Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:492ed4d0f3818fed98de3941d658fb38acbf31c455cecf440ef3bd31dc1aa8ca
+oid sha256:4f3ad1b6d274eb43de17344f450870901cecff0de5ce02378f0e3ad778a78808
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19cefdfcc1d7ea228e608e70c7735f1de286d6cbf37a1f95e576bbe18a514c46
+oid sha256:96eb5df809f98f1c8285ca67dc9e1e03eaa162e9cd68aab5b3b54e9a96dcaf97
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ccd347f115ccc59633c278fa33d78abe6b2eebd3c57362efa5ddd352b18a332
+oid sha256:ab1a02c25ae1b5a3c377dea79611c33bf9c9892510a00f6c45a350ae5b11ba1e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57b873f25b7c40b681dafa8387cd8e9e2f59895e0037e461b5d6d069ea736025
+oid sha256:e731b52b1207956548a0612bd4d0a876059197b93a830f2c9449337dabe4f5a3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f40dafdc9b8905e0adc5975ad37db44938ec12cbb5083367d0c18f8bb459decf
+oid sha256:bc31abb2f678eab855914a64a004767f8ab3f3f751635436e3a9a084c389a54f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1426e2681fe60ef49172c0f2e14791560c2c5f9fb099a47c9c7d4e9b40f057af
+oid sha256:4d33e48563b3db6b784e0cb699a7a5e1672d6a25fe65a8bf05e45cb35f788ae0
 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": 0.0494825541973114,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.32102728731942215,
+  "best_metric": 0.04146807640790939,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6420545746388443,
   "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": 35.138,
       "eval_steps_per_second": 9.136,
       "step": 25
+    },
+    {
+      "epoch": 0.33386837881219905,
+      "grad_norm": 0.20905837416648865,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0245,
+      "step": 26
+    },
+    {
+      "epoch": 0.3467094703049759,
+      "grad_norm": 0.30377206206321716,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0387,
+      "step": 27
+    },
+    {
+      "epoch": 0.3595505617977528,
+      "grad_norm": 0.27176252007484436,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0467,
+      "step": 28
+    },
+    {
+      "epoch": 0.3723916532905297,
+      "grad_norm": 0.2371463179588318,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0226,
+      "step": 29
+    },
+    {
+      "epoch": 0.3852327447833066,
+      "grad_norm": 0.31079021096229553,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0387,
+      "step": 30
+    },
+    {
+      "epoch": 0.39807383627608345,
+      "grad_norm": 0.3452705442905426,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0517,
+      "step": 31
+    },
+    {
+      "epoch": 0.41091492776886035,
+      "grad_norm": 0.3658089339733124,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0658,
+      "step": 32
+    },
+    {
+      "epoch": 0.42375601926163725,
+      "grad_norm": 0.4322083294391632,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0681,
+      "step": 33
+    },
+    {
+      "epoch": 0.43659711075441415,
+      "grad_norm": 0.4732019305229187,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0646,
+      "step": 34
+    },
+    {
+      "epoch": 0.449438202247191,
+      "grad_norm": 0.4330652058124542,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0844,
+      "step": 35
+    },
+    {
+      "epoch": 0.4622792937399679,
+      "grad_norm": 0.7389253377914429,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0973,
+      "step": 36
+    },
+    {
+      "epoch": 0.4751203852327448,
+      "grad_norm": 0.49224039912223816,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.096,
+      "step": 37
+    },
+    {
+      "epoch": 0.48796147672552165,
+      "grad_norm": 0.13378825783729553,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0347,
+      "step": 38
+    },
+    {
+      "epoch": 0.5008025682182986,
+      "grad_norm": 0.2096407264471054,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0399,
+      "step": 39
+    },
+    {
+      "epoch": 0.5136436597110754,
+      "grad_norm": 0.16437120735645294,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0273,
+      "step": 40
+    },
+    {
+      "epoch": 0.5264847512038523,
+      "grad_norm": 0.18588468432426453,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0318,
+      "step": 41
+    },
+    {
+      "epoch": 0.5393258426966292,
+      "grad_norm": 0.27155569195747375,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0459,
+      "step": 42
+    },
+    {
+      "epoch": 0.5521669341894061,
+      "grad_norm": 0.29355552792549133,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.049,
+      "step": 43
+    },
+    {
+      "epoch": 0.565008025682183,
+      "grad_norm": 0.1788083165884018,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0402,
+      "step": 44
+    },
+    {
+      "epoch": 0.5778491171749599,
+      "grad_norm": 0.4135901927947998,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0646,
+      "step": 45
+    },
+    {
+      "epoch": 0.5906902086677368,
+      "grad_norm": 0.5709441900253296,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0726,
+      "step": 46
+    },
+    {
+      "epoch": 0.6035313001605136,
+      "grad_norm": 0.5146852135658264,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0611,
+      "step": 47
+    },
+    {
+      "epoch": 0.6163723916532905,
+      "grad_norm": 0.45884639024734497,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0695,
+      "step": 48
+    },
+    {
+      "epoch": 0.6292134831460674,
+      "grad_norm": 0.3609980046749115,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0776,
+      "step": 49
+    },
+    {
+      "epoch": 0.6420545746388443,
+      "grad_norm": 0.46642816066741943,
+      "learning_rate": 1e-05,
+      "loss": 0.079,
+      "step": 50
+    },
+    {
+      "epoch": 0.6420545746388443,
+      "eval_loss": 0.04146807640790939,
+      "eval_runtime": 1.4221,
+      "eval_samples_per_second": 35.16,
+      "eval_steps_per_second": 9.142,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null