Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ed1b848bdd415394d96ba74750871747f7fb0cf690cc0056eacd188588867b9
+oid sha256:d48d83991d5bc356df63ce8b26fe46d0a33942c262e7aeec548da22e4408539a
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b501f13787be6b33e3b45818b4e6083ffa9447625d7d574fadc3d2bc48933007
+oid sha256:43bcde7665c2309709283acbb125506e9e41e46af2ce43984692bcf98e33530e
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9905814fbb2fc131e00c4b7ccc00efc101e6a998a13db516a2f9bbc96ed92ccd
+oid sha256:094aeb78cff133451177f4c5120451fcec196d1586bdb973be43f69f03d74b90
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76e4e9a13fef00e8d6c242762dbe2184e420e04066542299127c9df3cd08c6e5
+oid sha256:401f9b94bf7d6d62ce97d57267570906ed348225c66494137025622423328db4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd41fb90b99338d4c842f51a144d73231d209f4b4a100dd5843d9f18f543e2dc
+oid sha256:b1284110fba89ebb8d8dd116391f03a4ffad0c185ab6c7e574c380938cae1bf7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4680b04d373cddc2ebd3be69c2a42d1e3359e2b1e7d11bc19a7165507206e5a
+oid sha256:78b8f1b7c00d105938b95d6ed5a81b2e99a4d661807bffa5306bb75663b85293
 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": 0.13595739006996155,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.11904761904761904,
+  "best_metric": 0.06823227554559708,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.23809523809523808,
   "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": 35.143,
       "eval_steps_per_second": 9.137,
       "step": 25
+    },
+    {
+      "epoch": 0.12380952380952381,
+      "grad_norm": 13.140822410583496,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.3957,
+      "step": 26
+    },
+    {
+      "epoch": 0.12857142857142856,
+      "grad_norm": 11.16737174987793,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.3047,
+      "step": 27
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 4.448553085327148,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.1518,
+      "step": 28
+    },
+    {
+      "epoch": 0.1380952380952381,
+      "grad_norm": 4.07476806640625,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0956,
+      "step": 29
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 8.63122844696045,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.2256,
+      "step": 30
+    },
+    {
+      "epoch": 0.14761904761904762,
+      "grad_norm": 4.493725299835205,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0864,
+      "step": 31
+    },
+    {
+      "epoch": 0.1523809523809524,
+      "grad_norm": 2.2688863277435303,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.1022,
+      "step": 32
+    },
+    {
+      "epoch": 0.15714285714285714,
+      "grad_norm": 3.0792179107666016,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0549,
+      "step": 33
+    },
+    {
+      "epoch": 0.1619047619047619,
+      "grad_norm": 5.766729831695557,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.1233,
+      "step": 34
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 3.24430251121521,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0759,
+      "step": 35
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 3.6115334033966064,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.1239,
+      "step": 36
+    },
+    {
+      "epoch": 0.1761904761904762,
+      "grad_norm": 0.517220139503479,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0514,
+      "step": 37
+    },
+    {
+      "epoch": 0.18095238095238095,
+      "grad_norm": 1.8826234340667725,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0598,
+      "step": 38
+    },
+    {
+      "epoch": 0.18571428571428572,
+      "grad_norm": 0.8073082566261292,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0755,
+      "step": 39
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 1.5226880311965942,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0665,
+      "step": 40
+    },
+    {
+      "epoch": 0.19523809523809524,
+      "grad_norm": 1.1428807973861694,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0544,
+      "step": 41
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.020280361175537,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0717,
+      "step": 42
+    },
+    {
+      "epoch": 0.20476190476190476,
+      "grad_norm": 1.7617835998535156,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.1163,
+      "step": 43
+    },
+    {
+      "epoch": 0.20952380952380953,
+      "grad_norm": 1.8393968343734741,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0714,
+      "step": 44
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 1.7359673976898193,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0973,
+      "step": 45
+    },
+    {
+      "epoch": 0.21904761904761905,
+      "grad_norm": 1.216193437576294,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0493,
+      "step": 46
+    },
+    {
+      "epoch": 0.22380952380952382,
+      "grad_norm": 0.49069568514823914,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0514,
+      "step": 47
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.7987019419670105,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0502,
+      "step": 48
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 0.8119701147079468,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0502,
+      "step": 49
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 1.2248444557189941,
+      "learning_rate": 1e-05,
+      "loss": 0.0268,
+      "step": 50
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "eval_loss": 0.06823227554559708,
+      "eval_runtime": 1.4194,
+      "eval_samples_per_second": 35.227,
+      "eval_steps_per_second": 9.159,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null