Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1db7d0a4b36909d64a931e7d1b6816b42acb68edb37fcc2cbe0c8bde34af21a5
+oid sha256:d560915e36c9ff28dfe5902d7cd34e153b52e95bd0e98500697da890db78438c
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61b1f09303558e072b6e675145033a801a3096658514ac0d8307581126084396
+oid sha256:e2db7f79a2cd5eac95fcbcbce2ee7c7370d76d7abf6c73ac1594140e5c183210
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d18612397c340e72394219a15a72ba6dd23b135ed28f23ed683469063aec0e1e
+oid sha256:fa2f71d1032120d859655f67a60b631a61e71ee3ed34f394c43e7224e54ce20b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32d044b46a2d0ae0fbb83b8e4b7c88f76b8aee7cd96cc208633dfa05fad1cd36
+oid sha256:5d8902ab0a037bc16c7b3c49ae3eb36fca42a7103508a7a3e6ce364415ff159c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55d3f0fc1dca7b487d7f05f6fa601f660a934a6e9bcc5d4817c7e4fe9de2466d
+oid sha256:bfa27628d8a583d346d942030eed0677967ac5ea9ea05faf2914efb4dcc91c8c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:931e6c5edee5b0ab7154f9d959ec56cf516526ea8fe9db947ef74480c1bf58d2
+oid sha256:e5a598828c6e4d08f0eef9a107cdeb0f5a1462d143d7ce3cbc862662cade0001
 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": 0.016865907236933708,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.005634437683119224,
+  "best_metric": 0.009789057075977325,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.011268875366238449,
   "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": 14.941,
       "eval_steps_per_second": 1.868,
       "step": 25
+    },
+    {
+      "epoch": 0.005859815190443994,
+      "grad_norm": 0.43277430534362793,
+      "learning_rate": 5e-05,
+      "loss": 0.0169,
+      "step": 26
+    },
+    {
+      "epoch": 0.006085192697768763,
+      "grad_norm": 0.12261365354061127,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0088,
+      "step": 27
+    },
+    {
+      "epoch": 0.006310570205093531,
+      "grad_norm": 0.36166757345199585,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0105,
+      "step": 28
+    },
+    {
+      "epoch": 0.006535947712418301,
+      "grad_norm": 0.2865087389945984,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0072,
+      "step": 29
+    },
+    {
+      "epoch": 0.0067613252197430695,
+      "grad_norm": 0.13543976843357086,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0089,
+      "step": 30
+    },
+    {
+      "epoch": 0.006986702727067838,
+      "grad_norm": 0.32603442668914795,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0081,
+      "step": 31
+    },
+    {
+      "epoch": 0.007212080234392608,
+      "grad_norm": 0.07940559834241867,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0042,
+      "step": 32
+    },
+    {
+      "epoch": 0.0074374577417173765,
+      "grad_norm": 0.6605622172355652,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0211,
+      "step": 33
+    },
+    {
+      "epoch": 0.007662835249042145,
+      "grad_norm": 0.45941802859306335,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0177,
+      "step": 34
+    },
+    {
+      "epoch": 0.007888212756366914,
+      "grad_norm": 0.34309831261634827,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0087,
+      "step": 35
+    },
+    {
+      "epoch": 0.008113590263691683,
+      "grad_norm": 0.34011223912239075,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0104,
+      "step": 36
+    },
+    {
+      "epoch": 0.008338967771016453,
+      "grad_norm": 0.2117564082145691,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.005,
+      "step": 37
+    },
+    {
+      "epoch": 0.00856434527834122,
+      "grad_norm": 0.09729141741991043,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0082,
+      "step": 38
+    },
+    {
+      "epoch": 0.00878972278566599,
+      "grad_norm": 0.10410496592521667,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0044,
+      "step": 39
+    },
+    {
+      "epoch": 0.00901510029299076,
+      "grad_norm": 0.3540576696395874,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0212,
+      "step": 40
+    },
+    {
+      "epoch": 0.009240477800315528,
+      "grad_norm": 0.6972055435180664,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.013,
+      "step": 41
+    },
+    {
+      "epoch": 0.009465855307640297,
+      "grad_norm": 0.43922847509384155,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0087,
+      "step": 42
+    },
+    {
+      "epoch": 0.009691232814965067,
+      "grad_norm": 0.1131017655134201,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0029,
+      "step": 43
+    },
+    {
+      "epoch": 0.009916610322289835,
+      "grad_norm": 0.3094264566898346,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0085,
+      "step": 44
+    },
+    {
+      "epoch": 0.010141987829614604,
+      "grad_norm": 0.7499658465385437,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0167,
+      "step": 45
+    },
+    {
+      "epoch": 0.010367365336939374,
+      "grad_norm": 0.12543810904026031,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0081,
+      "step": 46
+    },
+    {
+      "epoch": 0.010592742844264142,
+      "grad_norm": 0.12715910375118256,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0063,
+      "step": 47
+    },
+    {
+      "epoch": 0.010818120351588911,
+      "grad_norm": 0.33462029695510864,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0123,
+      "step": 48
+    },
+    {
+      "epoch": 0.01104349785891368,
+      "grad_norm": 0.30533668398857117,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0052,
+      "step": 49
+    },
+    {
+      "epoch": 0.011268875366238449,
+      "grad_norm": 0.3823198676109314,
+      "learning_rate": 0.0,
+      "loss": 0.0208,
+      "step": 50
+    },
+    {
+      "epoch": 0.011268875366238449,
+      "eval_loss": 0.009789057075977325,
+      "eval_runtime": 1999.7394,
+      "eval_samples_per_second": 14.948,
+      "eval_steps_per_second": 1.869,
+      "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