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:e6f3150efe7d878c7b4f77230f46525988715b8e8e511805f3c691cb94270c10
+oid sha256:3016673da52f8881d6716043b9310eba4a7a0ef2f300e100a363bf6a1066ca52
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:affa9e92b5a8189166c4fb595f5dc9dbcbc60a464d7b3e757fb0c951ecef7c32
+oid sha256:cd64ed07f5f41baa57405b51edcdc537426dbbeb4fceddb7fe03664e0e43222c
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a0e13ed16b168987466055df4c2f0eb259751a73fe86609c47d4b3a02be0540
+oid sha256:53e5808ab021ddad419ff33a88a514154ceff2651339355d42de4eca11fcfe1c
 size 14960

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": 0.4674427807331085,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.1111111111111112,
+  "best_metric": 0.03835269808769226,
+  "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": 5.863,
       "eval_steps_per_second": 1.524,
       "step": 25
+    },
+    {
+      "epoch": 1.1555555555555554,
+      "grad_norm": 12.888225555419922,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.6015,
+      "step": 26
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 13.187077522277832,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.4939,
+      "step": 27
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 2.669879674911499,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0848,
+      "step": 28
+    },
+    {
+      "epoch": 1.2888888888888888,
+      "grad_norm": 6.082226753234863,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.1901,
+      "step": 29
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 6.845930099487305,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.1438,
+      "step": 30
+    },
+    {
+      "epoch": 1.3777777777777778,
+      "grad_norm": 3.527693748474121,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0763,
+      "step": 31
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 3.684480905532837,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0606,
+      "step": 32
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 3.098820686340332,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0797,
+      "step": 33
+    },
+    {
+      "epoch": 1.511111111111111,
+      "grad_norm": 2.297424554824829,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0386,
+      "step": 34
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 4.277784824371338,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0329,
+      "step": 35
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.5591373443603516,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0492,
+      "step": 36
+    },
+    {
+      "epoch": 1.6444444444444444,
+      "grad_norm": 2.6662991046905518,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0238,
+      "step": 37
+    },
+    {
+      "epoch": 1.6888888888888889,
+      "grad_norm": 1.7695767879486084,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0106,
+      "step": 38
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.13798579573631287,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0019,
+      "step": 39
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 8.660087585449219,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.1515,
+      "step": 40
+    },
+    {
+      "epoch": 1.8222222222222222,
+      "grad_norm": 1.4062175750732422,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.014,
+      "step": 41
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 1.929388403892517,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0195,
+      "step": 42
+    },
+    {
+      "epoch": 1.911111111111111,
+      "grad_norm": 1.239054799079895,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0084,
+      "step": 43
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 1.154092788696289,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0081,
+      "step": 44
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7374815940856934,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0199,
+      "step": 45
+    },
+    {
+      "epoch": 2.0444444444444443,
+      "grad_norm": 1.071720004081726,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0101,
+      "step": 46
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 0.10346444696187973,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0012,
+      "step": 47
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.33200082182884216,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0021,
+      "step": 48
+    },
+    {
+      "epoch": 2.1777777777777776,
+      "grad_norm": 0.09029132127761841,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0008,
+      "step": 49
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.11896515637636185,
+      "learning_rate": 1e-05,
+      "loss": 0.0007,
+      "step": 50
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "eval_loss": 0.03835269808769226,
+      "eval_runtime": 8.515,
+      "eval_samples_per_second": 5.872,
+      "eval_steps_per_second": 1.527,
+      "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