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:b603b2ae456db6f899005a714748168a0cbed2708faa43b2a70e5b5d2da13f13
+oid sha256:9fa4c7ff4d8e4168e3d79e4fec7bcff4b5919d0bb57fc787febecb005b5107b6
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65c1ff41fc660fdec4b5bb50472664ed93ad0f26a83f57d278b231ae59a18b66
+oid sha256:e30e3062bff1b36b6eebf7a8441924f9ea64a325862dda5dc353c27a0d54d772
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd46732ea485a8c6d4076bcb2969fd03c7f8db3074ad048ed1dc69441e817149
+oid sha256:ef658ddb0029cb254e393761787b71e6accc3be330001e6ed073cc2fc293dbef
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f50f069b647594212794bb73b151ac9bcf9c62cac99bcae8561b681f41a5674f
+oid sha256:30ed8e4a89ffdbeb53b8cf8c81ff8d6f3535bdec41ad30d9d01d00c9c089a2ca
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8137d5dd5332cf90e24a223ec76efe8ad77dd5918605ed9ea781120e3030282c
+oid sha256:3fee7afbde275e53b70160fc284c0a4ff30d879fb0f426acd7fe144bf3c906df
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c2e2f7af63318c8ed77ae9f1567da8f9cbf09ab18f5bdea364d626296a93e6e
+oid sha256:ebbfc374e3b39a496828d0d262a34379f096fc2620909130b5d8eb8b6dbdbf51
 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": 1.1061513423919678,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.012519953676171399,
+  "best_metric": 1.0602198839187622,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.025039907352342797,
   "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": 21.391,
       "eval_steps_per_second": 5.562,
       "step": 25
+    },
+    {
+      "epoch": 0.013020751823218255,
+      "grad_norm": 6.150357246398926,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 20.203,
+      "step": 26
+    },
+    {
+      "epoch": 0.01352154997026511,
+      "grad_norm": 7.324110984802246,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 20.2245,
+      "step": 27
+    },
+    {
+      "epoch": 0.014022348117311966,
+      "grad_norm": 4.4846391677856445,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 17.0902,
+      "step": 28
+    },
+    {
+      "epoch": 0.014523146264358822,
+      "grad_norm": 4.2537126541137695,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 17.783,
+      "step": 29
+    },
+    {
+      "epoch": 0.015023944411405678,
+      "grad_norm": 3.3687477111816406,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 19.8318,
+      "step": 30
+    },
+    {
+      "epoch": 0.015524742558452534,
+      "grad_norm": 3.4171719551086426,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 17.4442,
+      "step": 31
+    },
+    {
+      "epoch": 0.01602554070549939,
+      "grad_norm": 4.006035327911377,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 17.9844,
+      "step": 32
+    },
+    {
+      "epoch": 0.016526338852546247,
+      "grad_norm": 4.396282196044922,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 18.255,
+      "step": 33
+    },
+    {
+      "epoch": 0.0170271369995931,
+      "grad_norm": 4.883106231689453,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 18.8518,
+      "step": 34
+    },
+    {
+      "epoch": 0.01752793514663996,
+      "grad_norm": 5.509437561035156,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 17.9827,
+      "step": 35
+    },
+    {
+      "epoch": 0.018028733293686813,
+      "grad_norm": 4.919665813446045,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 15.706,
+      "step": 36
+    },
+    {
+      "epoch": 0.01852953144073367,
+      "grad_norm": 6.44651460647583,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 16.1781,
+      "step": 37
+    },
+    {
+      "epoch": 0.019030329587780524,
+      "grad_norm": 5.128076553344727,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 21.4918,
+      "step": 38
+    },
+    {
+      "epoch": 0.019531127734827382,
+      "grad_norm": 9.525840759277344,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 21.2966,
+      "step": 39
+    },
+    {
+      "epoch": 0.020031925881874236,
+      "grad_norm": 3.75991153717041,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 17.6723,
+      "step": 40
+    },
+    {
+      "epoch": 0.020532724028921093,
+      "grad_norm": 3.4625003337860107,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 15.4358,
+      "step": 41
+    },
+    {
+      "epoch": 0.021033522175967947,
+      "grad_norm": 4.435390472412109,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 17.5912,
+      "step": 42
+    },
+    {
+      "epoch": 0.021534320323014805,
+      "grad_norm": 4.710116386413574,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 16.8838,
+      "step": 43
+    },
+    {
+      "epoch": 0.02203511847006166,
+      "grad_norm": 4.531633377075195,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 17.465,
+      "step": 44
+    },
+    {
+      "epoch": 0.022535916617108517,
+      "grad_norm": 3.9686601161956787,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 17.882,
+      "step": 45
+    },
+    {
+      "epoch": 0.023036714764155374,
+      "grad_norm": 3.2548906803131104,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 17.3054,
+      "step": 46
+    },
+    {
+      "epoch": 0.02353751291120223,
+      "grad_norm": 3.3293542861938477,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 16.5476,
+      "step": 47
+    },
+    {
+      "epoch": 0.024038311058249086,
+      "grad_norm": 3.773627996444702,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 16.9503,
+      "step": 48
+    },
+    {
+      "epoch": 0.02453910920529594,
+      "grad_norm": 3.537731647491455,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 14.9813,
+      "step": 49
+    },
+    {
+      "epoch": 0.025039907352342797,
+      "grad_norm": 6.06915283203125,
+      "learning_rate": 1e-05,
+      "loss": 17.1321,
+      "step": 50
+    },
+    {
+      "epoch": 0.025039907352342797,
+      "eval_loss": 1.0602198839187622,
+      "eval_runtime": 2.2315,
+      "eval_samples_per_second": 22.407,
+      "eval_steps_per_second": 5.826,
+      "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": 2.9582754301188506e+17,
+  "total_flos": 5.9050464574754e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null