Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07b987907c0f1eb5da0c97e93e0d602affda919cb871ba564c5d18da8af528c5
+oid sha256:11780dc28ab102c9b7c4298ada10e241f82496b069bf193cfce8bd2e5173620e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0751dec0e653fd17855348fa702bd032d3f4e343e9ec5526b2bba03009cc608c
+oid sha256:2621e0a9c7f151dfbd27f1dcb89b0e4123aac307ff04e83f6b0d561188299caf
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b30c7da00aac4aa0643bc545d72b48a80453b5e54d3fe277161c6d35d3fb5e
+oid sha256:66024677a9ad1d583f25eb5cd47ceb12f230bbf77c83383a1e2e59771399afad
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c41ab61deda29321f06cde6f9f935de9246260563e2c8e91548d90e7acc36a9a
+oid sha256:4b6100369292301b62fc671b5247267926f421d763535b566ad566bd2017afbc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8412bedb0d22baad097a948e5509ccaea9611f8fd16dc16a1129ba059f0f4bd
+oid sha256:9a2a8ae79f863dc0df4608975a4a6e05f6814eedcfc71dae05f6b84b946de261
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cac20eac54c4259d1a674f79e4e9ef28dc5117587fec8da03c9c1be02d6c91d
+oid sha256:32216e3bc50e8e353d7a9f1fb85399a2a9bc4a3524ecb6ecd0770d70ac5c693e
 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": 0.17940543591976166,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1341606573872212,
+  "best_metric": 0.0652083232998848,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2683213147744424,
   "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": 16.686,
       "eval_steps_per_second": 4.338,
       "step": 25
+    },
+    {
+      "epoch": 0.13952708368271005,
+      "grad_norm": 3.3402652740478516,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.1104,
+      "step": 26
+    },
+    {
+      "epoch": 0.1448935099781989,
+      "grad_norm": 1.7462341785430908,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0606,
+      "step": 27
+    },
+    {
+      "epoch": 0.15025993627368775,
+      "grad_norm": 0.6455514430999756,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0409,
+      "step": 28
+    },
+    {
+      "epoch": 0.15562636256917659,
+      "grad_norm": 0.31426483392715454,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0113,
+      "step": 29
+    },
+    {
+      "epoch": 0.16099278886466545,
+      "grad_norm": 1.9350186586380005,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0438,
+      "step": 30
+    },
+    {
+      "epoch": 0.16635921516015428,
+      "grad_norm": 1.6222811937332153,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.142,
+      "step": 31
+    },
+    {
+      "epoch": 0.17172564145564315,
+      "grad_norm": 1.8674970865249634,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.1582,
+      "step": 32
+    },
+    {
+      "epoch": 0.17709206775113198,
+      "grad_norm": 1.088249683380127,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0596,
+      "step": 33
+    },
+    {
+      "epoch": 0.18245849404662082,
+      "grad_norm": 0.7902882695198059,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.023,
+      "step": 34
+    },
+    {
+      "epoch": 0.18782492034210968,
+      "grad_norm": 1.519347071647644,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0899,
+      "step": 35
+    },
+    {
+      "epoch": 0.19319134663759852,
+      "grad_norm": 1.544364333152771,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0702,
+      "step": 36
+    },
+    {
+      "epoch": 0.19855777293308738,
+      "grad_norm": 0.4949541389942169,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0538,
+      "step": 37
+    },
+    {
+      "epoch": 0.20392419922857621,
+      "grad_norm": 1.5156257152557373,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.1169,
+      "step": 38
+    },
+    {
+      "epoch": 0.20929062552406508,
+      "grad_norm": 1.4696093797683716,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0471,
+      "step": 39
+    },
+    {
+      "epoch": 0.2146570518195539,
+      "grad_norm": 0.8628442883491516,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0546,
+      "step": 40
+    },
+    {
+      "epoch": 0.22002347811504278,
+      "grad_norm": 0.5932831764221191,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0482,
+      "step": 41
+    },
+    {
+      "epoch": 0.2253899044105316,
+      "grad_norm": 0.5823434591293335,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0862,
+      "step": 42
+    },
+    {
+      "epoch": 0.23075633070602045,
+      "grad_norm": 1.1892814636230469,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0461,
+      "step": 43
+    },
+    {
+      "epoch": 0.2361227570015093,
+      "grad_norm": 0.4474555552005768,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0823,
+      "step": 44
+    },
+    {
+      "epoch": 0.24148918329699814,
+      "grad_norm": 0.5299607515335083,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0391,
+      "step": 45
+    },
+    {
+      "epoch": 0.246855609592487,
+      "grad_norm": 0.583759069442749,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0858,
+      "step": 46
+    },
+    {
+      "epoch": 0.25222203588797587,
+      "grad_norm": 0.6683781743049622,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0648,
+      "step": 47
+    },
+    {
+      "epoch": 0.2575884621834647,
+      "grad_norm": 0.7462744116783142,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0461,
+      "step": 48
+    },
+    {
+      "epoch": 0.26295488847895354,
+      "grad_norm": 0.7885873913764954,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.046,
+      "step": 49
+    },
+    {
+      "epoch": 0.2683213147744424,
+      "grad_norm": 1.0941061973571777,
+      "learning_rate": 1e-05,
+      "loss": 0.0947,
+      "step": 50
+    },
+    {
+      "epoch": 0.2683213147744424,
+      "eval_loss": 0.0652083232998848,
+      "eval_runtime": 3.0477,
+      "eval_samples_per_second": 16.406,
+      "eval_steps_per_second": 4.265,
+      "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": 2.984974321220321e+17,
+  "total_flos": 5.969016129878753e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null