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:e714f62a4f1a827c607e1c046e63c59e058ba827649a48754737aef11a8ad263
+oid sha256:372ccc5c54daf0e20ec682c32418bdebb829f427e45cdd1ba9e761cbebc99daf
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a73fe8d1e64592c12c52cdb2caa456dbfaaa3dfae6d817cf8e80cc4566f38ea
+oid sha256:8e1bcbcb6d0349043f8b3177604d41412a336920391cee1c4e461fd52aa183bc
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b2b605a18c1e9d63d97caa633ca6cdf7fa315a19bd5f3f8301d23fea752cd12
+oid sha256:1538f2cd2957ef98135cec1c4a54138120da2b7d38f64a09bb2b20307c8e6ddf
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e07727f4cecbed94107f85752e660f57e83c883c36640902031fc5d7b9d64556
+oid sha256:d5eb4d267055605afac182d860e34e417b0da17fabe58e5211cf88746415064e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac40af53413e53de4b6563446478531305622daad92d9626b700d5c10486c5f7
+oid sha256:95d5754518ebc0a14f24e1b0af319cd8f60383c25e9c966f77e677b5dba8542a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59e1e4342fce77db7aeed234833fa0869f9f95e61e583ebcba2f612091b59311
+oid sha256:ba98f41635f875652bb28a7885c315c4c7cb9e45af0861f44e949259e2dbf899
 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": 0.3346240222454071,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06743088334457181,
+  "best_metric": 0.31840619444847107,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13486176668914363,
   "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": 16.905,
       "eval_steps_per_second": 4.395,
       "step": 25
+    },
+    {
+      "epoch": 0.07012811867835468,
+      "grad_norm": 2.3370919227600098,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.5921,
+      "step": 26
+    },
+    {
+      "epoch": 0.07282535401213756,
+      "grad_norm": 3.2230148315429688,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.3536,
+      "step": 27
+    },
+    {
+      "epoch": 0.07552258934592043,
+      "grad_norm": 2.93990159034729,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 4.2959,
+      "step": 28
+    },
+    {
+      "epoch": 0.0782198246797033,
+      "grad_norm": 3.1565818786621094,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.6705,
+      "step": 29
+    },
+    {
+      "epoch": 0.08091706001348618,
+      "grad_norm": 3.6498372554779053,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 5.1664,
+      "step": 30
+    },
+    {
+      "epoch": 0.08361429534726905,
+      "grad_norm": 3.4346346855163574,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 5.2198,
+      "step": 31
+    },
+    {
+      "epoch": 0.08631153068105192,
+      "grad_norm": 3.956606149673462,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 5.5977,
+      "step": 32
+    },
+    {
+      "epoch": 0.08900876601483479,
+      "grad_norm": 3.851478099822998,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 5.6571,
+      "step": 33
+    },
+    {
+      "epoch": 0.09170600134861767,
+      "grad_norm": 4.546712875366211,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 6.7095,
+      "step": 34
+    },
+    {
+      "epoch": 0.09440323668240054,
+      "grad_norm": 3.8208866119384766,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 5.8349,
+      "step": 35
+    },
+    {
+      "epoch": 0.09710047201618341,
+      "grad_norm": 4.768429279327393,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 7.5512,
+      "step": 36
+    },
+    {
+      "epoch": 0.09979770734996629,
+      "grad_norm": 5.413884162902832,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 7.3688,
+      "step": 37
+    },
+    {
+      "epoch": 0.10249494268374916,
+      "grad_norm": 4.375186443328857,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 5.5095,
+      "step": 38
+    },
+    {
+      "epoch": 0.10519217801753203,
+      "grad_norm": 3.01485276222229,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 4.156,
+      "step": 39
+    },
+    {
+      "epoch": 0.1078894133513149,
+      "grad_norm": 2.998155355453491,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.4575,
+      "step": 40
+    },
+    {
+      "epoch": 0.11058664868509778,
+      "grad_norm": 3.271318197250366,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 4.4771,
+      "step": 41
+    },
+    {
+      "epoch": 0.11328388401888065,
+      "grad_norm": 3.5302789211273193,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 5.1778,
+      "step": 42
+    },
+    {
+      "epoch": 0.11598111935266352,
+      "grad_norm": 3.289346694946289,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 4.9498,
+      "step": 43
+    },
+    {
+      "epoch": 0.11867835468644639,
+      "grad_norm": 3.5944786071777344,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 5.2595,
+      "step": 44
+    },
+    {
+      "epoch": 0.12137559002022927,
+      "grad_norm": 3.664254665374756,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 5.761,
+      "step": 45
+    },
+    {
+      "epoch": 0.12407282535401214,
+      "grad_norm": 3.8446664810180664,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 5.475,
+      "step": 46
+    },
+    {
+      "epoch": 0.126770060687795,
+      "grad_norm": 4.252958297729492,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 6.1862,
+      "step": 47
+    },
+    {
+      "epoch": 0.1294672960215779,
+      "grad_norm": 4.536473751068115,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 6.3884,
+      "step": 48
+    },
+    {
+      "epoch": 0.13216453135536074,
+      "grad_norm": 5.003567218780518,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 6.9914,
+      "step": 49
+    },
+    {
+      "epoch": 0.13486176668914363,
+      "grad_norm": 6.126743316650391,
+      "learning_rate": 1e-05,
+      "loss": 9.3718,
+      "step": 50
+    },
+    {
+      "epoch": 0.13486176668914363,
+      "eval_loss": 0.31840619444847107,
+      "eval_runtime": 2.9606,
+      "eval_samples_per_second": 16.889,
+      "eval_steps_per_second": 4.391,
+      "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": 2.629552387915776e+17,
+  "total_flos": 5.259104775831552e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null