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:b384c2980acd4e46ad0118673ec526ba1883554312c213a0528be8cdd5f54077
+oid sha256:2ac5dff6876962e0eac82d2450162b156d1ec6e8845bc145db7ea244ab033276
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb99be061e50fa175eb537e605969a1f65f4ae3abb13007b914aebd66996d25d
+oid sha256:6f83cb59930af7287c0d7e168b66e53ebefc2f7eeb25f8dfd57a4e8f75da8460
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64a00dbaafff41c0f14e70ae96f8a8403be2d304ba875815bc9555ac5e02669e
+oid sha256:1db15103b741658840b2484995de7d26618d0de4f9fd00dc97166a9df58e54f4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cadfac35015d4c96b7baf56d7a322e9021e7541c630c4335104e962792089410
+oid sha256:90d552c3e266c08a21746e4d5bddc3771cafc1d587bd72965b50b516eac5e2c5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91ba146d5724bc35729ef64ef867d75ffb35c9fab121e293294f849518f568a8
+oid sha256:892926e27ac75f89a2eeec6647ec34883615674b3ac0126e7629822a61951cf9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4c0be5a29e08e77044d85594aa3de4901f98ec9ec6003959ccb8ed96d28ce7
+oid sha256:3c5c8a6a9b6ed78f4a05a5638226ecfed2250b26030ef80eb24b7a55727fe1be
 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": 3.217378854751587,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2695417789757412,
+  "best_metric": 2.978853464126587,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5390835579514824,
   "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": 19.118,
       "eval_steps_per_second": 4.971,
       "step": 25
+    },
+    {
+      "epoch": 0.2803234501347709,
+      "grad_norm": 2.7146284580230713,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 4.7519,
+      "step": 26
+    },
+    {
+      "epoch": 0.29110512129380056,
+      "grad_norm": 1.6230659484863281,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.024,
+      "step": 27
+    },
+    {
+      "epoch": 0.3018867924528302,
+      "grad_norm": 1.2240214347839355,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.6623,
+      "step": 28
+    },
+    {
+      "epoch": 0.31266846361185985,
+      "grad_norm": 0.9349792003631592,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.369,
+      "step": 29
+    },
+    {
+      "epoch": 0.32345013477088946,
+      "grad_norm": 1.0889204740524292,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.0932,
+      "step": 30
+    },
+    {
+      "epoch": 0.33423180592991913,
+      "grad_norm": 1.3626528978347778,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.8357,
+      "step": 31
+    },
+    {
+      "epoch": 0.3450134770889488,
+      "grad_norm": 1.3906242847442627,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.6933,
+      "step": 32
+    },
+    {
+      "epoch": 0.3557951482479784,
+      "grad_norm": 1.2971469163894653,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.6283,
+      "step": 33
+    },
+    {
+      "epoch": 0.3665768194070081,
+      "grad_norm": 1.0674742460250854,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.5326,
+      "step": 34
+    },
+    {
+      "epoch": 0.37735849056603776,
+      "grad_norm": 0.9163751006126404,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.5948,
+      "step": 35
+    },
+    {
+      "epoch": 0.3881401617250674,
+      "grad_norm": 0.7036921381950378,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.4848,
+      "step": 36
+    },
+    {
+      "epoch": 0.39892183288409705,
+      "grad_norm": 0.4230988323688507,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.3287,
+      "step": 37
+    },
+    {
+      "epoch": 0.40970350404312667,
+      "grad_norm": 2.271873950958252,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 4.5126,
+      "step": 38
+    },
+    {
+      "epoch": 0.42048517520215634,
+      "grad_norm": 2.1975555419921875,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 3.9926,
+      "step": 39
+    },
+    {
+      "epoch": 0.431266846361186,
+      "grad_norm": 1.8238301277160645,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 3.5651,
+      "step": 40
+    },
+    {
+      "epoch": 0.4420485175202156,
+      "grad_norm": 1.4213221073150635,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.2511,
+      "step": 41
+    },
+    {
+      "epoch": 0.4528301886792453,
+      "grad_norm": 1.154116153717041,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.9906,
+      "step": 42
+    },
+    {
+      "epoch": 0.4636118598382749,
+      "grad_norm": 0.9232210516929626,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.8678,
+      "step": 43
+    },
+    {
+      "epoch": 0.4743935309973046,
+      "grad_norm": 0.5954862236976624,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.74,
+      "step": 44
+    },
+    {
+      "epoch": 0.48517520215633425,
+      "grad_norm": 0.3422981798648834,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.5759,
+      "step": 45
+    },
+    {
+      "epoch": 0.49595687331536387,
+      "grad_norm": 0.36076000332832336,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.5384,
+      "step": 46
+    },
+    {
+      "epoch": 0.5067385444743935,
+      "grad_norm": 0.41339829564094543,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.4947,
+      "step": 47
+    },
+    {
+      "epoch": 0.5175202156334232,
+      "grad_norm": 0.42015019059181213,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.5452,
+      "step": 48
+    },
+    {
+      "epoch": 0.5283018867924528,
+      "grad_norm": 0.48948684334754944,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.3207,
+      "step": 49
+    },
+    {
+      "epoch": 0.5390835579514824,
+      "grad_norm": 0.32463398575782776,
+      "learning_rate": 1e-05,
+      "loss": 2.4077,
+      "step": 50
+    },
+    {
+      "epoch": 0.5390835579514824,
+      "eval_loss": 2.978853464126587,
+      "eval_runtime": 2.2172,
+      "eval_samples_per_second": 22.551,
+      "eval_steps_per_second": 5.863,
+      "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": 7.813278662341427e+16,
+  "total_flos": 1.5595304203268915e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null