grad_norm": 3.4834606647491455,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7614,
+      "step": 31
+    },
+    {
+      "epoch": 0.17038269550748752,
+      "grad_norm": 3.2497472763061523,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7866,
+      "step": 32
+    },
+    {
+      "epoch": 0.1757071547420965,
+      "grad_norm": 4.107487201690674,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.7755,
+      "step": 33
+    },
+    {
+      "epoch": 0.1810316139767055,
+      "grad_norm": 3.7900607585906982,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6497,
+      "step": 34
+    },
+    {
+      "epoch": 0.18635607321131448,
+      "grad_norm": 4.495862007141113,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.776,
+      "step": 35
+    },
+    {
+      "epoch": 0.19168053244592345,
+      "grad_norm": 4.210362434387207,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8306,
+      "step": 36
+    },
+    {
+      "epoch": 0.19700499168053245,
+      "grad_norm": 5.1397175788879395,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.859,
+      "step": 37
+    },
+    {
+      "epoch": 0.20232945091514143,
+      "grad_norm": 5.5402936935424805,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8157,
+      "step": 38
+    },
+    {
+      "epoch": 0.2076539101497504,
+      "grad_norm": 3.070615530014038,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.5884,
+      "step": 39
+    },
+    {
+      "epoch": 0.2129783693843594,
+      "grad_norm": 3.0448577404022217,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6112,
+      "step": 40
+    },
+    {
+      "epoch": 0.21830282861896838,
+      "grad_norm": 3.166132926940918,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6329,
+      "step": 41
+    },
+    {
+      "epoch": 0.22362728785357738,
+      "grad_norm": 2.86126971244812,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4517,
+      "step": 42
+    },
+    {
+      "epoch": 0.22895174708818636,
+      "grad_norm": 3.097123384475708,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.5897,
+      "step": 43
+    },
+    {
+      "epoch": 0.23427620632279533,
+      "grad_norm": 2.668059825897217,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4817,
+      "step": 44
+    },
+    {
+      "epoch": 0.23960066555740434,
+      "grad_norm": 2.4491469860076904,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4798,
+      "step": 45
+    },
+    {
+      "epoch": 0.2449251247920133,
+      "grad_norm": 4.0405778884887695,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5788,
+      "step": 46
+    },
+    {
+      "epoch": 0.2502495840266223,
+      "grad_norm": 2.962510108947754,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4239,
+      "step": 47
+    },
+    {
+      "epoch": 0.2555740432612313,
+      "grad_norm": 3.4761126041412354,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5796,
+      "step": 48
+    },
+    {
+      "epoch": 0.2608985024958403,
+      "grad_norm": 3.6893534660339355,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.6451,
+      "step": 49
+    },
+    {
+      "epoch": 0.26622296173044924,
+      "grad_norm": 6.921513080596924,
+      "learning_rate": 0.0,
+      "loss": 1.1654,
+      "step": 50
+    },
+    {
+      "epoch": 0.26622296173044924,
+      "eval_loss": 0.6133490204811096,
+      "eval_runtime": 18.5142,
+      "eval_samples_per_second": 68.326,
+      "eval_steps_per_second": 8.588,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null