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:a4dd80ee7431434bd1f8c0fc7f80984baf3210f325e246bb037bfc51bd7149ea
+oid sha256:ec848829d4005e34c2893c4a3e40edc48c5801c7f2812f054502d7646599c368
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bdcb59ff38c517978606cca24f3dac617ced8104dbba77752d1556b43b4adfb
+oid sha256:e3074b4e4376e25fac6b49a79510105a76884e5e6d9021fa53ea9f8955fb9a04
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10cfcae64a48aa1c56b8ff92e3fc73cba1f42f5eebd8f511f97429cbe416d587
+oid sha256:22c9aefe09d602cefb4b6b42422160a819fec855f4d30789fecde7ddc6df8665
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c606a80c7540e98ed97614423d05cc21d48593aec2f6d68f1c089fb03a29727a
+oid sha256:de74045bc2d1dcdeb66bd35c86d4b735e95b30ab2fb001b522982303c81f3f4d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38d14f21ecbf00dddb583795d619f26461694332154a76eb57b673c4c3c258e3
+oid sha256:0e1940a99b5dfae6ca687be31b6d6bd6cc61bafefab92435e279bb790544e0cf
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c06c7c979370b98f8e5a935dc84e616c5be353a4c559109f0801a3581580556
+oid sha256:4e6e518d2375dc1432bde28d65a33e80b468f13d228a0c6a9f8803764f86d315
 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": 1.617965817451477,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006403175975283741,
+  "best_metric": 1.5958507061004639,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.012806351950567481,
   "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": 75.557,
       "eval_steps_per_second": 19.645,
       "step": 25
+    },
+    {
+      "epoch": 0.00665930301429509,
+      "grad_norm": 0.40817996859550476,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.0082,
+      "step": 26
+    },
+    {
+      "epoch": 0.00691543005330644,
+      "grad_norm": 0.4682709872722626,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.1889,
+      "step": 27
+    },
+    {
+      "epoch": 0.00717155709231779,
+      "grad_norm": 0.5050235986709595,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.3271,
+      "step": 28
+    },
+    {
+      "epoch": 0.007427684131329139,
+      "grad_norm": 0.3686935305595398,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.2991,
+      "step": 29
+    },
+    {
+      "epoch": 0.007683811170340489,
+      "grad_norm": 0.2502523362636566,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.3933,
+      "step": 30
+    },
+    {
+      "epoch": 0.007939938209351838,
+      "grad_norm": 0.2137083113193512,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.4678,
+      "step": 31
+    },
+    {
+      "epoch": 0.008196065248363188,
+      "grad_norm": 0.21022151410579681,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.6702,
+      "step": 32
+    },
+    {
+      "epoch": 0.008452192287374538,
+      "grad_norm": 0.24133265018463135,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.632,
+      "step": 33
+    },
+    {
+      "epoch": 0.008708319326385888,
+      "grad_norm": 0.3395995795726776,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.5687,
+      "step": 34
+    },
+    {
+      "epoch": 0.008964446365397238,
+      "grad_norm": 0.3980751633644104,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.7686,
+      "step": 35
+    },
+    {
+      "epoch": 0.009220573404408587,
+      "grad_norm": 0.5121943950653076,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.7378,
+      "step": 36
+    },
+    {
+      "epoch": 0.009476700443419936,
+      "grad_norm": 0.6918196082115173,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.8551,
+      "step": 37
+    },
+    {
+      "epoch": 0.009732827482431285,
+      "grad_norm": 0.19062906503677368,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.067,
+      "step": 38
+    },
+    {
+      "epoch": 0.009988954521442635,
+      "grad_norm": 0.1364046037197113,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.0974,
+      "step": 39
+    },
+    {
+      "epoch": 0.010245081560453985,
+      "grad_norm": 0.1472988724708557,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.1545,
+      "step": 40
+    },
+    {
+      "epoch": 0.010501208599465335,
+      "grad_norm": 0.1773543506860733,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.2833,
+      "step": 41
+    },
+    {
+      "epoch": 0.010757335638476685,
+      "grad_norm": 0.18720166385173798,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.4385,
+      "step": 42
+    },
+    {
+      "epoch": 0.011013462677488034,
+      "grad_norm": 0.1837349832057953,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.4987,
+      "step": 43
+    },
+    {
+      "epoch": 0.011269589716499384,
+      "grad_norm": 0.20710361003875732,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.5536,
+      "step": 44
+    },
+    {
+      "epoch": 0.011525716755510734,
+      "grad_norm": 0.22093434631824493,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.5326,
+      "step": 45
+    },
+    {
+      "epoch": 0.011781843794522084,
+      "grad_norm": 0.21961745619773865,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.5564,
+      "step": 46
+    },
+    {
+      "epoch": 0.012037970833533432,
+      "grad_norm": 0.278564453125,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.6989,
+      "step": 47
+    },
+    {
+      "epoch": 0.012294097872544782,
+      "grad_norm": 0.24441421031951904,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.6805,
+      "step": 48
+    },
+    {
+      "epoch": 0.012550224911556131,
+      "grad_norm": 0.3852005898952484,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.7377,
+      "step": 49
+    },
+    {
+      "epoch": 0.012806351950567481,
+      "grad_norm": 0.9400036334991455,
+      "learning_rate": 1e-05,
+      "loss": 1.9483,
+      "step": 50
+    },
+    {
+      "epoch": 0.012806351950567481,
+      "eval_loss": 1.5958507061004639,
+      "eval_runtime": 0.662,
+      "eval_samples_per_second": 75.531,
+      "eval_steps_per_second": 19.638,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null