Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:428081c332e3899b0dbde472f424da212482558b15a09b706fbdb45c3e280773
+oid sha256:e37d74f2d05043aaea0b8f5451bf196a04e22d91e403b6c36956e05a312d59d9
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b34c314e490a0af3626abda2682c0a4d219413c5c7447d20a4ca5ed6332297d
+oid sha256:6d891c334141d2915be63fd4ae500ee88ab88d763240501312615d09ef787afc
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deed00677a83233b0f863749342c78990956b3b3e0bc0441487485539faa4a22
+oid sha256:07fdc6635c08bf739126c6b578ca8bb9ccb2c08a077e49f57d4f308a78de485b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c083d9d7e3fc3eea1618be996625f66909208ab8e5521b18004ff077a0cae367
+oid sha256:f4df6ffd0dadc9bf3872cc0a5ea3b4b3db7b7d403474f9434d95d293b39fb768
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc80b4195bd268392de3f830ffc8a0cedc87f207d276251ffb73b5b624088d98
+oid sha256:1d9b0dae6547eb12d48ae22af2828741214581de3b72c0de1e27d414548e7f36
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:850bcf8cbc88f773cc9263c58c3430961ce387aec95816412fb2e93247307058
+oid sha256:7c43d6b875495cfade6be027b6424376d324909ad76d4f4890d1b3e043e2de35
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0526127815246582,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.09465215333648841,
+  "best_metric": 1.0053794384002686,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.18930430667297682,
   "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": 24.657,
       "eval_steps_per_second": 6.411,
       "step": 25
+    },
+    {
+      "epoch": 0.09843823946994794,
+      "grad_norm": 0.7997608184814453,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.0595,
+      "step": 26
+    },
+    {
+      "epoch": 0.10222432560340748,
+      "grad_norm": 0.9007599353790283,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.1109,
+      "step": 27
+    },
+    {
+      "epoch": 0.10601041173686701,
+      "grad_norm": 0.9283623099327087,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.1029,
+      "step": 28
+    },
+    {
+      "epoch": 0.10979649787032655,
+      "grad_norm": 0.9904077053070068,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.1447,
+      "step": 29
+    },
+    {
+      "epoch": 0.11358258400378608,
+      "grad_norm": 0.9736183285713196,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.1642,
+      "step": 30
+    },
+    {
+      "epoch": 0.11736867013724563,
+      "grad_norm": 0.8450034856796265,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.2258,
+      "step": 31
+    },
+    {
+      "epoch": 0.12115475627070516,
+      "grad_norm": 0.9699908494949341,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.112,
+      "step": 32
+    },
+    {
+      "epoch": 0.1249408424041647,
+      "grad_norm": 1.067191243171692,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.0924,
+      "step": 33
+    },
+    {
+      "epoch": 0.12872692853762424,
+      "grad_norm": 1.109052062034607,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.1621,
+      "step": 34
+    },
+    {
+      "epoch": 0.13251301467108376,
+      "grad_norm": 1.1744805574417114,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.0986,
+      "step": 35
+    },
+    {
+      "epoch": 0.1362991008045433,
+      "grad_norm": 1.281468391418457,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.022,
+      "step": 36
+    },
+    {
+      "epoch": 0.14008518693800284,
+      "grad_norm": 1.494238257408142,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.0764,
+      "step": 37
+    },
+    {
+      "epoch": 0.14387127307146239,
+      "grad_norm": 0.6449403166770935,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.9728,
+      "step": 38
+    },
+    {
+      "epoch": 0.1476573592049219,
+      "grad_norm": 0.5640941262245178,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.0272,
+      "step": 39
+    },
+    {
+      "epoch": 0.15144344533838144,
+      "grad_norm": 0.5843005776405334,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.0219,
+      "step": 40
+    },
+    {
+      "epoch": 0.155229531471841,
+      "grad_norm": 0.591860294342041,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.0287,
+      "step": 41
+    },
+    {
+      "epoch": 0.15901561760530053,
+      "grad_norm": 0.6270464658737183,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.1001,
+      "step": 42
+    },
+    {
+      "epoch": 0.16280170373876005,
+      "grad_norm": 0.6936808824539185,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.1502,
+      "step": 43
+    },
+    {
+      "epoch": 0.1665877898722196,
+      "grad_norm": 1.0310381650924683,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.0836,
+      "step": 44
+    },
+    {
+      "epoch": 0.17037387600567913,
+      "grad_norm": 1.016648769378662,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.0123,
+      "step": 45
+    },
+    {
+      "epoch": 0.17415996213913867,
+      "grad_norm": 1.1334302425384521,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.0984,
+      "step": 46
+    },
+    {
+      "epoch": 0.1779460482725982,
+      "grad_norm": 1.206661343574524,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.0054,
+      "step": 47
+    },
+    {
+      "epoch": 0.18173213440605773,
+      "grad_norm": 1.2735713720321655,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.9726,
+      "step": 48
+    },
+    {
+      "epoch": 0.18551822053951728,
+      "grad_norm": 1.4444059133529663,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.0457,
+      "step": 49
+    },
+    {
+      "epoch": 0.18930430667297682,
+      "grad_norm": 1.7697523832321167,
+      "learning_rate": 1e-05,
+      "loss": 1.0625,
+      "step": 50
+    },
+    {
+      "epoch": 0.18930430667297682,
+      "eval_loss": 1.0053794384002686,
+      "eval_runtime": 2.0429,
+      "eval_samples_per_second": 24.475,
+      "eval_steps_per_second": 6.364,
+      "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": 7.94731890081792e+16,
+  "total_flos": 1.589463780163584e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null