Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21ac18204761817a8db30e7dfcf2a8b10843d191340691b5dead504363d30089
+oid sha256:aba11c915c402d27bffd35259eef830e4592e94db92d1a95cc63547b3f16ec44
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cd6f9197222099caec21c3ecd9a09613413ff737e3f8a6ae120a93fd9bac80d
+oid sha256:d18a44176098ad1b01bb71d82e990f61f74b2f8a88121c9b99af62ad7841384d
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e773604d360f5752189e2af255e78d0aba333070c93b97ce8e0708199e88fe9
+oid sha256:756d0e6d355c69ee792230965ba80f3f7918a4696bf3905b19ee6a4b81d905f3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e2da82098a9cef6adaa84537fb110aac2f6209bc7b39448e283f401be48cacc
+oid sha256:fb8b05e9aaa42da9a0b5ee94170967b06b90a9319531725becd952c2a5020200
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bb44373eebe454b7984038b0ebab6e39a4c1898602756e911ce6256c89546ac
+oid sha256:a98a5976433eea6faf84ad24b46dc776524fbed5ee6d6ba8d4ec9016accfbbbb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07367dcbfdaafa8c3e80bc9a548be50ddad47340733fe98569c3fe90485dea21
+oid sha256:3db4b46a46fe0be7765da6c82c483ce2fcdc8b8eb72af756282afd48055fda48
 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": 0.301417738199234,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2147074610842727,
+  "best_metric": 0.2479654848575592,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4294149221685454,
   "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": 15.018,
       "eval_steps_per_second": 3.905,
       "step": 25
+    },
+    {
+      "epoch": 0.22329575952764358,
+      "grad_norm": 5.314520835876465,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.3691,
+      "step": 26
+    },
+    {
+      "epoch": 0.2318840579710145,
+      "grad_norm": 1.5764119625091553,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.3472,
+      "step": 27
+    },
+    {
+      "epoch": 0.2404723564143854,
+      "grad_norm": 1.4415510892868042,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.343,
+      "step": 28
+    },
+    {
+      "epoch": 0.2490606548577563,
+      "grad_norm": 1.1646080017089844,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.3098,
+      "step": 29
+    },
+    {
+      "epoch": 0.2576489533011272,
+      "grad_norm": 0.6379237174987793,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.294,
+      "step": 30
+    },
+    {
+      "epoch": 0.26623725174449814,
+      "grad_norm": 0.4787558615207672,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.2771,
+      "step": 31
+    },
+    {
+      "epoch": 0.274825550187869,
+      "grad_norm": 1.1004618406295776,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.2637,
+      "step": 32
+    },
+    {
+      "epoch": 0.2834138486312399,
+      "grad_norm": 0.5449252128601074,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.2707,
+      "step": 33
+    },
+    {
+      "epoch": 0.29200214707461086,
+      "grad_norm": 1.1775004863739014,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.3555,
+      "step": 34
+    },
+    {
+      "epoch": 0.30059044551798175,
+      "grad_norm": 0.8506811857223511,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.2903,
+      "step": 35
+    },
+    {
+      "epoch": 0.30917874396135264,
+      "grad_norm": 1.2801744937896729,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.3428,
+      "step": 36
+    },
+    {
+      "epoch": 0.3177670424047236,
+      "grad_norm": 1.0148999691009521,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.3404,
+      "step": 37
+    },
+    {
+      "epoch": 0.3263553408480945,
+      "grad_norm": 0.9798362851142883,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.3151,
+      "step": 38
+    },
+    {
+      "epoch": 0.33494363929146537,
+      "grad_norm": 2.059889554977417,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.3205,
+      "step": 39
+    },
+    {
+      "epoch": 0.3435319377348363,
+      "grad_norm": 2.1281702518463135,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.3427,
+      "step": 40
+    },
+    {
+      "epoch": 0.3521202361782072,
+      "grad_norm": 0.7399386167526245,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.284,
+      "step": 41
+    },
+    {
+      "epoch": 0.3607085346215781,
+      "grad_norm": 0.8385106325149536,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.2985,
+      "step": 42
+    },
+    {
+      "epoch": 0.369296833064949,
+      "grad_norm": 0.4932496249675751,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.2779,
+      "step": 43
+    },
+    {
+      "epoch": 0.3778851315083199,
+      "grad_norm": 0.8921447396278381,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.3136,
+      "step": 44
+    },
+    {
+      "epoch": 0.3864734299516908,
+      "grad_norm": 0.7302391529083252,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.2885,
+      "step": 45
+    },
+    {
+      "epoch": 0.3950617283950617,
+      "grad_norm": 0.5096395015716553,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.2812,
+      "step": 46
+    },
+    {
+      "epoch": 0.40365002683843265,
+      "grad_norm": 0.7803435325622559,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.2857,
+      "step": 47
+    },
+    {
+      "epoch": 0.41223832528180354,
+      "grad_norm": 0.9682196378707886,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.3371,
+      "step": 48
+    },
+    {
+      "epoch": 0.42082662372517443,
+      "grad_norm": 1.1506094932556152,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.3735,
+      "step": 49
+    },
+    {
+      "epoch": 0.4294149221685454,
+      "grad_norm": 0.6556252837181091,
+      "learning_rate": 1e-05,
+      "loss": 0.3252,
+      "step": 50
+    },
+    {
+      "epoch": 0.4294149221685454,
+      "eval_loss": 0.2479654848575592,
+      "eval_runtime": 3.3272,
+      "eval_samples_per_second": 15.028,
+      "eval_steps_per_second": 3.907,
+      "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": 2.66009604784128e+17,
+  "total_flos": 5.32019209568256e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null