Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fc318475e67f3f7a0d09f66fa96479bec040561e3aa975f962a089b922f131e
+oid sha256:21e30f8f0bf62aa6d7d7dd954f79c920a936a50c852f274b60cebc6d15844f6e
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:964e78cad1e2f216ac8c47fba28e91083f7fd48cb9e43a0af22ddfe57f29205e
+oid sha256:e64bc273f3de23926260f948a3f03081b40b447b9a55143eb9d62e7e90a2bc8d
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a565f5083286d95833b4f57982ea4266b275b3a1b0a93fdfd8d8ff3528d36b29
+oid sha256:e5a12a4de8ba60f35527f32f54a0500b4afe816d1406b9dd0398fc1c1da804de
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46b894fee8c85c0f6730aa1be7408ffb8927a5587a865818b63eeb1d22156722
+oid sha256:8397af011d59a56af428957f981776bd25cb8603cd2f709c898bd94fdd8ac5f5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba3910de388f90862a37d836aca32d681123a4b339d2059e6da6598460a90946
+oid sha256:da91c845a9ad30665280b797873964c24128079b527dc73dac0e9bcde98c1bad
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16990c7f1230a8325ae0e854c993fdfff63061a4f742d656e83c6883a0a821a7
+oid sha256:04d7fe6f1d2b83d33f723e9efb7d7b1f20f5fa78df0fe3e97ee598faa3886a09
 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": 1.6196093559265137,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06575702778234424,
+  "best_metric": 1.4852975606918335,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13151405556468848,
   "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": 10.147,
       "eval_steps_per_second": 2.638,
       "step": 25
+    },
+    {
+      "epoch": 0.068387308893638,
+      "grad_norm": 2.2736575603485107,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.5558,
+      "step": 26
+    },
+    {
+      "epoch": 0.07101759000493178,
+      "grad_norm": 2.2506535053253174,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.5879,
+      "step": 27
+    },
+    {
+      "epoch": 0.07364787111622555,
+      "grad_norm": 2.1792917251586914,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.5075,
+      "step": 28
+    },
+    {
+      "epoch": 0.07627815222751931,
+      "grad_norm": 2.11507248878479,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.5453,
+      "step": 29
+    },
+    {
+      "epoch": 0.07890843333881309,
+      "grad_norm": 2.233987331390381,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.6225,
+      "step": 30
+    },
+    {
+      "epoch": 0.08153871445010685,
+      "grad_norm": 2.1487109661102295,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.5094,
+      "step": 31
+    },
+    {
+      "epoch": 0.08416899556140063,
+      "grad_norm": 3.797689437866211,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.5324,
+      "step": 32
+    },
+    {
+      "epoch": 0.0867992766726944,
+      "grad_norm": 3.757350444793701,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.5409,
+      "step": 33
+    },
+    {
+      "epoch": 0.08942955778398816,
+      "grad_norm": 3.233478546142578,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.6367,
+      "step": 34
+    },
+    {
+      "epoch": 0.09205983889528194,
+      "grad_norm": 4.003518581390381,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.546,
+      "step": 35
+    },
+    {
+      "epoch": 0.0946901200065757,
+      "grad_norm": 4.850443363189697,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.3959,
+      "step": 36
+    },
+    {
+      "epoch": 0.09732040111786948,
+      "grad_norm": 4.212044715881348,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.2452,
+      "step": 37
+    },
+    {
+      "epoch": 0.09995068222916324,
+      "grad_norm": 3.1043128967285156,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.4457,
+      "step": 38
+    },
+    {
+      "epoch": 0.10258096334045701,
+      "grad_norm": 2.4784271717071533,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.3701,
+      "step": 39
+    },
+    {
+      "epoch": 0.10521124445175078,
+      "grad_norm": 2.052419900894165,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.4042,
+      "step": 40
+    },
+    {
+      "epoch": 0.10784152556304455,
+      "grad_norm": 2.2570297718048096,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.5581,
+      "step": 41
+    },
+    {
+      "epoch": 0.11047180667433831,
+      "grad_norm": 2.2795116901397705,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.5224,
+      "step": 42
+    },
+    {
+      "epoch": 0.11310208778563209,
+      "grad_norm": 2.148151159286499,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.5585,
+      "step": 43
+    },
+    {
+      "epoch": 0.11573236889692586,
+      "grad_norm": 2.2137041091918945,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.537,
+      "step": 44
+    },
+    {
+      "epoch": 0.11836265000821963,
+      "grad_norm": 2.4538509845733643,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.5816,
+      "step": 45
+    },
+    {
+      "epoch": 0.1209929311195134,
+      "grad_norm": 3.2917592525482178,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.683,
+      "step": 46
+    },
+    {
+      "epoch": 0.12362321223080716,
+      "grad_norm": 3.220569372177124,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.5974,
+      "step": 47
+    },
+    {
+      "epoch": 0.12625349334210093,
+      "grad_norm": 3.6013734340667725,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.5183,
+      "step": 48
+    },
+    {
+      "epoch": 0.12888377445339472,
+      "grad_norm": 3.7834768295288086,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.2478,
+      "step": 49
+    },
+    {
+      "epoch": 0.13151405556468848,
+      "grad_norm": 4.990466594696045,
+      "learning_rate": 1e-05,
+      "loss": 1.3318,
+      "step": 50
+    },
+    {
+      "epoch": 0.13151405556468848,
+      "eval_loss": 1.4852975606918335,
+      "eval_runtime": 4.9279,
+      "eval_samples_per_second": 10.146,
+      "eval_steps_per_second": 2.638,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null