Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:165507ae19815fa8572d4cd4e22c1f8a49b83b7dec5a1f564c3b577a065e49d5
+oid sha256:d6a624dc0ec857b5c05d852d6ffabc01935679ffbceb7cecdef80ed7f60a78d8
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86ac81a62c3abfefa9effae01a5df4f5bae8edd66a130895709f4ee0295637a2
+oid sha256:234782a719dbfddb265f1378ec1a88bfbb56609692635e65fcf67920b749feb8
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2db7496ec69a8ee7ceac893e470dbe7bf871a38f975f24e71df6d7fd50d0c4d
+oid sha256:5ffb999b2eead980c8a0f17b76dbd0b8cb538b2c046fe2f2a2b964fa02626ff2
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96d9723aa94ddef6bc3878ec1b96cd26a1806f7a9c1830cf5b447abaa14baba0
+oid sha256:a5f6ce525a70871cae6e86a7e4d58ee17844118dc5f6de1462ae1618378b778a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd9710ffb8c7142def89d81b29ada2b54e01080f5508d9ed1c82f72d71b8c8e
+oid sha256:b40466a409b05b023c3721c61d818c72122e321c24a40595ba36049b30e35390
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f335c661bf775712b9e4a8b99b1571a0be99dd68cb84939d3d9c5c8e90eda459
+oid sha256:3a0c9b6f1bd506c2f7437cc88a4a2cbf2facec81b743bffbc4006f3ef1db2ef1
 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": 0.5611550807952881,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3404255319148936,
+  "best_metric": 0.2833782136440277,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6808510638297872,
   "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": 39.52,
       "eval_steps_per_second": 10.275,
       "step": 25
+    },
+    {
+      "epoch": 0.35404255319148936,
+      "grad_norm": 2.8560750484466553,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.2116,
+      "step": 26
+    },
+    {
+      "epoch": 0.3676595744680851,
+      "grad_norm": 3.257420301437378,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.3268,
+      "step": 27
+    },
+    {
+      "epoch": 0.38127659574468087,
+      "grad_norm": 3.010044574737549,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.3178,
+      "step": 28
+    },
+    {
+      "epoch": 0.3948936170212766,
+      "grad_norm": 2.024600028991699,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.1889,
+      "step": 29
+    },
+    {
+      "epoch": 0.4085106382978723,
+      "grad_norm": 1.2341009378433228,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.1911,
+      "step": 30
+    },
+    {
+      "epoch": 0.4221276595744681,
+      "grad_norm": 1.252215027809143,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.2421,
+      "step": 31
+    },
+    {
+      "epoch": 0.4357446808510638,
+      "grad_norm": 1.4999184608459473,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.194,
+      "step": 32
+    },
+    {
+      "epoch": 0.4493617021276596,
+      "grad_norm": 1.5111395120620728,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.2403,
+      "step": 33
+    },
+    {
+      "epoch": 0.46297872340425533,
+      "grad_norm": 1.3706086874008179,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.225,
+      "step": 34
+    },
+    {
+      "epoch": 0.4765957446808511,
+      "grad_norm": 1.4278351068496704,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.2078,
+      "step": 35
+    },
+    {
+      "epoch": 0.4902127659574468,
+      "grad_norm": 1.333633303642273,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.1474,
+      "step": 36
+    },
+    {
+      "epoch": 0.5038297872340426,
+      "grad_norm": 1.118594765663147,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.1509,
+      "step": 37
+    },
+    {
+      "epoch": 0.5174468085106383,
+      "grad_norm": 0.9480551481246948,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.1769,
+      "step": 38
+    },
+    {
+      "epoch": 0.531063829787234,
+      "grad_norm": 1.409814476966858,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.1691,
+      "step": 39
+    },
+    {
+      "epoch": 0.5446808510638298,
+      "grad_norm": 2.1385762691497803,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.2022,
+      "step": 40
+    },
+    {
+      "epoch": 0.5582978723404255,
+      "grad_norm": 1.9792088270187378,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.2006,
+      "step": 41
+    },
+    {
+      "epoch": 0.5719148936170213,
+      "grad_norm": 1.943965196609497,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.193,
+      "step": 42
+    },
+    {
+      "epoch": 0.585531914893617,
+      "grad_norm": 2.0789599418640137,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.2098,
+      "step": 43
+    },
+    {
+      "epoch": 0.5991489361702128,
+      "grad_norm": 1.5010707378387451,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.1491,
+      "step": 44
+    },
+    {
+      "epoch": 0.6127659574468085,
+      "grad_norm": 2.0292575359344482,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.1774,
+      "step": 45
+    },
+    {
+      "epoch": 0.6263829787234042,
+      "grad_norm": 1.5886896848678589,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.1914,
+      "step": 46
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.02972674369812,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.1959,
+      "step": 47
+    },
+    {
+      "epoch": 0.6536170212765957,
+      "grad_norm": 2.147615432739258,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.2052,
+      "step": 48
+    },
+    {
+      "epoch": 0.6672340425531915,
+      "grad_norm": 1.4841364622116089,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.1658,
+      "step": 49
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 1.6794753074645996,
+      "learning_rate": 1e-05,
+      "loss": 0.098,
+      "step": 50
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "eval_loss": 0.2833782136440277,
+      "eval_runtime": 1.2463,
+      "eval_samples_per_second": 40.117,
+      "eval_steps_per_second": 10.43,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null