Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8355022cd7a86577a40a12cd390397b67da16490fb7ab4a62e7bf6998f908420
+oid sha256:e1cf97e430d3f07c2af17baabe54ca1cbf0236a21430be2020b7429d89405f3d
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b38cefed6e18f7a2765d6fe623c51f21de512e9364817cd8dbbe5429529eea9b
+oid sha256:9c7fc26f2fd03f6a2277c5f0b94b0deda38f016c490f4e5555ed264eb907fcbb
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28f4de291e4352286061731c17e575abeecf8d7baaf5c33f658c817011780d65
+oid sha256:ec69236fb94f13a8ad2901585fd98e35f95509200a554d4cb2597322b002c7ef
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fadb089e146735105c15430f881e49623fa01865697418e3410b50112bc84b99
+oid sha256:04d7d8bea2588335943537315e40fffcfad2348c34d33f785bb18d6628189537
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b802bda4436202901d91a7327c49a8bf96329884e28c240cb0a6ebb364145744
+oid sha256:d581c9f2523397f008773a0a4724190f2dca4a0435b7a4d26078c6e174cd0dc9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2937edcf09605a52b4092d62064291b2091e02eaf6e2950cd45f1e2a765a88f6
+oid sha256:49883bf2758759a7631ba9a614c6b208054e7b91892884f8b515a2b4fc490d37
 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": 0.6047177314758301,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.011113580795732384,
+  "best_metric": 0.5870347023010254,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.02222716159146477,
   "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": 14.374,
       "eval_steps_per_second": 3.737,
       "step": 25
+    },
+    {
+      "epoch": 0.01155812402756168,
+      "grad_norm": 0.14327451586723328,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.6614,
+      "step": 26
+    },
+    {
+      "epoch": 0.012002667259390976,
+      "grad_norm": 0.1515110284090042,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.6824,
+      "step": 27
+    },
+    {
+      "epoch": 0.012447210491220271,
+      "grad_norm": 0.15741868317127228,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.6585,
+      "step": 28
+    },
+    {
+      "epoch": 0.012891753723049567,
+      "grad_norm": 0.17712979018688202,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.6518,
+      "step": 29
+    },
+    {
+      "epoch": 0.013336296954878863,
+      "grad_norm": 0.1943611204624176,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.6639,
+      "step": 30
+    },
+    {
+      "epoch": 0.013780840186708157,
+      "grad_norm": 0.19372722506523132,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.6339,
+      "step": 31
+    },
+    {
+      "epoch": 0.014225383418537452,
+      "grad_norm": 0.17396874725818634,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.5713,
+      "step": 32
+    },
+    {
+      "epoch": 0.014669926650366748,
+      "grad_norm": 0.16710332036018372,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.615,
+      "step": 33
+    },
+    {
+      "epoch": 0.015114469882196044,
+      "grad_norm": 0.16157880425453186,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.5574,
+      "step": 34
+    },
+    {
+      "epoch": 0.01555901311402534,
+      "grad_norm": 0.16557228565216064,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.5262,
+      "step": 35
+    },
+    {
+      "epoch": 0.016003556345854635,
+      "grad_norm": 0.18180273473262787,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.5055,
+      "step": 36
+    },
+    {
+      "epoch": 0.01644809957768393,
+      "grad_norm": 0.25119903683662415,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.4996,
+      "step": 37
+    },
+    {
+      "epoch": 0.016892642809513227,
+      "grad_norm": 0.16843101382255554,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.7076,
+      "step": 38
+    },
+    {
+      "epoch": 0.01733718604134252,
+      "grad_norm": 0.139786958694458,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.676,
+      "step": 39
+    },
+    {
+      "epoch": 0.017781729273171815,
+      "grad_norm": 0.13475798070430756,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.6726,
+      "step": 40
+    },
+    {
+      "epoch": 0.018226272505001112,
+      "grad_norm": 0.13363976776599884,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.6386,
+      "step": 41
+    },
+    {
+      "epoch": 0.018670815736830406,
+      "grad_norm": 0.12477023899555206,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.6495,
+      "step": 42
+    },
+    {
+      "epoch": 0.019115358968659703,
+      "grad_norm": 0.12433835864067078,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.6185,
+      "step": 43
+    },
+    {
+      "epoch": 0.019559902200488997,
+      "grad_norm": 0.135418102145195,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.6286,
+      "step": 44
+    },
+    {
+      "epoch": 0.02000444543231829,
+      "grad_norm": 0.1305476576089859,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.5891,
+      "step": 45
+    },
+    {
+      "epoch": 0.02044898866414759,
+      "grad_norm": 0.1284274160861969,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.5447,
+      "step": 46
+    },
+    {
+      "epoch": 0.020893531895976883,
+      "grad_norm": 0.1395895779132843,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.5439,
+      "step": 47
+    },
+    {
+      "epoch": 0.02133807512780618,
+      "grad_norm": 0.1462106853723526,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.4906,
+      "step": 48
+    },
+    {
+      "epoch": 0.021782618359635474,
+      "grad_norm": 0.16900724172592163,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.518,
+      "step": 49
+    },
+    {
+      "epoch": 0.02222716159146477,
+      "grad_norm": 0.34547173976898193,
+      "learning_rate": 1e-05,
+      "loss": 0.5824,
+      "step": 50
+    },
+    {
+      "epoch": 0.02222716159146477,
+      "eval_loss": 0.5870347023010254,
+      "eval_runtime": 3.4885,
+      "eval_samples_per_second": 14.333,
+      "eval_steps_per_second": 3.727,
+      "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": 2.9859068337822106e+17,
+  "total_flos": 5.975543717811978e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null