Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c1e3b3a2b4c42f31246221c9f9645e1fc530054986b3d0ae80b657757b9c500
+oid sha256:42b080ae405f5c199b98d17c0e2e120613209797dfbddcc5f9f550e1020579f4
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68b7934cc699c8ccb40d8bed96c4dd1a960657d27b564c66085b09e9815deeb3
+oid sha256:479ff44f42771d9e1ec58796794dccc1e15996a69c66dad973941a9d0704bffa
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:148bbe719f580f9599ca909a24894e506b8cbeb7896ea4f677fafed298f64947
+oid sha256:9c184d45c32e68b6567fabd06b66fe7a693eb1394bdc6b57fecc43b3dfb214f3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efb9baa43c611681d545970397b02c86cef4f769f9d50dfa5e2096bd29d851b6
+oid sha256:0234801562b15c9f6e31676bedb884b279ba04f8355f2fc2dc8d646a8e617fb6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abc6aa64526605673f62d52bab73a9d2451fe697e726e4521624035eee491e11
+oid sha256:5b95207cda63d1d1268c062b263d0e6fae096694a0a754a6d59ecb1915cd2236
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cd61f4242d2b722b4f0249d844a60d2881486551a1355b96a2f89f4d509f9c2
+oid sha256:318948ac45d48e675145ca744c2ef55db140b5d0bb69bf70bf5052e51082610f
 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": 0.3435630798339844,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08352474420547087,
+  "best_metric": 0.29790541529655457,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.16704948841094175,
   "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": 14.611,
       "eval_steps_per_second": 3.799,
       "step": 25
+    },
+    {
+      "epoch": 0.0868657339736897,
+      "grad_norm": 0.5458437204360962,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.4751,
+      "step": 26
+    },
+    {
+      "epoch": 0.09020672374190854,
+      "grad_norm": 0.5423816442489624,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.3978,
+      "step": 27
+    },
+    {
+      "epoch": 0.09354771351012738,
+      "grad_norm": 0.4660660922527313,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.4156,
+      "step": 28
+    },
+    {
+      "epoch": 0.09688870327834621,
+      "grad_norm": 0.4113824665546417,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.3687,
+      "step": 29
+    },
+    {
+      "epoch": 0.10022969304656504,
+      "grad_norm": 0.37375932931900024,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.3397,
+      "step": 30
+    },
+    {
+      "epoch": 0.10357068281478388,
+      "grad_norm": 0.37807485461235046,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.3362,
+      "step": 31
+    },
+    {
+      "epoch": 0.10691167258300271,
+      "grad_norm": 0.4310266971588135,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.2948,
+      "step": 32
+    },
+    {
+      "epoch": 0.11025266235122155,
+      "grad_norm": 0.4565795660018921,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.2934,
+      "step": 33
+    },
+    {
+      "epoch": 0.11359365211944038,
+      "grad_norm": 0.41135865449905396,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.2764,
+      "step": 34
+    },
+    {
+      "epoch": 0.11693464188765922,
+      "grad_norm": 0.37899094820022583,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.2857,
+      "step": 35
+    },
+    {
+      "epoch": 0.12027563165587805,
+      "grad_norm": 0.4301278293132782,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.3117,
+      "step": 36
+    },
+    {
+      "epoch": 0.12361662142409689,
+      "grad_norm": 0.48227614164352417,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.4325,
+      "step": 37
+    },
+    {
+      "epoch": 0.12695761119231572,
+      "grad_norm": 0.5348661541938782,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.4335,
+      "step": 38
+    },
+    {
+      "epoch": 0.13029860096053456,
+      "grad_norm": 0.5197682976722717,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.3746,
+      "step": 39
+    },
+    {
+      "epoch": 0.1336395907287534,
+      "grad_norm": 0.47809088230133057,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.3728,
+      "step": 40
+    },
+    {
+      "epoch": 0.13698058049697223,
+      "grad_norm": 0.45601916313171387,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.352,
+      "step": 41
+    },
+    {
+      "epoch": 0.14032157026519107,
+      "grad_norm": 0.46553006768226624,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.3421,
+      "step": 42
+    },
+    {
+      "epoch": 0.1436625600334099,
+      "grad_norm": 0.3643818795681,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.3094,
+      "step": 43
+    },
+    {
+      "epoch": 0.14700354980162872,
+      "grad_norm": 0.3495977520942688,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.3007,
+      "step": 44
+    },
+    {
+      "epoch": 0.15034453956984756,
+      "grad_norm": 0.2826536297798157,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.2688,
+      "step": 45
+    },
+    {
+      "epoch": 0.1536855293380664,
+      "grad_norm": 0.29497799277305603,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.2618,
+      "step": 46
+    },
+    {
+      "epoch": 0.15702651910628523,
+      "grad_norm": 0.32323595881462097,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.282,
+      "step": 47
+    },
+    {
+      "epoch": 0.16036750887450407,
+      "grad_norm": 0.38904955983161926,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.2693,
+      "step": 48
+    },
+    {
+      "epoch": 0.1637084986427229,
+      "grad_norm": 0.4347740411758423,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.3387,
+      "step": 49
+    },
+    {
+      "epoch": 0.16704948841094175,
+      "grad_norm": 0.5141857862472534,
+      "learning_rate": 1e-05,
+      "loss": 0.3518,
+      "step": 50
+    },
+    {
+      "epoch": 0.16704948841094175,
+      "eval_loss": 0.29790541529655457,
+      "eval_runtime": 3.4453,
+      "eval_samples_per_second": 14.512,
+      "eval_steps_per_second": 3.773,
+      "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": 3.462824662369567e+17,
+  "total_flos": 6.913215448104305e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null