Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:702fe99f36f83c43342143ea5919ee830a41551aff2853daa2f847cbe68ed48a
+oid sha256:9bba3b404f1f7f41cd51b82c02faaf1ca610f74d12cdf82dfbd4ad33d4026be9
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9507077eb7c793310022dc7ab36af9c2cf0c390f21e6f17922779c3f48d5f4ff
+oid sha256:5d2304eaf3ba8cf75f89be9467f4ff2dfbcb3bae6f46ae561cce8e6fbf1ea381
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1704c7d79e57f529890ba4fd36adc96e050e486957b3c4a022d85e51dcf2b3
+oid sha256:3c34362211b896329df853aff031e90c5ad76fb014ee6d3ce9a13deb093ffcb6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50ef5377787762b62a101b102056f607ba202ff0e66ef708b1a2a61ffe65b095
+oid sha256:44bd50abd9603165d7f5fb207e5bcb0f69404c0ef85e664a81d66484c86678a3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4765e5c06cc4bb277b640f673fd7e2dd0ac0494904be5a35a98484d60f5fa52b
+oid sha256:609704ef8aba962751f0b62eed73ecebc3b11d383cc4b406570e56e777b0d7cd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a57cb6d910eef619b3e7c500f902c0f71f7c05a1338eb5c1d6c6ec244c425f8e
+oid sha256:05a411dca0680adb438448151cb4cb815a6e477f52e8c610d3c27743d5448836
 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": 10.358295440673828,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.007772649987855235,
+  "best_metric": 10.356054306030273,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.01554529997571047,
   "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": 304.125,
       "eval_steps_per_second": 79.073,
       "step": 25
+    },
+    {
+      "epoch": 0.008083555987369444,
+      "grad_norm": 0.04640369117259979,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3664,
+      "step": 26
+    },
+    {
+      "epoch": 0.008394461986883654,
+      "grad_norm": 0.04907889664173126,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.3663,
+      "step": 27
+    },
+    {
+      "epoch": 0.008705367986397863,
+      "grad_norm": 0.049038540571928024,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3648,
+      "step": 28
+    },
+    {
+      "epoch": 0.009016273985912072,
+      "grad_norm": 0.05122429132461548,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3664,
+      "step": 29
+    },
+    {
+      "epoch": 0.009327179985426282,
+      "grad_norm": 0.06270774453878403,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.3653,
+      "step": 30
+    },
+    {
+      "epoch": 0.009638085984940491,
+      "grad_norm": 0.06517155468463898,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.3642,
+      "step": 31
+    },
+    {
+      "epoch": 0.0099489919844547,
+      "grad_norm": 0.07292282581329346,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3632,
+      "step": 32
+    },
+    {
+      "epoch": 0.010259897983968909,
+      "grad_norm": 0.07600072771310806,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.3613,
+      "step": 33
+    },
+    {
+      "epoch": 0.010570803983483118,
+      "grad_norm": 0.08401823788881302,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.3627,
+      "step": 34
+    },
+    {
+      "epoch": 0.010881709982997327,
+      "grad_norm": 0.08103804290294647,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.361,
+      "step": 35
+    },
+    {
+      "epoch": 0.011192615982511537,
+      "grad_norm": 0.10982982069253922,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.3584,
+      "step": 36
+    },
+    {
+      "epoch": 0.011503521982025746,
+      "grad_norm": 0.11374383419752121,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3544,
+      "step": 37
+    },
+    {
+      "epoch": 0.011814427981539956,
+      "grad_norm": 0.06625819206237793,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3624,
+      "step": 38
+    },
+    {
+      "epoch": 0.012125333981054165,
+      "grad_norm": 0.05948749557137489,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.3643,
+      "step": 39
+    },
+    {
+      "epoch": 0.012436239980568375,
+      "grad_norm": 0.05686202272772789,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.3667,
+      "step": 40
+    },
+    {
+      "epoch": 0.012747145980082584,
+      "grad_norm": 0.06398730725049973,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.3646,
+      "step": 41
+    },
+    {
+      "epoch": 0.013058051979596794,
+      "grad_norm": 0.0700625479221344,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.3624,
+      "step": 42
+    },
+    {
+      "epoch": 0.013368957979111003,
+      "grad_norm": 0.06388375163078308,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.3595,
+      "step": 43
+    },
+    {
+      "epoch": 0.013679863978625213,
+      "grad_norm": 0.07169952243566513,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.363,
+      "step": 44
+    },
+    {
+      "epoch": 0.013990769978139422,
+      "grad_norm": 0.06670381873846054,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.361,
+      "step": 45
+    },
+    {
+      "epoch": 0.014301675977653631,
+      "grad_norm": 0.08351664245128632,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.3558,
+      "step": 46
+    },
+    {
+      "epoch": 0.014612581977167841,
+      "grad_norm": 0.07962903380393982,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.3576,
+      "step": 47
+    },
+    {
+      "epoch": 0.01492348797668205,
+      "grad_norm": 0.09934556484222412,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.3547,
+      "step": 48
+    },
+    {
+      "epoch": 0.01523439397619626,
+      "grad_norm": 0.11625286936759949,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.3543,
+      "step": 49
+    },
+    {
+      "epoch": 0.01554529997571047,
+      "grad_norm": 0.15434855222702026,
+      "learning_rate": 1e-05,
+      "loss": 10.3445,
+      "step": 50
+    },
+    {
+      "epoch": 0.01554529997571047,
+      "eval_loss": 10.356054306030273,
+      "eval_runtime": 0.1673,
+      "eval_samples_per_second": 298.888,
+      "eval_steps_per_second": 77.711,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null