Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d719c78ddade4b01f6d1784192f7f0505a7e59c2928c7c6111edb592e829dc5
+oid sha256:7f79a6e758e950bcc125e01f7b7eb92252f24ab9263da52860b39b80396aa628
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:675081fef38be8fb5f62c037bfdedc020f5018a0a54f6425a51d336fa5c8100d
+oid sha256:a36971bfbedafcc9da9ab275247a5de073b668f5ae1f323ae651fe3b11594276
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eef5709d95d5c4104be9741a318fd11660ff6b96cacf4a0e72527888af5c487
+oid sha256:2f1e639c61bddc3e7abfd362203ff7adc45d644f9fc356a7ef325f32865e5a76
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97c1faa2b55912af44b8481b098c4da14287f5e3500f694798b240363d58449b
+oid sha256:d136a6b165145de78b198ba162fb981834c1c5904b48c04dafae3171f1b02d40
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eadf0ab39fd7fc8bed37cc3ee9b7d76e12b70ff9354a260ced4c82e72baf1500
+oid sha256:ca0b926483b5672265e788cd9375d6e7a18442307fe5ddfb3a40c8c1c6f8ec3e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77a83d5a25ce6114fff82614493e80314f94bf28daae9ffdabc06d558a9042ac
+oid sha256:d8c2a509050855845fd8bb9b7f61236c069f91a13b2dfecb0a74c800daef19ab
 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": 0.8656136393547058,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0625,
+  "best_metric": 0.8412864208221436,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.125,
   "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": 21.495,
       "eval_steps_per_second": 5.589,
       "step": 25
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 0.2663879692554474,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.4851,
+      "step": 26
+    },
+    {
+      "epoch": 0.0675,
+      "grad_norm": 0.2828787863254547,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.6305,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.3093838691711426,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.6392,
+      "step": 28
+    },
+    {
+      "epoch": 0.0725,
+      "grad_norm": 0.33329126238822937,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.6667,
+      "step": 29
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 0.3540312647819519,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.6825,
+      "step": 30
+    },
+    {
+      "epoch": 0.0775,
+      "grad_norm": 0.3708834946155548,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.7007,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.37742483615875244,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.7389,
+      "step": 32
+    },
+    {
+      "epoch": 0.0825,
+      "grad_norm": 0.41441866755485535,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.745,
+      "step": 33
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 0.5062286257743835,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.8639,
+      "step": 34
+    },
+    {
+      "epoch": 0.0875,
+      "grad_norm": 0.614949643611908,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.865,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.7550729513168335,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.8755,
+      "step": 36
+    },
+    {
+      "epoch": 0.0925,
+      "grad_norm": 0.8111172914505005,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.1576,
+      "step": 37
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 0.3536604642868042,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.5238,
+      "step": 38
+    },
+    {
+      "epoch": 0.0975,
+      "grad_norm": 0.33883461356163025,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.5649,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.37112748622894287,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.5962,
+      "step": 40
+    },
+    {
+      "epoch": 0.1025,
+      "grad_norm": 0.3818936049938202,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.6846,
+      "step": 41
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 0.3865486979484558,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.7252,
+      "step": 42
+    },
+    {
+      "epoch": 0.1075,
+      "grad_norm": 0.35471948981285095,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.6879,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.38089480996131897,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.715,
+      "step": 44
+    },
+    {
+      "epoch": 0.1125,
+      "grad_norm": 0.3577588200569153,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.6943,
+      "step": 45
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 0.40845608711242676,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.7526,
+      "step": 46
+    },
+    {
+      "epoch": 0.1175,
+      "grad_norm": 0.48637714982032776,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.8287,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5862032175064087,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.891,
+      "step": 48
+    },
+    {
+      "epoch": 0.1225,
+      "grad_norm": 0.7420929074287415,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.0351,
+      "step": 49
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 1.0091607570648193,
+      "learning_rate": 1e-05,
+      "loss": 1.1372,
+      "step": 50
+    },
+    {
+      "epoch": 0.125,
+      "eval_loss": 0.8412864208221436,
+      "eval_runtime": 2.3229,
+      "eval_samples_per_second": 21.525,
+      "eval_steps_per_second": 5.596,
+      "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": 3.09881683174228e+17,
+  "total_flos": 6.189915553566556e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null