Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3246faf763357e9f816c942f335cbe285bc2d6b4e4731229ea88bf4b79566bac
+oid sha256:64cc518d132db7e630018ddde2c6c267c96c7f21cd9f5eb75386578f142d2aa6
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bc16b474ee41a3badf4b7791364c8b0c7491dbd26c90e197b844415523bc95f
+oid sha256:e0656b273cf60d2f853c8fd5860cc8846206a736d12e96dc8eee06dc14a8d60d
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1e035883ee723cd2c3bb42899bf212b86def1b99a0f1df52f9b0aa66ca48f42
+oid sha256:a4910b99839680a89acc2139e7d1e9760455dd4430daa792c894ec2b317bf879
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb8fb862c9b908eaab657db91ecb400eb9c1268bcb22d420464aa831a31a69b3
+oid sha256:2d4b2a34452a5bb6a4b590b3dfe9a8911dad5b75fa99613b0fbf21dcd208fa4a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31a4479786407903d6cfeed2fa41dab6ef3954acad9a1025d729451281cf3fa3
+oid sha256:64cecadba20b5a6121c71a8ecde01cfde1232ded456bc761423ad94323f83fc6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1291acdbfee5b1912145f377b4cc6ed551954e3d35b2dbe2cb095c3110bd698
+oid sha256:190b4952883ff7fc4d32ae6b3f7f4e96c8c326564fb8512b56f4a44c8356a4c4
 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": 1.201508641242981,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006404560046753288,
+  "best_metric": 1.1384953260421753,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.012809120093506576,
   "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": 32.847,
       "eval_steps_per_second": 8.54,
       "step": 25
+    },
+    {
+      "epoch": 0.0066607424486234195,
+      "grad_norm": 0.7317392826080322,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.7792,
+      "step": 26
+    },
+    {
+      "epoch": 0.006916924850493551,
+      "grad_norm": 1.2366492748260498,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.0891,
+      "step": 27
+    },
+    {
+      "epoch": 0.007173107252363683,
+      "grad_norm": 1.2961385250091553,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.6581,
+      "step": 28
+    },
+    {
+      "epoch": 0.007429289654233814,
+      "grad_norm": 1.205391764640808,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.2327,
+      "step": 29
+    },
+    {
+      "epoch": 0.007685472056103946,
+      "grad_norm": 1.108265995979309,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.1861,
+      "step": 30
+    },
+    {
+      "epoch": 0.007941654457974078,
+      "grad_norm": 0.9121682047843933,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.156,
+      "step": 31
+    },
+    {
+      "epoch": 0.00819783685984421,
+      "grad_norm": 0.7840728759765625,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.0705,
+      "step": 32
+    },
+    {
+      "epoch": 0.008454019261714341,
+      "grad_norm": 0.7209661602973938,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.0062,
+      "step": 33
+    },
+    {
+      "epoch": 0.008710201663584473,
+      "grad_norm": 0.5964431166648865,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.9278,
+      "step": 34
+    },
+    {
+      "epoch": 0.008966384065454604,
+      "grad_norm": 0.5967997312545776,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.8185,
+      "step": 35
+    },
+    {
+      "epoch": 0.009222566467324736,
+      "grad_norm": 0.5782707929611206,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.7699,
+      "step": 36
+    },
+    {
+      "epoch": 0.009478748869194868,
+      "grad_norm": 1.7378571033477783,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.0288,
+      "step": 37
+    },
+    {
+      "epoch": 0.009734931271064999,
+      "grad_norm": 0.5410066843032837,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.7,
+      "step": 38
+    },
+    {
+      "epoch": 0.00999111367293513,
+      "grad_norm": 0.7376120686531067,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.2896,
+      "step": 39
+    },
+    {
+      "epoch": 0.010247296074805262,
+      "grad_norm": 0.8110925555229187,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.8188,
+      "step": 40
+    },
+    {
+      "epoch": 0.010503478476675394,
+      "grad_norm": 0.7669232487678528,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.3056,
+      "step": 41
+    },
+    {
+      "epoch": 0.010759660878545525,
+      "grad_norm": 0.7149698734283447,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.138,
+      "step": 42
+    },
+    {
+      "epoch": 0.011015843280415655,
+      "grad_norm": 0.6171885132789612,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.1505,
+      "step": 43
+    },
+    {
+      "epoch": 0.011272025682285787,
+      "grad_norm": 0.5427089333534241,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.0181,
+      "step": 44
+    },
+    {
+      "epoch": 0.011528208084155918,
+      "grad_norm": 0.41735145449638367,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.9324,
+      "step": 45
+    },
+    {
+      "epoch": 0.01178439048602605,
+      "grad_norm": 0.4027903079986572,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.9263,
+      "step": 46
+    },
+    {
+      "epoch": 0.012040572887896181,
+      "grad_norm": 0.41988879442214966,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.8873,
+      "step": 47
+    },
+    {
+      "epoch": 0.012296755289766313,
+      "grad_norm": 0.45334821939468384,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.8117,
+      "step": 48
+    },
+    {
+      "epoch": 0.012552937691636444,
+      "grad_norm": 0.7448716759681702,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.9191,
+      "step": 49
+    },
+    {
+      "epoch": 0.012809120093506576,
+      "grad_norm": 1.5897629261016846,
+      "learning_rate": 1e-05,
+      "loss": 0.9977,
+      "step": 50
+    },
+    {
+      "epoch": 0.012809120093506576,
+      "eval_loss": 1.1384953260421753,
+      "eval_runtime": 1.5387,
+      "eval_samples_per_second": 32.495,
+      "eval_steps_per_second": 8.449,
+      "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": 1,
   "trial_name": null,
   "trial_params": null