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:a9747c23a05c88d7f76bae3f03f29332f6098a1f4628f1c2346cee8833a20465
+oid sha256:3bb628016e74b02d3bee7b359790a91071c0cc264eb27cf686bfa114cee0bc0b
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98279ca4dc9898afd247b0ba19272e30f51ecf0c94b7d70e78535c7d867703f1
+oid sha256:d7bc94992315f85bfe1d9a769ae86c111703a9a4810d32f344be7d9c1df8ed8a
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a1180e8d462a8fb3b7d2796d532d58931636ddbfa6314113159302ebaeb2e25
+oid sha256:c2779fddc8c9d9349746edda01f05abbcee851a3f4c5898577ea5a79af0027c0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fc362792d450222c8d4caf10a8ae36ce980d0159692fc9515b7a3d1e03bab8d
+oid sha256:3ea1b1661df80a8bb2bb95b52a6ca54ee5a313f779417793e49378d7d7bbd70a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2475b561b34afeb0ff9d3c233ce3e175b13c6f8d757b911c351c80954a47527e
+oid sha256:b8332caf65a69dbb7875f8f82eba5be590b447b98dedcc7e62e38a48cac75571
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fea52ec44a1dbf25c8b096168be1ebd439a78d74f616fc4468e13d985e6de830
+oid sha256:4b3efbaf5f8055efbe738d527ead4e6b4cc4bce4e44f6e5bce0b08217482ebc5
 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": 0.22734582424163818,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.009680307833789115,
+  "best_metric": 0.12096888571977615,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.01936061566757823,
   "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": 66.752,
       "eval_steps_per_second": 17.356,
       "step": 25
+    },
+    {
+      "epoch": 0.01006752014714068,
+      "grad_norm": 20.296913146972656,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.5689,
+      "step": 26
+    },
+    {
+      "epoch": 0.010454732460492243,
+      "grad_norm": 16.466005325317383,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.3623,
+      "step": 27
+    },
+    {
+      "epoch": 0.010841944773843808,
+      "grad_norm": 11.937307357788086,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.1949,
+      "step": 28
+    },
+    {
+      "epoch": 0.011229157087195372,
+      "grad_norm": 4.361509799957275,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0386,
+      "step": 29
+    },
+    {
+      "epoch": 0.011616369400546937,
+      "grad_norm": 0.3395012319087982,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0033,
+      "step": 30
+    },
+    {
+      "epoch": 0.012003581713898502,
+      "grad_norm": 0.09539712965488434,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.001,
+      "step": 31
+    },
+    {
+      "epoch": 0.012390794027250067,
+      "grad_norm": 0.04306734725832939,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0005,
+      "step": 32
+    },
+    {
+      "epoch": 0.012778006340601632,
+      "grad_norm": 0.02652687579393387,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0003,
+      "step": 33
+    },
+    {
+      "epoch": 0.013165218653953197,
+      "grad_norm": 0.01844121888279915,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0002,
+      "step": 34
+    },
+    {
+      "epoch": 0.01355243096730476,
+      "grad_norm": 0.01470676064491272,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0002,
+      "step": 35
+    },
+    {
+      "epoch": 0.013939643280656324,
+      "grad_norm": 5.602317810058594,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.3781,
+      "step": 36
+    },
+    {
+      "epoch": 0.01432685559400789,
+      "grad_norm": 14.764276504516602,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.0644,
+      "step": 37
+    },
+    {
+      "epoch": 0.014714067907359454,
+      "grad_norm": 9.552111625671387,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.1546,
+      "step": 38
+    },
+    {
+      "epoch": 0.015101280220711019,
+      "grad_norm": 0.046891260892152786,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0006,
+      "step": 39
+    },
+    {
+      "epoch": 0.015488492534062584,
+      "grad_norm": 0.07456453889608383,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0009,
+      "step": 40
+    },
+    {
+      "epoch": 0.015875704847414147,
+      "grad_norm": 0.10584703087806702,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0013,
+      "step": 41
+    },
+    {
+      "epoch": 0.01626291716076571,
+      "grad_norm": 0.13033287227153778,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0017,
+      "step": 42
+    },
+    {
+      "epoch": 0.016650129474117276,
+      "grad_norm": 0.14958032965660095,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.002,
+      "step": 43
+    },
+    {
+      "epoch": 0.01703734178746884,
+      "grad_norm": 0.15836258232593536,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0021,
+      "step": 44
+    },
+    {
+      "epoch": 0.017424554100820406,
+      "grad_norm": 0.1604108363389969,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0022,
+      "step": 45
+    },
+    {
+      "epoch": 0.01781176641417197,
+      "grad_norm": 0.15006719529628754,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.002,
+      "step": 46
+    },
+    {
+      "epoch": 0.018198978727523536,
+      "grad_norm": 0.13892512023448944,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0019,
+      "step": 47
+    },
+    {
+      "epoch": 0.0185861910408751,
+      "grad_norm": 0.12713688611984253,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0017,
+      "step": 48
+    },
+    {
+      "epoch": 0.018973403354226665,
+      "grad_norm": 8.707756996154785,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.5475,
+      "step": 49
+    },
+    {
+      "epoch": 0.01936061566757823,
+      "grad_norm": 8.732000350952148,
+      "learning_rate": 1e-05,
+      "loss": 0.5323,
+      "step": 50
+    },
+    {
+      "epoch": 0.01936061566757823,
+      "eval_loss": 0.12096888571977615,
+      "eval_runtime": 0.7605,
+      "eval_samples_per_second": 65.748,
+      "eval_steps_per_second": 17.094,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null