Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6339fae9c48408456c346945fe0ce661a465a3c8e2fa0b1b708d5bbe157b004c
+oid sha256:d2109a5c071062a63c01d2e468eabbf326c10a752f2848df31c483fde13a74da
 size 524363632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55e952ce5cd6800cd49bb4bf994d7c975551a5be6630a8d7e86e87f40c3b363c
+oid sha256:a1a3ad66aa45f362ca1082626ad6577055e9f94d2ea23476795078a4432d084f
 size 1049049122

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9a08c59a870384efb21be5ae8565bb280e5cde985da627ce7e72e4cae8ce06a
+oid sha256:59e66f18b84af6c04419840eb6bab9a08842b318954838fe85050d168de12ed5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6ff1dc5c2d74a3e3436f68f074ea64359d057304a6ffc4b658be01e8b48b1be
+oid sha256:c69fa505b73b0bba06f2daa5c830c4c8aa3e0cd64ce2540cace99cf0f85f8bd6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1df7eb7dd46edf1e7c1923856b2aae90734f9f3bd5f0d485c7f4563474e37e6e
+oid sha256:ba0cd26e33abdf0e3569a655e89bc5c1f780e20d5fb62add340854d118529cd9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ce988c185bdcdef249d707d1ba1eb6988bff954f55f39b63095122d742d70c0
+oid sha256:0ecffa98083d1fa7704b6f899a41465fcf713387d5c6779953fbb1c98eefb3de
 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": 1.4605278968811035,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.39603960396039606,
+  "best_metric": 1.4205576181411743,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7920792079207921,
   "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": 20.171,
       "eval_steps_per_second": 2.557,
       "step": 25
+    },
+    {
+      "epoch": 0.41188118811881186,
+      "grad_norm": 12.851859092712402,
+      "learning_rate": 5e-05,
+      "loss": 1.6169,
+      "step": 26
+    },
+    {
+      "epoch": 0.4277227722772277,
+      "grad_norm": 10.011022567749023,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.6847,
+      "step": 27
+    },
+    {
+      "epoch": 0.44356435643564357,
+      "grad_norm": 7.418447017669678,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.4793,
+      "step": 28
+    },
+    {
+      "epoch": 0.4594059405940594,
+      "grad_norm": 7.6047749519348145,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.4387,
+      "step": 29
+    },
+    {
+      "epoch": 0.4752475247524752,
+      "grad_norm": 7.529312610626221,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.2696,
+      "step": 30
+    },
+    {
+      "epoch": 0.4910891089108911,
+      "grad_norm": 5.887645244598389,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2813,
+      "step": 31
+    },
+    {
+      "epoch": 0.5069306930693069,
+      "grad_norm": 4.471807479858398,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2555,
+      "step": 32
+    },
+    {
+      "epoch": 0.5227722772277228,
+      "grad_norm": 4.865562915802002,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.3376,
+      "step": 33
+    },
+    {
+      "epoch": 0.5386138613861386,
+      "grad_norm": 4.343969345092773,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.3163,
+      "step": 34
+    },
+    {
+      "epoch": 0.5544554455445545,
+      "grad_norm": 4.894163608551025,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.3629,
+      "step": 35
+    },
+    {
+      "epoch": 0.5702970297029702,
+      "grad_norm": 5.443630695343018,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.3183,
+      "step": 36
+    },
+    {
+      "epoch": 0.5861386138613861,
+      "grad_norm": 9.0098876953125,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.4488,
+      "step": 37
+    },
+    {
+      "epoch": 0.601980198019802,
+      "grad_norm": 6.921519756317139,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.5777,
+      "step": 38
+    },
+    {
+      "epoch": 0.6178217821782178,
+      "grad_norm": 8.694135665893555,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.6112,
+      "step": 39
+    },
+    {
+      "epoch": 0.6336633663366337,
+      "grad_norm": 6.186464786529541,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.5085,
+      "step": 40
+    },
+    {
+      "epoch": 0.6495049504950495,
+      "grad_norm": 5.976185321807861,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.3798,
+      "step": 41
+    },
+    {
+      "epoch": 0.6653465346534654,
+      "grad_norm": 5.398346900939941,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3313,
+      "step": 42
+    },
+    {
+      "epoch": 0.6811881188118812,
+      "grad_norm": 4.827998161315918,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.3266,
+      "step": 43
+    },
+    {
+      "epoch": 0.697029702970297,
+      "grad_norm": 4.136651515960693,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3478,
+      "step": 44
+    },
+    {
+      "epoch": 0.7128712871287128,
+      "grad_norm": 4.079899787902832,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.2925,
+      "step": 45
+    },
+    {
+      "epoch": 0.7287128712871287,
+      "grad_norm": 4.743795871734619,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.3243,
+      "step": 46
+    },
+    {
+      "epoch": 0.7445544554455445,
+      "grad_norm": 5.614559173583984,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.3783,
+      "step": 47
+    },
+    {
+      "epoch": 0.7603960396039604,
+      "grad_norm": 5.586382865905762,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.4069,
+      "step": 48
+    },
+    {
+      "epoch": 0.7762376237623763,
+      "grad_norm": 7.032140254974365,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.3624,
+      "step": 49
+    },
+    {
+      "epoch": 0.7920792079207921,
+      "grad_norm": 10.226324081420898,
+      "learning_rate": 0.0,
+      "loss": 1.3784,
+      "step": 50
+    },
+    {
+      "epoch": 0.7920792079207921,
+      "eval_loss": 1.4205576181411743,
+      "eval_runtime": 21.0936,
+      "eval_samples_per_second": 20.196,
+      "eval_steps_per_second": 2.56,
+      "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": 5.476375360176128e+17,
+  "total_flos": 1.0952750720352256e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null