Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56602795929816899dd803758a8301f895dea653c81fc7443a118468871ee03e
+oid sha256:135d479c025f4cc7a3d9d8a15ae4c3c23f0518886fa46174454498d56b61a110
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ed3bb2b61546f20ddef254cc54fbd6c2f9b1f4697ad944594b8f532ff68749f
+oid sha256:f9603dd3933118b793d746fbc2e8a88ddd8576bfdfe76e9b2dc6ca42d1de1803
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3beea284146e4df664f27a143e1a147ead4d61ad0b6e04ac01e794f2c46702f3
+oid sha256:cafba242f7096b205a65a6f53124d9c12e11ca2887d5f0887cde65cae5c472c2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f223fb0b1b65c16f333a30be07ac684e3c0dd18f67b97fb6c267e6094b2f7443
+oid sha256:a623a5e5da619d887b04025d0a600fcf82e19828538a907df12e0d41e1156ee9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc64c500f67e6ffb2b71363d132b825b9b1ec3b1fa4959004915de1825fd228
+oid sha256:a3c34744c6bf088b7ddd79347e62560915821b8efe34dde07f0c2ed1f7e7cd54
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4ec35df3cca32a579c8d6ea725869d4e688ea44a5a6c7dc3b56e3b4ac59a54
+oid sha256:dd1a88a39db975e67ed20740260029517485b8691bd5b2c9f095493cb16cb7d5
 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": 6.92898416519165,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.005081107173253052,
+  "best_metric": 6.92307186126709,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.010162214346506104,
   "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": 392.966,
       "eval_steps_per_second": 102.171,
       "step": 25
+    },
+    {
+      "epoch": 0.005284351460183174,
+      "grad_norm": 0.09798461943864822,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 6.9302,
+      "step": 26
+    },
+    {
+      "epoch": 0.005487595747113296,
+      "grad_norm": 0.09589119255542755,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 6.9309,
+      "step": 27
+    },
+    {
+      "epoch": 0.005690840034043418,
+      "grad_norm": 0.10878289490938187,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 6.9289,
+      "step": 28
+    },
+    {
+      "epoch": 0.00589408432097354,
+      "grad_norm": 0.10759259760379791,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 6.9276,
+      "step": 29
+    },
+    {
+      "epoch": 0.006097328607903662,
+      "grad_norm": 0.10860608518123627,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 6.9266,
+      "step": 30
+    },
+    {
+      "epoch": 0.006300572894833784,
+      "grad_norm": 0.12264492362737656,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 6.9263,
+      "step": 31
+    },
+    {
+      "epoch": 0.006503817181763906,
+      "grad_norm": 0.12330181896686554,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 6.9263,
+      "step": 32
+    },
+    {
+      "epoch": 0.006707061468694028,
+      "grad_norm": 0.12452418357133865,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 6.9239,
+      "step": 33
+    },
+    {
+      "epoch": 0.00691030575562415,
+      "grad_norm": 0.131307452917099,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 6.9239,
+      "step": 34
+    },
+    {
+      "epoch": 0.007113550042554272,
+      "grad_norm": 0.1308247298002243,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 6.9252,
+      "step": 35
+    },
+    {
+      "epoch": 0.007316794329484394,
+      "grad_norm": 0.14916321635246277,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 6.924,
+      "step": 36
+    },
+    {
+      "epoch": 0.007520038616414516,
+      "grad_norm": 0.15847186744213104,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 6.9211,
+      "step": 37
+    },
+    {
+      "epoch": 0.007723282903344638,
+      "grad_norm": 0.1158829927444458,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 6.925,
+      "step": 38
+    },
+    {
+      "epoch": 0.00792652719027476,
+      "grad_norm": 0.10773951560258865,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 6.9268,
+      "step": 39
+    },
+    {
+      "epoch": 0.008129771477204882,
+      "grad_norm": 0.11924441158771515,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 6.9269,
+      "step": 40
+    },
+    {
+      "epoch": 0.008333015764135004,
+      "grad_norm": 0.12030573934316635,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 6.9251,
+      "step": 41
+    },
+    {
+      "epoch": 0.008536260051065126,
+      "grad_norm": 0.12425759434700012,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 6.9232,
+      "step": 42
+    },
+    {
+      "epoch": 0.008739504337995248,
+      "grad_norm": 0.12707437574863434,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 6.9242,
+      "step": 43
+    },
+    {
+      "epoch": 0.00894274862492537,
+      "grad_norm": 0.13171014189720154,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 6.9229,
+      "step": 44
+    },
+    {
+      "epoch": 0.009145992911855493,
+      "grad_norm": 0.12991087138652802,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 6.921,
+      "step": 45
+    },
+    {
+      "epoch": 0.009349237198785615,
+      "grad_norm": 0.13416709005832672,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 6.9232,
+      "step": 46
+    },
+    {
+      "epoch": 0.009552481485715738,
+      "grad_norm": 0.13503502309322357,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 6.9227,
+      "step": 47
+    },
+    {
+      "epoch": 0.00975572577264586,
+      "grad_norm": 0.14602893590927124,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 6.9204,
+      "step": 48
+    },
+    {
+      "epoch": 0.009958970059575982,
+      "grad_norm": 0.14785030484199524,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 6.9203,
+      "step": 49
+    },
+    {
+      "epoch": 0.010162214346506104,
+      "grad_norm": 0.17115415632724762,
+      "learning_rate": 1e-05,
+      "loss": 6.9184,
+      "step": 50
+    },
+    {
+      "epoch": 0.010162214346506104,
+      "eval_loss": 6.92307186126709,
+      "eval_runtime": 0.1177,
+      "eval_samples_per_second": 424.749,
+      "eval_steps_per_second": 110.435,
+      "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": 2852978688000.0,
+  "total_flos": 5705957376000.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null