Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:942e8c98836570a510645bc7d2e829c8fa5e273b129cff668b35d993c4b52a69
+oid sha256:34cc4163bd441aeab5e7c61e5ee2a3e3b9642beda0e0708dff4926adab1d11c9
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:221b889b4212519723aec47733fc1f2b251e337e7d40d0644dc0d93a72c414ad
+oid sha256:c6e1f9bde23ae1d9929e7bb8d96e176ef5038d5b29f2a628ff18c19843f12ec6
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7d6fce12069ff388e44433dc5ce7231bd5213a9fa54a43665cab6548de76557
+oid sha256:93e8bc109c059b375cfc4c36589e2406d27b96177cacc3ee3626954115c8222f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e980a369392718f51199736b56e2d29554893d52b054e338a4fdcee23d5ae318
+oid sha256:9e3fddc36e661f28d706dec7084e9b54aa1e9b5805428664bab711a349d41fbc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:011739a207ed52accb6616c62a223bce11c6881edd4e1e8312a99e39cbc3bcaf
+oid sha256:83082907f8fd340708884daedabbd38e5fea3d67daed1eb3b394ef90a463d98d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eea9112c218a725a5f2f6026d5e8eef81e238ff1dd0c64e4a7bbbd050455efc4
+oid sha256:ae25accc62e6aef6fb5caebadc03c016d8136dcac03fe2bb076992fa3c8b3d02
 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": 1.8678327798843384,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22271714922049,
+  "best_metric": 1.7232028245925903,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.44543429844098,
   "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": 37.365,
       "eval_steps_per_second": 9.715,
       "step": 25
+    },
+    {
+      "epoch": 0.23162583518930957,
+      "grad_norm": 0.4222097396850586,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.6003,
+      "step": 26
+    },
+    {
+      "epoch": 0.24053452115812918,
+      "grad_norm": 0.80172199010849,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.6958,
+      "step": 27
+    },
+    {
+      "epoch": 0.24944320712694878,
+      "grad_norm": 0.8624845743179321,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.2583518930957684,
+      "grad_norm": 1.0457912683486938,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.8821,
+      "step": 29
+    },
+    {
+      "epoch": 0.267260579064588,
+      "grad_norm": 0.801153838634491,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.9877,
+      "step": 30
+    },
+    {
+      "epoch": 0.27616926503340755,
+      "grad_norm": 0.6440266966819763,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.0081,
+      "step": 31
+    },
+    {
+      "epoch": 0.28507795100222716,
+      "grad_norm": 0.48909497261047363,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.9782,
+      "step": 32
+    },
+    {
+      "epoch": 0.29398663697104677,
+      "grad_norm": 0.4719208776950836,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.7975,
+      "step": 33
+    },
+    {
+      "epoch": 0.3028953229398664,
+      "grad_norm": 0.6802312135696411,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.8392,
+      "step": 34
+    },
+    {
+      "epoch": 0.311804008908686,
+      "grad_norm": 1.0054951906204224,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.7632,
+      "step": 35
+    },
+    {
+      "epoch": 0.3207126948775056,
+      "grad_norm": 1.5242421627044678,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.6814,
+      "step": 36
+    },
+    {
+      "epoch": 0.32962138084632514,
+      "grad_norm": 3.246612071990967,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.6508,
+      "step": 37
+    },
+    {
+      "epoch": 0.33853006681514475,
+      "grad_norm": 0.32325273752212524,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.6682,
+      "step": 38
+    },
+    {
+      "epoch": 0.34743875278396436,
+      "grad_norm": 0.2519363760948181,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.4816,
+      "step": 39
+    },
+    {
+      "epoch": 0.35634743875278396,
+      "grad_norm": 0.3244990110397339,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.7353,
+      "step": 40
+    },
+    {
+      "epoch": 0.36525612472160357,
+      "grad_norm": 0.3196703791618347,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.7866,
+      "step": 41
+    },
+    {
+      "epoch": 0.3741648106904232,
+      "grad_norm": 0.2564365565776825,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.9444,
+      "step": 42
+    },
+    {
+      "epoch": 0.3830734966592428,
+      "grad_norm": 0.2975054979324341,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.88,
+      "step": 43
+    },
+    {
+      "epoch": 0.39198218262806234,
+      "grad_norm": 0.35675594210624695,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.929,
+      "step": 44
+    },
+    {
+      "epoch": 0.40089086859688194,
+      "grad_norm": 0.32580721378326416,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.8816,
+      "step": 45
+    },
+    {
+      "epoch": 0.40979955456570155,
+      "grad_norm": 0.4181939959526062,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.8151,
+      "step": 46
+    },
+    {
+      "epoch": 0.41870824053452116,
+      "grad_norm": 0.5043487548828125,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.7663,
+      "step": 47
+    },
+    {
+      "epoch": 0.42761692650334077,
+      "grad_norm": 0.7439761757850647,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.8092,
+      "step": 48
+    },
+    {
+      "epoch": 0.4365256124721604,
+      "grad_norm": 1.6642370223999023,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.5948,
+      "step": 49
+    },
+    {
+      "epoch": 0.44543429844098,
+      "grad_norm": 4.350525379180908,
+      "learning_rate": 1e-05,
+      "loss": 2.0755,
+      "step": 50
+    },
+    {
+      "epoch": 0.44543429844098,
+      "eval_loss": 1.7232028245925903,
+      "eval_runtime": 1.3416,
+      "eval_samples_per_second": 37.27,
+      "eval_steps_per_second": 9.69,
+      "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": 5.314237029574246e+16,
+  "total_flos": 1.0621851957775565e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null