Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97c2ade2f4d493f83e7fce91a525225bce9a008b2a109c45cb42bcc18edefd67
+oid sha256:a00ddc42da83a94d2297674418f877184d6fff9fb02e3780cd92be6685d287f8
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6541f342f70ccdc2ab141a5e5120fc0b86d719c1ec030602a99d90cf6de1125a
+oid sha256:ebd6d2cb96960fbbcd0e7b492211e038895bc3cd26787c07ecb4baf2128b83fe
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:243d421decf31082ab80e2d551ffc09a369a4e51dd527f93d3ecd91de21ea35a
+oid sha256:c178a7702b6f06be3d0b4b3d3a919acc6f01d372a931df3deec782fe01c1a771
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27b061d39b47fbd000536a5e3e880d3150834f164fedc0117b4e4020ec386cd4
+oid sha256:a28e5a51b82e9e434ec5d4262a9812052021217d923162e4bd648a9d5930f958
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ab94c473bcf27a3b850d2a49a2118397b6eb9574eea1a7cb7b4d513a9749dfe
+oid sha256:1ac57f2249c8cb691f70d2422531cd8365e3ae6be2323181ebf0159f044cf018
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:139062b512a66833abc76dba3a1f3587749ca36105baf705a302983d08d3fb15
+oid sha256:06259a02582bdba827e2264fdfdaf42f82ef486da0ce15234343c19ff86296f8
 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": 0.447214812040329,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.1111111111111112,
+  "best_metric": 0.015249949879944324,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.2222222222222223,
   "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": 5.827,
       "eval_steps_per_second": 1.515,
       "step": 25
+    },
+    {
+      "epoch": 1.1555555555555554,
+      "grad_norm": 12.346272468566895,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.6652,
+      "step": 26
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 12.182293891906738,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.5499,
+      "step": 27
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 2.7045016288757324,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0956,
+      "step": 28
+    },
+    {
+      "epoch": 1.2888888888888888,
+      "grad_norm": 6.3735480308532715,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.2023,
+      "step": 29
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 7.7382893562316895,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.1611,
+      "step": 30
+    },
+    {
+      "epoch": 1.3777777777777778,
+      "grad_norm": 3.8647775650024414,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0872,
+      "step": 31
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 4.321582317352295,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0772,
+      "step": 32
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 3.3833365440368652,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0712,
+      "step": 33
+    },
+    {
+      "epoch": 1.511111111111111,
+      "grad_norm": 1.7499160766601562,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0332,
+      "step": 34
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 5.335814952850342,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0531,
+      "step": 35
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.5655996799468994,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0357,
+      "step": 36
+    },
+    {
+      "epoch": 1.6444444444444444,
+      "grad_norm": 3.485537052154541,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0309,
+      "step": 37
+    },
+    {
+      "epoch": 1.6888888888888889,
+      "grad_norm": 2.6600377559661865,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0241,
+      "step": 38
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.8413442373275757,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.004,
+      "step": 39
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 2.198671340942383,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0167,
+      "step": 40
+    },
+    {
+      "epoch": 1.8222222222222222,
+      "grad_norm": 2.00276255607605,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0299,
+      "step": 41
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.9371952414512634,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0056,
+      "step": 42
+    },
+    {
+      "epoch": 1.911111111111111,
+      "grad_norm": 0.3950294852256775,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0031,
+      "step": 43
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 0.4528917372226715,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.003,
+      "step": 44
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.7309563159942627,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0279,
+      "step": 45
+    },
+    {
+      "epoch": 2.0444444444444443,
+      "grad_norm": 0.38156214356422424,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0029,
+      "step": 46
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 0.22612902522087097,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0016,
+      "step": 47
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.22579126060009003,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0017,
+      "step": 48
+    },
+    {
+      "epoch": 2.1777777777777776,
+      "grad_norm": 0.3204649090766907,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0015,
+      "step": 49
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.06680531799793243,
+      "learning_rate": 1e-05,
+      "loss": 0.0006,
+      "step": 50
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "eval_loss": 0.015249949879944324,
+      "eval_runtime": 8.5494,
+      "eval_samples_per_second": 5.848,
+      "eval_steps_per_second": 1.521,
+      "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": 5.74998392174805e+17,
+  "total_flos": 1.1457518287265464e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null