Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:171cd4153b4a8581c5a79505ffbe2ce67a0a8ed823d595f16cdd53b272bca505
+oid sha256:312e9aee1dd3752045572806afa5ddea57c0bbf3a759d7d1a2e04f297f0d78f5
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e0711f23538a5117f34a286c3fb093ebff1df6b4e4ba3f39b42680af212be49
+oid sha256:7b1433feaa4442323bc5f351294a16e700581409d5fa045688586a6a43f19978
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5624d58037519df2ed5d1c02bc49581f7b9a384f99fcaa0c5ec71a96541beca6
+oid sha256:f74941f75e308f769f1a0d21c685a66a9187a378ed09c69f4d5099efc15b16ff
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:943615e3ceebbfb2fe9e2781d91f243c367509ab756d40310b755f9b1c11138f
+oid sha256:823eab2c5225d683eddaa888b90d7570bff19e2b7da8dcc39354a5271c3e7cfd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e35f570380d4ee1e030a84f8c9ba769977b917a08be3ebeb23fac6acfb966d4
+oid sha256:121063f6ec13b8e25517fdfbc7084dc05997cc90a700bb89fc412be2a7ce451d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cd4d625a1dbf9ef17b1dded5809eaf43653428c7a0f98d21dddf154f47f63ca
+oid sha256:969a2dba5823f181d90e29848de9ee5febf8f276b45ab73e4a3a2bfd45c469f8
 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": 11.914202690124512,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7421150278293135,
+  "best_metric": 11.910809516906738,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.4916512059369202,
   "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": 293.777,
       "eval_steps_per_second": 76.382,
       "step": 25
+    },
+    {
+      "epoch": 0.7717996289424861,
+      "grad_norm": 0.05901161581277847,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.9242,
+      "step": 26
+    },
+    {
+      "epoch": 0.8014842300556586,
+      "grad_norm": 0.06706172227859497,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.9231,
+      "step": 27
+    },
+    {
+      "epoch": 0.8311688311688312,
+      "grad_norm": 0.07833290100097656,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.9237,
+      "step": 28
+    },
+    {
+      "epoch": 0.8608534322820037,
+      "grad_norm": 0.091151162981987,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.9266,
+      "step": 29
+    },
+    {
+      "epoch": 0.8905380333951762,
+      "grad_norm": 0.11896399408578873,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.929,
+      "step": 30
+    },
+    {
+      "epoch": 0.9202226345083488,
+      "grad_norm": 0.11437124013900757,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.9297,
+      "step": 31
+    },
+    {
+      "epoch": 0.9499072356215214,
+      "grad_norm": 0.13641905784606934,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.9235,
+      "step": 32
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "grad_norm": 0.15378476679325104,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.9242,
+      "step": 33
+    },
+    {
+      "epoch": 1.0166975881261595,
+      "grad_norm": 0.13144145905971527,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 17.6087,
+      "step": 34
+    },
+    {
+      "epoch": 1.0463821892393321,
+      "grad_norm": 0.07724036276340485,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 13.2434,
+      "step": 35
+    },
+    {
+      "epoch": 1.0760667903525047,
+      "grad_norm": 0.0806306004524231,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.7137,
+      "step": 36
+    },
+    {
+      "epoch": 1.1057513914656771,
+      "grad_norm": 0.09000066667795181,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 12.1179,
+      "step": 37
+    },
+    {
+      "epoch": 1.1354359925788498,
+      "grad_norm": 0.12084916979074478,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.5785,
+      "step": 38
+    },
+    {
+      "epoch": 1.1651205936920221,
+      "grad_norm": 0.12375957518815994,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.8553,
+      "step": 39
+    },
+    {
+      "epoch": 1.1948051948051948,
+      "grad_norm": 0.1317008137702942,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.8129,
+      "step": 40
+    },
+    {
+      "epoch": 1.2244897959183674,
+      "grad_norm": 0.14589351415634155,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.9896,
+      "step": 41
+    },
+    {
+      "epoch": 1.25417439703154,
+      "grad_norm": 0.10819032043218613,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.9097,
+      "step": 42
+    },
+    {
+      "epoch": 1.2838589981447124,
+      "grad_norm": 0.08235201239585876,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 13.3787,
+      "step": 43
+    },
+    {
+      "epoch": 1.313543599257885,
+      "grad_norm": 0.08341158926486969,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.532,
+      "step": 44
+    },
+    {
+      "epoch": 1.3432282003710574,
+      "grad_norm": 0.09403184056282043,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.4107,
+      "step": 45
+    },
+    {
+      "epoch": 1.37291280148423,
+      "grad_norm": 0.09566580504179001,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 13.2582,
+      "step": 46
+    },
+    {
+      "epoch": 1.4025974025974026,
+      "grad_norm": 0.12213481962680817,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.283,
+      "step": 47
+    },
+    {
+      "epoch": 1.4322820037105752,
+      "grad_norm": 0.11991226673126221,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 12.1191,
+      "step": 48
+    },
+    {
+      "epoch": 1.4619666048237476,
+      "grad_norm": 0.15538115799427032,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 12.0205,
+      "step": 49
+    },
+    {
+      "epoch": 1.4916512059369202,
+      "grad_norm": 0.13172012567520142,
+      "learning_rate": 1e-05,
+      "loss": 10.5414,
+      "step": 50
+    },
+    {
+      "epoch": 1.4916512059369202,
+      "eval_loss": 11.910809516906738,
+      "eval_runtime": 0.1853,
+      "eval_samples_per_second": 269.832,
+      "eval_steps_per_second": 70.156,
+      "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": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null