Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43e3da93643092d833fa62f12dcab5fad68d458b0d0192262d3376ec23368d83
+oid sha256:b0d73130e70d4292c8d4bb2979deea9c84bfe78dff4c9c791eece7c61187690b
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4780db2abe575d2b70a522cffac94e68b82eb563af3120bf3bb3994b7df70c0e
+oid sha256:3e676c44f1e88e4fb38df6cdef25fe99d10d4cb999d0dc6f9eeb872e16a2fcf1
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3c01a80664285e7d5390820807762890d7d649ff529d24bc110df999a722c9a
+oid sha256:8066a8fce9d55dac9daad2ad7a95eee3ca41a28c3ca97002ba6d884580d00ab6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b2808b4ec73fbcc9736c08d37c424d724fae72c532d108c617350b4a053207
+oid sha256:7728bbd8c2b314bc5cc878c06847c81f1886c79d3f48803f64a02a522dcee135
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a8627af71d0f62077e96e95238bd9db5fe6a62434e89d9f45943a309cab94fd
+oid sha256:8d98e76b5d6907d288fe29a1b37db6d8c6501718be49c5826034cc22d2baf037
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e66227f5c954fd9260d9bc34bb893c3c94a506cf790ea1ef4328d5c9d4b283
+oid sha256:f991b0b770a9b4b790ae4822e231cee53fd7e3e7642bce4020b2ffa8635a6cd5
 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": 9.181326866149902,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.017778172848285517,
+  "best_metric": 8.905207633972168,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03555634569657103,
   "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": 106.656,
       "eval_steps_per_second": 27.731,
       "step": 25
+    },
+    {
+      "epoch": 0.01848929976221694,
+      "grad_norm": 2.6871771812438965,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 8.7595,
+      "step": 26
+    },
+    {
+      "epoch": 0.01920042667614836,
+      "grad_norm": 2.3026132583618164,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 9.0285,
+      "step": 27
+    },
+    {
+      "epoch": 0.01991155359007978,
+      "grad_norm": 2.0922391414642334,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 9.0976,
+      "step": 28
+    },
+    {
+      "epoch": 0.0206226805040112,
+      "grad_norm": 2.124882936477661,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 9.0691,
+      "step": 29
+    },
+    {
+      "epoch": 0.02133380741794262,
+      "grad_norm": 2.0727596282958984,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 9.2239,
+      "step": 30
+    },
+    {
+      "epoch": 0.02204493433187404,
+      "grad_norm": 1.893613576889038,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 9.3525,
+      "step": 31
+    },
+    {
+      "epoch": 0.022756061245805464,
+      "grad_norm": 1.9661246538162231,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 9.2901,
+      "step": 32
+    },
+    {
+      "epoch": 0.023467188159736883,
+      "grad_norm": 1.8640170097351074,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 9.332,
+      "step": 33
+    },
+    {
+      "epoch": 0.024178315073668303,
+      "grad_norm": 1.9543989896774292,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 9.3554,
+      "step": 34
+    },
+    {
+      "epoch": 0.024889441987599726,
+      "grad_norm": 1.9747636318206787,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 9.4425,
+      "step": 35
+    },
+    {
+      "epoch": 0.025600568901531146,
+      "grad_norm": 2.04024600982666,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 9.7109,
+      "step": 36
+    },
+    {
+      "epoch": 0.026311695815462565,
+      "grad_norm": 2.1174285411834717,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 9.3722,
+      "step": 37
+    },
+    {
+      "epoch": 0.027022822729393988,
+      "grad_norm": 1.8444091081619263,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 8.786,
+      "step": 38
+    },
+    {
+      "epoch": 0.027733949643325408,
+      "grad_norm": 1.920892596244812,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 8.958,
+      "step": 39
+    },
+    {
+      "epoch": 0.028445076557256827,
+      "grad_norm": 1.868925929069519,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 8.7157,
+      "step": 40
+    },
+    {
+      "epoch": 0.02915620347118825,
+      "grad_norm": 1.63834547996521,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 8.9606,
+      "step": 41
+    },
+    {
+      "epoch": 0.02986733038511967,
+      "grad_norm": 1.5350797176361084,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 9.0381,
+      "step": 42
+    },
+    {
+      "epoch": 0.03057845729905109,
+      "grad_norm": 1.5533965826034546,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 9.0667,
+      "step": 43
+    },
+    {
+      "epoch": 0.03128958421298251,
+      "grad_norm": 1.6352142095565796,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 9.1235,
+      "step": 44
+    },
+    {
+      "epoch": 0.03200071112691393,
+      "grad_norm": 1.6297922134399414,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 9.1851,
+      "step": 45
+    },
+    {
+      "epoch": 0.032711838040845355,
+      "grad_norm": 1.6186994314193726,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 9.4025,
+      "step": 46
+    },
+    {
+      "epoch": 0.03342296495477677,
+      "grad_norm": 1.5999581813812256,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 9.324,
+      "step": 47
+    },
+    {
+      "epoch": 0.034134091868708194,
+      "grad_norm": 1.7737746238708496,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 9.326,
+      "step": 48
+    },
+    {
+      "epoch": 0.03484521878263962,
+      "grad_norm": 1.9884766340255737,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 9.4523,
+      "step": 49
+    },
+    {
+      "epoch": 0.03555634569657103,
+      "grad_norm": 2.1337687969207764,
+      "learning_rate": 1e-05,
+      "loss": 9.5157,
+      "step": 50
+    },
+    {
+      "epoch": 0.03555634569657103,
+      "eval_loss": 8.905207633972168,
+      "eval_runtime": 0.4716,
+      "eval_samples_per_second": 106.032,
+      "eval_steps_per_second": 27.568,
+      "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": 116006898892800.0,
+  "total_flos": 232013797785600.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null