Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:405c497fbd0979cfd44e56d4927eccc1821e1771804b5877af2d328ae77a9636
+oid sha256:7c3a89f1244ba80315427e57532bb95c1755ba50904da34137a0ff443774f294
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e3c90b492336ba0dd406098aa4a6a6c097a17453cc697d6d60fabe578424cb1
+oid sha256:66c56713627627c08c4f6e8645db5ff4eb2b052efe10f90c4828fd86749d5b09
 size 141053442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bac57fb095f3ba2ab8f28329dbf22fa774761450fd2bbfb08f0ed22584e108f5
+oid sha256:f6b2a804dc726ad6eaa1945df1364b855f669282930a6bc568a705831e217e23
 size 14244

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": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.004736109877749164,
+  "epoch": 0.009472219755498328,
   "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": 9.131,
       "eval_steps_per_second": 9.131,
       "step": 25
+    },
+    {
+      "epoch": 0.004925554272859131,
+      "grad_norm": 8.170857429504395,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.8941,
+      "step": 26
+    },
+    {
+      "epoch": 0.005114998667969097,
+      "grad_norm": 7.001986503601074,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.068,
+      "step": 27
+    },
+    {
+      "epoch": 0.0053044430630790635,
+      "grad_norm": 6.956447601318359,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.83,
+      "step": 28
+    },
+    {
+      "epoch": 0.00549388745818903,
+      "grad_norm": 16.064136505126953,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.3823,
+      "step": 29
+    },
+    {
+      "epoch": 0.005683331853298996,
+      "grad_norm": 7.477011680603027,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.2673,
+      "step": 30
+    },
+    {
+      "epoch": 0.005872776248408963,
+      "grad_norm": 9.061140060424805,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.8978,
+      "step": 31
+    },
+    {
+      "epoch": 0.006062220643518929,
+      "grad_norm": 11.521283149719238,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.6095,
+      "step": 32
+    },
+    {
+      "epoch": 0.006251665038628896,
+      "grad_norm": 18.75054168701172,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.9312,
+      "step": 33
+    },
+    {
+      "epoch": 0.006441109433738863,
+      "grad_norm": 0.0,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.006630553828848829,
+      "grad_norm": 12.122861862182617,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.6679,
+      "step": 35
+    },
+    {
+      "epoch": 0.006819998223958796,
+      "grad_norm": 13.706648826599121,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.0586,
+      "step": 36
+    },
+    {
+      "epoch": 0.007009442619068763,
+      "grad_norm": 0.0,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.007198887014178729,
+      "grad_norm": 16.214313507080078,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.4707,
+      "step": 38
+    },
+    {
+      "epoch": 0.0073883314092886955,
+      "grad_norm": 9.249471664428711,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.3148,
+      "step": 39
+    },
+    {
+      "epoch": 0.007577775804398662,
+      "grad_norm": 6.823072910308838,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.3958,
+      "step": 40
+    },
+    {
+      "epoch": 0.007767220199508628,
+      "grad_norm": 0.0,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.007956664594618594,
+      "grad_norm": 8.052329063415527,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.8573,
+      "step": 42
+    },
+    {
+      "epoch": 0.008146108989728562,
+      "grad_norm": 14.712080955505371,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.1297,
+      "step": 43
+    },
+    {
+      "epoch": 0.008335553384838528,
+      "grad_norm": 10.332724571228027,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.4763,
+      "step": 44
+    },
+    {
+      "epoch": 0.008524997779948494,
+      "grad_norm": 16.205141067504883,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.3307,
+      "step": 45
+    },
+    {
+      "epoch": 0.008714442175058462,
+      "grad_norm": 0.0,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.008903886570168428,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.009093330965278394,
+      "grad_norm": 11.246818542480469,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.285,
+      "step": 48
+    },
+    {
+      "epoch": 0.009282775360388362,
+      "grad_norm": 57.88637924194336,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 7.4546,
+      "step": 49
+    },
+    {
+      "epoch": 0.009472219755498328,
+      "grad_norm": 13.0756254196167,
+      "learning_rate": 1e-05,
+      "loss": 1.6765,
+      "step": 50
+    },
+    {
+      "epoch": 0.009472219755498328,
+      "eval_loss": NaN,
+      "eval_runtime": 5.7587,
+      "eval_samples_per_second": 8.683,
+      "eval_steps_per_second": 8.683,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3691261408051200.0,
+  "total_flos": 7382522816102400.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null