Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a6eba72c4922d10969693240da1a35a2b9d9fa56561b9ad98b1c6900a48e2f2
+oid sha256:e2bffa357b57c1371ee075555ff24469243f7fb2f58060668265c606aeb8b0cf
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ce9affd2c7e4bc5e19870cba1eeaa1d6c34a36da9a85b75dbf7fd7c81463ffc
+oid sha256:1fbf75bf0c0a846f609cf2ccab2b8785253d8cee9b417688fd9a36e20255f107
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0522390808dea701fdbc37d1b8f299b5a0ff18ff0643e92e82b122f6b836a494
+oid sha256:5005cb4aa617bbb56522379724c642f44a0f35524f8f6e64e9194964e8446504
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b31bb681a6ec4b292afea4e29034348387102427f7b4c55c4a4f0a7c2daf2f21
+oid sha256:473b80a8f8e20c1eb2367207fe88a38fbab31879702bc6b77abaf3bdb80b1978
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b8f7639ec42e0573836c857d2e154ece3467bca964d3368dd096ecb56380897
+oid sha256:2733892746eb1c577fc1c1c41afcee083ba8cb875df1996785af2768111edaf1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1d042e8aef3b60497e04cd6dfae2464a373582b102caa7531cdb282e16bbb73
+oid sha256:e3473fab340ee171d16f8883cc59d9d98017131f53bb49558eddae1f14f3040e
 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": 0.4617072641849518,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2184598580010923,
+  "best_metric": 0.42746028304100037,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4369197160021846,
   "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": 24.563,
       "eval_steps_per_second": 6.386,
       "step": 25
+    },
+    {
+      "epoch": 0.227198252321136,
+      "grad_norm": 4.0482306480407715,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.6277,
+      "step": 26
+    },
+    {
+      "epoch": 0.2359366466411797,
+      "grad_norm": 2.817641496658325,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.5705,
+      "step": 27
+    },
+    {
+      "epoch": 0.2446750409612234,
+      "grad_norm": 2.8091375827789307,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.4781,
+      "step": 28
+    },
+    {
+      "epoch": 0.2534134352812671,
+      "grad_norm": 1.60512375831604,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.463,
+      "step": 29
+    },
+    {
+      "epoch": 0.2621518296013108,
+      "grad_norm": 2.439929962158203,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.4522,
+      "step": 30
+    },
+    {
+      "epoch": 0.2708902239213545,
+      "grad_norm": 2.7370707988739014,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.5325,
+      "step": 31
+    },
+    {
+      "epoch": 0.2796286182413981,
+      "grad_norm": 3.792188882827759,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.5985,
+      "step": 32
+    },
+    {
+      "epoch": 0.2883670125614418,
+      "grad_norm": 2.362417221069336,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.5181,
+      "step": 33
+    },
+    {
+      "epoch": 0.2971054068814855,
+      "grad_norm": 1.852939486503601,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.5735,
+      "step": 34
+    },
+    {
+      "epoch": 0.3058438012015292,
+      "grad_norm": 2.0152199268341064,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.5105,
+      "step": 35
+    },
+    {
+      "epoch": 0.3145821955215729,
+      "grad_norm": 1.5743001699447632,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.5086,
+      "step": 36
+    },
+    {
+      "epoch": 0.3233205898416166,
+      "grad_norm": 2.5821549892425537,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.4851,
+      "step": 37
+    },
+    {
+      "epoch": 0.3320589841616603,
+      "grad_norm": 1.5192317962646484,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.3747,
+      "step": 38
+    },
+    {
+      "epoch": 0.340797378481704,
+      "grad_norm": 2.5886213779449463,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4625,
+      "step": 39
+    },
+    {
+      "epoch": 0.3495357728017477,
+      "grad_norm": 2.2665421962738037,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.5191,
+      "step": 40
+    },
+    {
+      "epoch": 0.3582741671217914,
+      "grad_norm": 1.9218324422836304,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.4629,
+      "step": 41
+    },
+    {
+      "epoch": 0.3670125614418351,
+      "grad_norm": 1.9608279466629028,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.5172,
+      "step": 42
+    },
+    {
+      "epoch": 0.3757509557618788,
+      "grad_norm": 2.31650447845459,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.4803,
+      "step": 43
+    },
+    {
+      "epoch": 0.3844893500819224,
+      "grad_norm": 1.8961042165756226,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.4779,
+      "step": 44
+    },
+    {
+      "epoch": 0.3932277444019661,
+      "grad_norm": 1.3068761825561523,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.4151,
+      "step": 45
+    },
+    {
+      "epoch": 0.4019661387220098,
+      "grad_norm": 1.743826985359192,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.4957,
+      "step": 46
+    },
+    {
+      "epoch": 0.4107045330420535,
+      "grad_norm": 1.177809715270996,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.4505,
+      "step": 47
+    },
+    {
+      "epoch": 0.4194429273620972,
+      "grad_norm": 1.4149682521820068,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.5065,
+      "step": 48
+    },
+    {
+      "epoch": 0.4281813216821409,
+      "grad_norm": 1.3999468088150024,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.3783,
+      "step": 49
+    },
+    {
+      "epoch": 0.4369197160021846,
+      "grad_norm": 2.459918260574341,
+      "learning_rate": 1e-05,
+      "loss": 0.4372,
+      "step": 50
+    },
+    {
+      "epoch": 0.4369197160021846,
+      "eval_loss": 0.42746028304100037,
+      "eval_runtime": 2.0362,
+      "eval_samples_per_second": 24.556,
+      "eval_steps_per_second": 6.385,
+      "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": 2.9859068337822106e+17,
+  "total_flos": 5.969948642440643e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null