Training in progress, step 76, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3d4aa09aa0dd78603db3306f784d0ec23232ed5848527b8669818e8e604216e
+oid sha256:17a688d72965a31498835e19a3d50bc535a4301ec1529cae220b288f76255751
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27f2475713637d9fdc7ed4f9c820faf378b8c7de64e190720c7b8e1d43f78df2
+oid sha256:14a37368ea40e4c82c5f268ea72a4c729bee978393ed7f62b728dd5129a46d12
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:711b2f547c3e14ffbae0aef655bef196504d1bf02154c4d697d4d62a93c53f24
+oid sha256:47acafa232bcc28ab5833d79ff3104d3e9a72de50268a1ee1ac71395fc84423e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eff4e51807fc2798ef7e3176a7ae7a505f7b610c949cf8c1d65662116e17ea14
+oid sha256:e8ddabf60630e29c65bf15d4d38a70b53e1096fcbf23378832f8b10226895763
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.9277753829956055,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.02137008988794059,
+  "epoch": 0.0324825366296697,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 76,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,196 @@
       "eval_samples_per_second": 3.509,
       "eval_steps_per_second": 3.509,
       "step": 50
+    },
+    {
+      "epoch": 0.021797491685699402,
+      "grad_norm": 73.92220306396484,
+      "learning_rate": 9.916118258515936e-05,
+      "loss": 60.9493,
+      "step": 51
+    },
+    {
+      "epoch": 0.022224893483458213,
+      "grad_norm": 65.9156265258789,
+      "learning_rate": 9.421851671977372e-05,
+      "loss": 60.0054,
+      "step": 52
+    },
+    {
+      "epoch": 0.022652295281217028,
+      "grad_norm": 49.42222595214844,
+      "learning_rate": 8.940340387142462e-05,
+      "loss": 57.0988,
+      "step": 53
+    },
+    {
+      "epoch": 0.02307969707897584,
+      "grad_norm": 31.272438049316406,
+      "learning_rate": 8.47245211989213e-05,
+      "loss": 59.2207,
+      "step": 54
+    },
+    {
+      "epoch": 0.02350709887673465,
+      "grad_norm": 19.92361831665039,
+      "learning_rate": 8.019030036508827e-05,
+      "loss": 58.0069,
+      "step": 55
+    },
+    {
+      "epoch": 0.023934500674493462,
+      "grad_norm": 33.7132453918457,
+      "learning_rate": 7.580891234233904e-05,
+      "loss": 56.2188,
+      "step": 56
+    },
+    {
+      "epoch": 0.024361902472252273,
+      "grad_norm": 23.189586639404297,
+      "learning_rate": 7.158825268803127e-05,
+      "loss": 56.9692,
+      "step": 57
+    },
+    {
+      "epoch": 0.024789304270011085,
+      "grad_norm": 21.800243377685547,
+      "learning_rate": 6.75359273161392e-05,
+      "loss": 61.5117,
+      "step": 58
+    },
+    {
+      "epoch": 0.0252167060677699,
+      "grad_norm": 20.54871940612793,
+      "learning_rate": 6.365923879088219e-05,
+      "loss": 57.6141,
+      "step": 59
+    },
+    {
+      "epoch": 0.02564410786552871,
+      "grad_norm": 23.886445999145508,
+      "learning_rate": 5.996517316701069e-05,
+      "loss": 56.7736,
+      "step": 60
+    },
+    {
+      "epoch": 0.026071509663287522,
+      "grad_norm": 25.174198150634766,
+      "learning_rate": 5.646038740046304e-05,
+      "loss": 55.5788,
+      "step": 61
+    },
+    {
+      "epoch": 0.026498911461046333,
+      "grad_norm": 25.409194946289062,
+      "learning_rate": 5.315119735208132e-05,
+      "loss": 58.9748,
+      "step": 62
+    },
+    {
+      "epoch": 0.026926313258805144,
+      "grad_norm": 25.356067657470703,
+      "learning_rate": 5.004356640600297e-05,
+      "loss": 55.9752,
+      "step": 63
+    },
+    {
+      "epoch": 0.027353715056563956,
+      "grad_norm": 30.15899085998535,
+      "learning_rate": 4.71430947232396e-05,
+      "loss": 60.8193,
+      "step": 64
+    },
+    {
+      "epoch": 0.027781116854322767,
+      "grad_norm": 25.970443725585938,
+      "learning_rate": 4.4455009149808265e-05,
+      "loss": 58.5226,
+      "step": 65
+    },
+    {
+      "epoch": 0.02820851865208158,
+      "grad_norm": 26.306665420532227,
+      "learning_rate": 4.1984153797601665e-05,
+      "loss": 58.1114,
+      "step": 66
+    },
+    {
+      "epoch": 0.028635920449840393,
+      "grad_norm": 25.005186080932617,
+      "learning_rate": 3.9734981314971234e-05,
+      "loss": 58.226,
+      "step": 67
+    },
+    {
+      "epoch": 0.029063322247599204,
+      "grad_norm": 25.699512481689453,
+      "learning_rate": 3.771154486275363e-05,
+      "loss": 55.8354,
+      "step": 68
+    },
+    {
+      "epoch": 0.029490724045358015,
+      "grad_norm": 25.881290435791016,
+      "learning_rate": 3.591749081020113e-05,
+      "loss": 55.4757,
+      "step": 69
+    },
+    {
+      "epoch": 0.029918125843116827,
+      "grad_norm": 29.308368682861328,
+      "learning_rate": 3.435605216397765e-05,
+      "loss": 60.0276,
+      "step": 70
+    },
+    {
+      "epoch": 0.030345527640875638,
+      "grad_norm": 27.00686264038086,
+      "learning_rate": 3.303004274206237e-05,
+      "loss": 59.6951,
+      "step": 71
+    },
+    {
+      "epoch": 0.030772929438634453,
+      "grad_norm": 27.934207916259766,
+      "learning_rate": 3.194185210305936e-05,
+      "loss": 56.2346,
+      "step": 72
+    },
+    {
+      "epoch": 0.031200331236393264,
+      "grad_norm": 28.110820770263672,
+      "learning_rate": 3.1093441240051626e-05,
+      "loss": 59.4317,
+      "step": 73
+    },
+    {
+      "epoch": 0.031627733034152075,
+      "grad_norm": 28.240201950073242,
+      "learning_rate": 3.048633904675892e-05,
+      "loss": 58.142,
+      "step": 74
+    },
+    {
+      "epoch": 0.032055134831910886,
+      "grad_norm": 30.365863800048828,
+      "learning_rate": 3.012163956236801e-05,
+      "loss": 56.8291,
+      "step": 75
+    },
+    {
+      "epoch": 0.032055134831910886,
+      "eval_loss": 1.7859845161437988,
+      "eval_runtime": 14.2376,
+      "eval_samples_per_second": 3.512,
+      "eval_steps_per_second": 3.512,
+      "step": 75
+    },
+    {
+      "epoch": 0.0324825366296697,
+      "grad_norm": 31.245229721069336,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 63.3069,
+      "step": 76
     }
   ],
   "logging_steps": 1,
@@ -404,12 +594,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.4472165943620403e+17,
+  "total_flos": 2.2066295782087066e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null