Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4810ab6a24716ee9f4bcca38c9267041d26cee23c55ac4f525a72d488170dce1
+oid sha256:4b732d1e7175de58f17c6b6b8e90484997a4c08abaae7cdd7da5d245c99c0079
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a02d5f298ad6603b492be29600124deef7b86596d3ca531e1b363a39cce5450
+oid sha256:41a18e42490ad338e1fd462043ca978f4159a4afc72fba0f56c57fcd189d5775
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a753572216fd0f7decfd3df10eb8379b43a539edaead3d36105201a0aad53522
+oid sha256:34a92d74e13dea15318d6632d5f61d55264b195a2901698f6e22b6b29b7f806a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ace1f1464268086624970cdef3cd8683f06c861bd49c4e091b838fae4dfbebd7
+oid sha256:79d536498d5f69180f16c81d582671b287ac898ae21aad60165b8f90fe132ec0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b9b0418ac171eb007f7a1e13b0d845398b91772e6fe5d5a010f184446a522c0
+oid sha256:ef78d7e69f041b20cfb19017f55aa90836191769462475f56bf00c4bfec901ab
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72f4372eab515598ad9608943e54e1d6e9c710ee903e77219d7883db3635c56a
+oid sha256:32fe14f1d5522a694bd3cecf69b53a3c6704048bf41c1964b34775e73d2c77a4
 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": 0.8781389594078064,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0625,
+  "best_metric": 0.8562852740287781,
+  "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": 12.262,
       "eval_steps_per_second": 3.188,
       "step": 25
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 0.270175963640213,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.489,
+      "step": 26
+    },
+    {
+      "epoch": 0.0675,
+      "grad_norm": 0.2893918454647064,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.6359,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.3046613335609436,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.6455,
+      "step": 28
+    },
+    {
+      "epoch": 0.0725,
+      "grad_norm": 0.3335619568824768,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.6744,
+      "step": 29
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 0.3445623517036438,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.6907,
+      "step": 30
+    },
+    {
+      "epoch": 0.0775,
+      "grad_norm": 0.3691665232181549,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.7053,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3850746750831604,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.7444,
+      "step": 32
+    },
+    {
+      "epoch": 0.0825,
+      "grad_norm": 0.4230135381221771,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.7554,
+      "step": 33
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 0.5101211071014404,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.8672,
+      "step": 34
+    },
+    {
+      "epoch": 0.0875,
+      "grad_norm": 0.616494357585907,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.8741,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.7683385610580444,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.885,
+      "step": 36
+    },
+    {
+      "epoch": 0.0925,
+      "grad_norm": 0.8297840356826782,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.1771,
+      "step": 37
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 0.3354261517524719,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.5277,
+      "step": 38
+    },
+    {
+      "epoch": 0.0975,
+      "grad_norm": 0.33234667778015137,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.5691,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.36417073011398315,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.6006,
+      "step": 40
+    },
+    {
+      "epoch": 0.1025,
+      "grad_norm": 0.37846243381500244,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.6895,
+      "step": 41
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 0.3880544900894165,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.7326,
+      "step": 42
+    },
+    {
+      "epoch": 0.1075,
+      "grad_norm": 0.365140825510025,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.6952,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.38633495569229126,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.7239,
+      "step": 44
+    },
+    {
+      "epoch": 0.1125,
+      "grad_norm": 0.3560256063938141,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.6973,
+      "step": 45
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 0.40417200326919556,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.7619,
+      "step": 46
+    },
+    {
+      "epoch": 0.1175,
+      "grad_norm": 0.48786085844039917,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.8403,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5909727811813354,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.9017,
+      "step": 48
+    },
+    {
+      "epoch": 0.1225,
+      "grad_norm": 0.7687093615531921,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.0387,
+      "step": 49
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 1.0339679718017578,
+      "learning_rate": 1e-05,
+      "loss": 1.1475,
+      "step": 50
+    },
+    {
+      "epoch": 0.125,
+      "eval_loss": 0.8562852740287781,
+      "eval_runtime": 4.0326,
+      "eval_samples_per_second": 12.399,
+      "eval_steps_per_second": 3.224,
+      "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