Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60935b627a9ed2610fa28e182e3d49adb2b30cde73176ea32b8e608f44e110ed
+oid sha256:2daff8bef14a3a7f18aef788d23d105d9a6b4013ddbc33e25a21b4b78926cc0d
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9afe5f574f97af0cddf2491317e00cc7eca7092596bdedb779ec3845bd24d44a
+oid sha256:59b09fc4799402b9800aa1c092e049bc2cb0c12ebbb99dff70e3ace020030c0d
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eac6a9b45301a828466e95e93a6c8436099f897bd712441356a35ab0271da45d
+oid sha256:da2598d7b767fcdba4cfaf32bf10ea3638827fe8bce8cdae7133cb6181e7fdac
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4b0d4a7a991d063db3c0bd8548d64374cb73900906199a11ea9285159802010
+oid sha256:4c98e7ef1d557929c05a7e5c1f4dfadf01669b8e4bb18df7ae7eb9df4020ccdf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd0c4ade609d7efd614d2380ddcd3fc0e8cc065b772175935f1f230ac9544ba6
+oid sha256:9af2d682bf66953b5e8c0897bb9dad2ec138225de6acf53815b3b8761f594cc8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fb930150d154d1df15ad1bd31939f15d49bf503a3dff35d6623ea392832cda3
+oid sha256:2864979444a6fcfb905515dfeb06cf89c5b17104f06c0e146e3e9b421af63d46
 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": 0.3329227864742279,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3005259203606311,
+  "best_metric": 0.17765101790428162,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6010518407212622,
   "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": 15.529,
       "eval_steps_per_second": 4.038,
       "step": 25
+    },
+    {
+      "epoch": 0.3125469571750564,
+      "grad_norm": 1.4042689800262451,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.858,
+      "step": 26
+    },
+    {
+      "epoch": 0.3245679939894816,
+      "grad_norm": 0.9543754458427429,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.2523,
+      "step": 27
+    },
+    {
+      "epoch": 0.33658903080390684,
+      "grad_norm": 0.7887716293334961,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.183,
+      "step": 28
+    },
+    {
+      "epoch": 0.3486100676183321,
+      "grad_norm": 0.5809823274612427,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.1227,
+      "step": 29
+    },
+    {
+      "epoch": 0.3606311044327573,
+      "grad_norm": 0.5213009715080261,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.1021,
+      "step": 30
+    },
+    {
+      "epoch": 0.37265214124718254,
+      "grad_norm": 0.7495287656784058,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.1105,
+      "step": 31
+    },
+    {
+      "epoch": 0.38467317806160783,
+      "grad_norm": 0.7786484956741333,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.1269,
+      "step": 32
+    },
+    {
+      "epoch": 0.39669421487603307,
+      "grad_norm": 0.9299702644348145,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.1516,
+      "step": 33
+    },
+    {
+      "epoch": 0.4087152516904583,
+      "grad_norm": 0.7013904452323914,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0962,
+      "step": 34
+    },
+    {
+      "epoch": 0.42073628850488354,
+      "grad_norm": 0.7207347750663757,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.1143,
+      "step": 35
+    },
+    {
+      "epoch": 0.43275732531930877,
+      "grad_norm": 1.1033786535263062,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.1311,
+      "step": 36
+    },
+    {
+      "epoch": 0.44477836213373406,
+      "grad_norm": 1.0275310277938843,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.11,
+      "step": 37
+    },
+    {
+      "epoch": 0.4567993989481593,
+      "grad_norm": 1.1997830867767334,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.747,
+      "step": 38
+    },
+    {
+      "epoch": 0.46882043576258453,
+      "grad_norm": 1.128527045249939,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.1777,
+      "step": 39
+    },
+    {
+      "epoch": 0.48084147257700977,
+      "grad_norm": 1.0002365112304688,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.167,
+      "step": 40
+    },
+    {
+      "epoch": 0.492862509391435,
+      "grad_norm": 0.6199818253517151,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.088,
+      "step": 41
+    },
+    {
+      "epoch": 0.5048835462058603,
+      "grad_norm": 0.7970647215843201,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.1077,
+      "step": 42
+    },
+    {
+      "epoch": 0.5169045830202855,
+      "grad_norm": 1.1322096586227417,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.1165,
+      "step": 43
+    },
+    {
+      "epoch": 0.5289256198347108,
+      "grad_norm": 0.6188007593154907,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0835,
+      "step": 44
+    },
+    {
+      "epoch": 0.540946656649136,
+      "grad_norm": 0.9790140986442566,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0758,
+      "step": 45
+    },
+    {
+      "epoch": 0.5529676934635612,
+      "grad_norm": 0.5559037923812866,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0812,
+      "step": 46
+    },
+    {
+      "epoch": 0.5649887302779865,
+      "grad_norm": 0.7460304498672485,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0698,
+      "step": 47
+    },
+    {
+      "epoch": 0.5770097670924117,
+      "grad_norm": 0.6634911894798279,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0954,
+      "step": 48
+    },
+    {
+      "epoch": 0.5890308039068369,
+      "grad_norm": 0.8137192726135254,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0842,
+      "step": 49
+    },
+    {
+      "epoch": 0.6010518407212622,
+      "grad_norm": 0.7482524514198303,
+      "learning_rate": 1e-05,
+      "loss": 0.1316,
+      "step": 50
+    },
+    {
+      "epoch": 0.6010518407212622,
+      "eval_loss": 0.17765101790428162,
+      "eval_runtime": 3.227,
+      "eval_samples_per_second": 15.494,
+      "eval_steps_per_second": 4.028,
+      "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": 2.8788146052477747e+17,
+  "total_flos": 5.776961889086996e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null