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:f242548cf888e100d1767d5129223bd385cff5628cb08b4d04a86722c51ccb41
+oid sha256:e0968a64e6d1fbef837d20aec1c7c8997a9d1dc57a23d13d7d4ac2b7e0929ac6
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb491c30a78dfe58c1f35bac863be902e22f0aaa4e0e23ad457302e32ae5bedb
+oid sha256:19db8a1b78ed945e10baaf1fdc979a2fe9ea295e5d5e0ebb254722d184ec9ff8
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d1202103cd7d52d4f848514cbbe506ba9a1488356cada662580c6709e211694
+oid sha256:a293291606a2a1ed398550d1d7e4bd55a865eece2c25894cfcafdfbd62f33190
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97bae4c461f9d0cb1d0d15ee7b1cfd5f6abf04cc66ce02f609aa0ac7fc0fa959
+oid sha256:bcf8ee35dd8a2665a9cda7da2a8804cc28ed8b69a6cf5299251067dc25d454ce
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48ab33b703b9cb79c7764d23f339f55d629ad73aa585f882e8832ce5e02d3f8c
+oid sha256:55983f2a4f5bb75cbb2bccbee6b00caaf4848f494b5fbbb3d3411132905511d1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:213abff81591e8ae80eecfd7f6ac29dcf06d0b67b14c69b97617efa91ac7949c
+oid sha256:aa839aad6f0cddcf83d7736bd554e72dc8b5a2b756dce6cb6fa9c8ae34dfdd43
 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": 1.8134595155715942,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006403996093562383,
+  "best_metric": 1.8081966638565063,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.012807992187124766,
   "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": 18.558,
       "eval_steps_per_second": 4.825,
       "step": 25
+    },
+    {
+      "epoch": 0.006660155937304878,
+      "grad_norm": 0.09590143710374832,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.4168,
+      "step": 26
+    },
+    {
+      "epoch": 0.006916315781047374,
+      "grad_norm": 0.10224228352308273,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.5611,
+      "step": 27
+    },
+    {
+      "epoch": 0.0071724756247898685,
+      "grad_norm": 0.10272631794214249,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.6511,
+      "step": 28
+    },
+    {
+      "epoch": 0.007428635468532364,
+      "grad_norm": 0.1190299317240715,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.7072,
+      "step": 29
+    },
+    {
+      "epoch": 0.007684795312274859,
+      "grad_norm": 0.12482059001922607,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.7487,
+      "step": 30
+    },
+    {
+      "epoch": 0.007940955156017355,
+      "grad_norm": 0.12380363792181015,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.8393,
+      "step": 31
+    },
+    {
+      "epoch": 0.00819711499975985,
+      "grad_norm": 0.12392839789390564,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.8953,
+      "step": 32
+    },
+    {
+      "epoch": 0.008453274843502346,
+      "grad_norm": 0.13712841272354126,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.9785,
+      "step": 33
+    },
+    {
+      "epoch": 0.008709434687244841,
+      "grad_norm": 0.12810565531253815,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.9857,
+      "step": 34
+    },
+    {
+      "epoch": 0.008965594530987336,
+      "grad_norm": 0.12361529469490051,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.9972,
+      "step": 35
+    },
+    {
+      "epoch": 0.009221754374729831,
+      "grad_norm": 0.14207932353019714,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.0546,
+      "step": 36
+    },
+    {
+      "epoch": 0.009477914218472328,
+      "grad_norm": 0.20625418424606323,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.9875,
+      "step": 37
+    },
+    {
+      "epoch": 0.009734074062214822,
+      "grad_norm": 0.09341422468423843,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.3998,
+      "step": 38
+    },
+    {
+      "epoch": 0.009990233905957317,
+      "grad_norm": 0.08384900540113449,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.5255,
+      "step": 39
+    },
+    {
+      "epoch": 0.010246393749699812,
+      "grad_norm": 0.08318038284778595,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.6168,
+      "step": 40
+    },
+    {
+      "epoch": 0.010502553593442309,
+      "grad_norm": 0.09067439287900925,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.6491,
+      "step": 41
+    },
+    {
+      "epoch": 0.010758713437184804,
+      "grad_norm": 0.09931217133998871,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.7333,
+      "step": 42
+    },
+    {
+      "epoch": 0.011014873280927298,
+      "grad_norm": 0.10532019287347794,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.8573,
+      "step": 43
+    },
+    {
+      "epoch": 0.011271033124669793,
+      "grad_norm": 0.11125041544437408,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.8293,
+      "step": 44
+    },
+    {
+      "epoch": 0.01152719296841229,
+      "grad_norm": 0.11470434814691544,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.928,
+      "step": 45
+    },
+    {
+      "epoch": 0.011783352812154785,
+      "grad_norm": 0.11768055707216263,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.9526,
+      "step": 46
+    },
+    {
+      "epoch": 0.01203951265589728,
+      "grad_norm": 0.1167469248175621,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.0492,
+      "step": 47
+    },
+    {
+      "epoch": 0.012295672499639775,
+      "grad_norm": 0.12404833734035492,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.019,
+      "step": 48
+    },
+    {
+      "epoch": 0.012551832343382271,
+      "grad_norm": 0.14609728753566742,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.0688,
+      "step": 49
+    },
+    {
+      "epoch": 0.012807992187124766,
+      "grad_norm": 0.25891968607902527,
+      "learning_rate": 1e-05,
+      "loss": 2.023,
+      "step": 50
+    },
+    {
+      "epoch": 0.012807992187124766,
+      "eval_loss": 1.8081966638565063,
+      "eval_runtime": 2.7056,
+      "eval_samples_per_second": 18.48,
+      "eval_steps_per_second": 4.805,
+      "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": 2.812907666370724e+17,
+  "total_flos": 5.624936571695268e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null