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:dd01ea9cc51b4b755796e3a4c13444a7702aa1df0a8ecd6bcbe4a7cadc76412b
+oid sha256:16cb250d7d09eb866b39f11b968a1972dde3ae56e94c90f8f85525b365ef50df
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f3364093310ed881ac4b91de7c0dbb83fe2929af47000d39f31b3f76102c1e1
+oid sha256:12f2fb72bf1f9118a6c705bced90904e22f8126b1146d69e8aa8972b92069c36
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:028c687b7a74800cba4ef295bd02a54d6e01f36643150224ed5ffb4542ee3fa9
+oid sha256:90167e8bf4a291f5f8c5ff2903aabaf2a3e094fb5bd5edf3fbf4e335cd4e2cbb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6a3c75d3bd67a1ae55bbc2f11d87bd3e99564bd48affd09d2b64fd31f2036ba
+oid sha256:a92c9d6f07e443566483ac8ace068f9a6f73ce0aef50d1901d277ccfd46e3449
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8404be8231b09ed3cfae242cdffead132bba9d4844ec2d5106512dee8706283
+oid sha256:89ca60a0a932e89ccd0d1311cc2ebccb8189150aa4efe4f3f319de3b0bbc06fb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b05e0a129b2d4aa22d47eeb5b372e57c15b5e4e76480c22e862b64c594df4c82
+oid sha256:681c4bd5c39fd7d9501835e3c8057f4568c0640bb8ec0d1924a5a00a5a3c2989
 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": 0.9667521715164185,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.37523452157598497,
+  "best_metric": 0.9443409442901611,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7504690431519699,
   "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": 32.26,
       "eval_steps_per_second": 4.095,
       "step": 25
+    },
+    {
+      "epoch": 0.3902439024390244,
+      "grad_norm": 0.2630976736545563,
+      "learning_rate": 5e-05,
+      "loss": 0.881,
+      "step": 26
+    },
+    {
+      "epoch": 0.4052532833020638,
+      "grad_norm": 0.26560088992118835,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9961,
+      "step": 27
+    },
+    {
+      "epoch": 0.4202626641651032,
+      "grad_norm": 0.23215793073177338,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.008,
+      "step": 28
+    },
+    {
+      "epoch": 0.4352720450281426,
+      "grad_norm": 0.2006905972957611,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9938,
+      "step": 29
+    },
+    {
+      "epoch": 0.450281425891182,
+      "grad_norm": 0.2019686996936798,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.9836,
+      "step": 30
+    },
+    {
+      "epoch": 0.4652908067542214,
+      "grad_norm": 0.20353145897388458,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.967,
+      "step": 31
+    },
+    {
+      "epoch": 0.4803001876172608,
+      "grad_norm": 0.2187284678220749,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.9788,
+      "step": 32
+    },
+    {
+      "epoch": 0.49530956848030017,
+      "grad_norm": 0.23200970888137817,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.9042,
+      "step": 33
+    },
+    {
+      "epoch": 0.5103189493433395,
+      "grad_norm": 0.21799759566783905,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9099,
+      "step": 34
+    },
+    {
+      "epoch": 0.525328330206379,
+      "grad_norm": 0.2261268049478531,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.9489,
+      "step": 35
+    },
+    {
+      "epoch": 0.5403377110694184,
+      "grad_norm": 0.2131943255662918,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8895,
+      "step": 36
+    },
+    {
+      "epoch": 0.5553470919324578,
+      "grad_norm": 0.23032636940479279,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8981,
+      "step": 37
+    },
+    {
+      "epoch": 0.5703564727954972,
+      "grad_norm": 0.1798233836889267,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8644,
+      "step": 38
+    },
+    {
+      "epoch": 0.5853658536585366,
+      "grad_norm": 0.23366278409957886,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.9421,
+      "step": 39
+    },
+    {
+      "epoch": 0.600375234521576,
+      "grad_norm": 0.22759605944156647,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.0072,
+      "step": 40
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.20452305674552917,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.9861,
+      "step": 41
+    },
+    {
+      "epoch": 0.6303939962476548,
+      "grad_norm": 0.21224012970924377,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9324,
+      "step": 42
+    },
+    {
+      "epoch": 0.6454033771106942,
+      "grad_norm": 0.19800162315368652,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.9566,
+      "step": 43
+    },
+    {
+      "epoch": 0.6604127579737336,
+      "grad_norm": 0.18474912643432617,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9571,
+      "step": 44
+    },
+    {
+      "epoch": 0.6754221388367729,
+      "grad_norm": 0.17070691287517548,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.9385,
+      "step": 45
+    },
+    {
+      "epoch": 0.6904315196998124,
+      "grad_norm": 0.17717796564102173,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.9539,
+      "step": 46
+    },
+    {
+      "epoch": 0.7054409005628518,
+      "grad_norm": 0.18040595948696136,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.9689,
+      "step": 47
+    },
+    {
+      "epoch": 0.7204502814258912,
+      "grad_norm": 0.17790913581848145,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.8991,
+      "step": 48
+    },
+    {
+      "epoch": 0.7354596622889306,
+      "grad_norm": 0.19197432696819305,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8769,
+      "step": 49
+    },
+    {
+      "epoch": 0.7504690431519699,
+      "grad_norm": 0.24990469217300415,
+      "learning_rate": 0.0,
+      "loss": 0.8438,
+      "step": 50
+    },
+    {
+      "epoch": 0.7504690431519699,
+      "eval_loss": 0.9443409442901611,
+      "eval_runtime": 13.9336,
+      "eval_samples_per_second": 32.224,
+      "eval_steps_per_second": 4.091,
+      "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": 2.984093348265984e+17,
+  "total_flos": 5.968186696531968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null