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:a5252974070254f57fcf934412933e66f7e01c2e6cab90f165e0bbd8db996643
+oid sha256:05d456f403b4119e8a39598802516ebd00f5181b2302436787a734db52029089
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7921a12d6985743c3fa397084da45f69bb8093398f749592accd26b636302b37
+oid sha256:49959c1d34bc238077d4a6d07e0ea445c3510cf4f4c7064057b12574cd6c2d5e
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f53b074a49a8ca281aee903d53635e9a9689d56a81734909ca190b5cd47d6a35
+oid sha256:e9b247bbf4dbe15aaeb011149e5852da198eba0330c8983b2b57552f24f8e40f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f99494d8352e70d67478274c54098271b27e17ad6cb3adfcde2d14e0f83098ef
+oid sha256:83ff7f3690dc32be7ee1f03fe1395fa92ee1fd49b0961659856ba12fb25b5fa2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0528906a996f371e92f639deacd5d1eabc5d83836535018b6fe0ee88769d2bd8
+oid sha256:52efdbad843ca17a7562ab8f1c2093ee21c46964a2ac92c1c69b18fd23d9fb58
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44a932912fd37f46d12e37c205ecf6dbabe69d70ed07fc4132c9c750b769a234
+oid sha256:04323bbc37505b9fdbada7853480211b62eaf9fa5db36b54931ecdf9019ef056
 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": 1.1880485544679686e-05,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.060505218575102104,
+  "best_metric": 6.333108103717677e-06,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12101043715020421,
   "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": 16.835,
       "eval_steps_per_second": 4.377,
       "step": 25
+    },
+    {
+      "epoch": 0.06292542731810619,
+      "grad_norm": 5.236049175262451,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.7224,
+      "step": 26
+    },
+    {
+      "epoch": 0.06534563606111027,
+      "grad_norm": 0.0036764470860362053,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0001,
+      "step": 27
+    },
+    {
+      "epoch": 0.06776584480411435,
+      "grad_norm": 0.0036135385744273663,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0001,
+      "step": 28
+    },
+    {
+      "epoch": 0.07018605354711843,
+      "grad_norm": 0.013541589491069317,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0002,
+      "step": 29
+    },
+    {
+      "epoch": 0.07260626229012253,
+      "grad_norm": 0.003832306945696473,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0002,
+      "step": 30
+    },
+    {
+      "epoch": 0.07502647103312661,
+      "grad_norm": 0.0027044774033129215,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0001,
+      "step": 31
+    },
+    {
+      "epoch": 0.07744667977613069,
+      "grad_norm": 0.017098935320973396,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0002,
+      "step": 32
+    },
+    {
+      "epoch": 0.07986688851913477,
+      "grad_norm": 9.107158660888672,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.1233,
+      "step": 33
+    },
+    {
+      "epoch": 0.08228709726213886,
+      "grad_norm": 0.002680846955627203,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0001,
+      "step": 34
+    },
+    {
+      "epoch": 0.08470730600514294,
+      "grad_norm": 0.003972608130425215,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0002,
+      "step": 35
+    },
+    {
+      "epoch": 0.08712751474814703,
+      "grad_norm": 0.003575769951567054,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0001,
+      "step": 36
+    },
+    {
+      "epoch": 0.08954772349115112,
+      "grad_norm": 0.003803999163210392,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0002,
+      "step": 37
+    },
+    {
+      "epoch": 0.0919679322341552,
+      "grad_norm": 72.67724609375,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.2959,
+      "step": 38
+    },
+    {
+      "epoch": 0.09438814097715928,
+      "grad_norm": 0.00248934724368155,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0001,
+      "step": 39
+    },
+    {
+      "epoch": 0.09680834972016336,
+      "grad_norm": 0.002764883218333125,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0001,
+      "step": 40
+    },
+    {
+      "epoch": 0.09922855846316744,
+      "grad_norm": 0.0022895580623298883,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0001,
+      "step": 41
+    },
+    {
+      "epoch": 0.10164876720617154,
+      "grad_norm": 0.002441002056002617,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0001,
+      "step": 42
+    },
+    {
+      "epoch": 0.10406897594917562,
+      "grad_norm": 0.0023592477664351463,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0001,
+      "step": 43
+    },
+    {
+      "epoch": 0.1064891846921797,
+      "grad_norm": 0.0023515636567026377,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0001,
+      "step": 44
+    },
+    {
+      "epoch": 0.10890939343518379,
+      "grad_norm": 0.002235549269244075,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0001,
+      "step": 45
+    },
+    {
+      "epoch": 0.11132960217818787,
+      "grad_norm": 0.00230324175208807,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0001,
+      "step": 46
+    },
+    {
+      "epoch": 0.11374981092119195,
+      "grad_norm": 0.019611643627285957,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0002,
+      "step": 47
+    },
+    {
+      "epoch": 0.11617001966419603,
+      "grad_norm": 0.0029431243892759085,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0001,
+      "step": 48
+    },
+    {
+      "epoch": 0.11859022840720013,
+      "grad_norm": 13.474868774414062,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0712,
+      "step": 49
+    },
+    {
+      "epoch": 0.12101043715020421,
+      "grad_norm": 0.3831072747707367,
+      "learning_rate": 1e-05,
+      "loss": 0.0015,
+      "step": 50
+    },
+    {
+      "epoch": 0.12101043715020421,
+      "eval_loss": 6.333108103717677e-06,
+      "eval_runtime": 2.9429,
+      "eval_samples_per_second": 16.99,
+      "eval_steps_per_second": 4.417,
+      "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": 2.631221648430203e+17,
+  "total_flos": 5.262443296860406e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null