Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:147379e11daa520287f113578e16770eaf6b9d1fe1d252c545aaa645876a2970
+oid sha256:085f6eb8a5b69b7873030280d069ff2d633fcedc5cdfdb5bfc504f93be0f07bd
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22bafe9d30694333f0b9eedd0930a491b84b52bcdf7e063cd43468cf9b6878df
+oid sha256:d977514678d34513bb3d7c96badbcd1d8c3eef746f445bcddbaeaee054d485fa
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83bf3e84ef770d39f143a71eb7882e8ef6f79d71f13d3befd13670443a77fa8f
+oid sha256:b25bbb2a5c00dbb90c16e714e1d29392c284fe7ee2ba43f553f642772822a7f2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c78bbca6baddc69d9419b54f4f4b154d61465f26ed7d7617a8a601eeb45400
+oid sha256:051d40e084697928140eed6a2583cdd4779392e7fb5b10669b1cb23a1f75b8b0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:582c43c91f18e8f8cdb53b9144d0a2cc2e99ca92bcc8581683cdcd9e42a2c936
+oid sha256:1e8d5e4f568c94136ed5b9c1a83c302eea65e82710d43b48ff88d2cd86880e17
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8445b52bff20902fc095eeac84d53953a5ba8bfd7f4083a81ae0f33c3b36cddd
+oid sha256:89fa1b3abae3bc13f5202f02bd67b3fb2b7ad0a58ebff3f35c2a124bab459a36
 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": 6.912273406982422,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01188407088848285,
+  "best_metric": 6.899521350860596,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0237681417769657,
   "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": 371.293,
       "eval_steps_per_second": 96.536,
       "step": 25
+    },
+    {
+      "epoch": 0.012359433724022163,
+      "grad_norm": 0.3867284655570984,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 6.898,
+      "step": 26
+    },
+    {
+      "epoch": 0.012834796559561478,
+      "grad_norm": 0.3198029398918152,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 6.9001,
+      "step": 27
+    },
+    {
+      "epoch": 0.013310159395100793,
+      "grad_norm": 0.3250506520271301,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 6.8974,
+      "step": 28
+    },
+    {
+      "epoch": 0.013785522230640106,
+      "grad_norm": 0.31791263818740845,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 6.8979,
+      "step": 29
+    },
+    {
+      "epoch": 0.01426088506617942,
+      "grad_norm": 0.30952978134155273,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 6.8985,
+      "step": 30
+    },
+    {
+      "epoch": 0.014736247901718734,
+      "grad_norm": 0.327973335981369,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 6.8955,
+      "step": 31
+    },
+    {
+      "epoch": 0.015211610737258048,
+      "grad_norm": 0.30642637610435486,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 6.899,
+      "step": 32
+    },
+    {
+      "epoch": 0.01568697357279736,
+      "grad_norm": 0.28234004974365234,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 6.9003,
+      "step": 33
+    },
+    {
+      "epoch": 0.016162336408336676,
+      "grad_norm": 0.2788352072238922,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 6.8998,
+      "step": 34
+    },
+    {
+      "epoch": 0.01663769924387599,
+      "grad_norm": 0.2545340657234192,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 6.9029,
+      "step": 35
+    },
+    {
+      "epoch": 0.017113062079415303,
+      "grad_norm": 0.19631724059581757,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 6.9147,
+      "step": 36
+    },
+    {
+      "epoch": 0.017588424914954617,
+      "grad_norm": 0.16539086401462555,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 6.9256,
+      "step": 37
+    },
+    {
+      "epoch": 0.018063787750493932,
+      "grad_norm": 0.4138210713863373,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 6.8862,
+      "step": 38
+    },
+    {
+      "epoch": 0.018539150586033247,
+      "grad_norm": 0.3455830514431,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 6.888,
+      "step": 39
+    },
+    {
+      "epoch": 0.01901451342157256,
+      "grad_norm": 0.33522090315818787,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 6.8893,
+      "step": 40
+    },
+    {
+      "epoch": 0.019489876257111873,
+      "grad_norm": 0.3389662802219391,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 6.8891,
+      "step": 41
+    },
+    {
+      "epoch": 0.019965239092651188,
+      "grad_norm": 0.31411075592041016,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 6.8911,
+      "step": 42
+    },
+    {
+      "epoch": 0.020440601928190503,
+      "grad_norm": 0.3265419602394104,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 6.8892,
+      "step": 43
+    },
+    {
+      "epoch": 0.020915964763729814,
+      "grad_norm": 0.3150964379310608,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 6.8915,
+      "step": 44
+    },
+    {
+      "epoch": 0.02139132759926913,
+      "grad_norm": 0.3052806556224823,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 6.891,
+      "step": 45
+    },
+    {
+      "epoch": 0.021866690434808444,
+      "grad_norm": 0.2852076590061188,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 6.894,
+      "step": 46
+    },
+    {
+      "epoch": 0.02234205327034776,
+      "grad_norm": 0.26825907826423645,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 6.8974,
+      "step": 47
+    },
+    {
+      "epoch": 0.02281741610588707,
+      "grad_norm": 0.2242056280374527,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 6.9082,
+      "step": 48
+    },
+    {
+      "epoch": 0.023292778941426385,
+      "grad_norm": 0.17848236858844757,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 6.9157,
+      "step": 49
+    },
+    {
+      "epoch": 0.0237681417769657,
+      "grad_norm": 0.28793561458587646,
+      "learning_rate": 1e-05,
+      "loss": 6.9226,
+      "step": 50
+    },
+    {
+      "epoch": 0.0237681417769657,
+      "eval_loss": 6.899521350860596,
+      "eval_runtime": 0.1284,
+      "eval_samples_per_second": 389.278,
+      "eval_steps_per_second": 101.212,
+      "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": 3118662336512.0,
+  "total_flos": 6231083778048.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null