Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6090090a83c7b25b53e9873e426a123141dcf4a5fa47f3427578a7656497962b
+oid sha256:cae3c5621df7f5258e7b23e5b08d084b1091fbc07bd85e10f5d5ca726ae43df8
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac4e2739a32fa5c41f3dd4ee62ec6386a02332c8361b7c3bf140741e0aec51ac
+oid sha256:d57ca9f80b95e15639b99e4bee4a79acfe0168d57ada696abe5ec175e75133d4
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b499855b7e63c676f3fcdcb4c4f20c9c6802a25462a5e41407f42216731ae1fa
+oid sha256:d5aa08c8b1fd82fef6a97d900d948f730e646f7f8b49e67990449e4bbb6d95d0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b47792236dedf54890b20213917b16cc716562763541b847e4f3519ec8337674
+oid sha256:62ec4205a7544a63274cf26b1f9c14fcb0de9d43ff86c8e23939c59fabdc1066
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec077b3b1365c8d004433a36cfd1d4cb0fdf75573f98bd86b1da57b4f001b18
+oid sha256:8b373d73b258b863bada775a2ae2c03675d83eb4f102128af23eace67c4cda2b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbf391da5f82e621f8e82303cadbd3dfe011d03e2d6596223ad6683019fd66f6
+oid sha256:85d9606f41ce4315b05b583a045958941d5739f0ee165b14738146b9782638e6
 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": 10.376198768615723,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2611818478615736,
+  "best_metric": 10.373831748962402,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5223636957231472,
   "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": 278.798,
       "eval_steps_per_second": 72.487,
       "step": 25
+    },
+    {
+      "epoch": 0.27162912177603654,
+      "grad_norm": 0.058083388954401016,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3754,
+      "step": 26
+    },
+    {
+      "epoch": 0.2820763956904995,
+      "grad_norm": 0.055568333715200424,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.3756,
+      "step": 27
+    },
+    {
+      "epoch": 0.29252366960496246,
+      "grad_norm": 0.059653159230947495,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3746,
+      "step": 28
+    },
+    {
+      "epoch": 0.3029709435194254,
+      "grad_norm": 0.04649928957223892,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3756,
+      "step": 29
+    },
+    {
+      "epoch": 0.31341821743388837,
+      "grad_norm": 0.053945064544677734,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.3747,
+      "step": 30
+    },
+    {
+      "epoch": 0.3238654913483513,
+      "grad_norm": 0.05790293961763382,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.3745,
+      "step": 31
+    },
+    {
+      "epoch": 0.3343127652628142,
+      "grad_norm": 0.053165897727012634,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3749,
+      "step": 32
+    },
+    {
+      "epoch": 0.34476003917727716,
+      "grad_norm": 0.04939047992229462,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.3745,
+      "step": 33
+    },
+    {
+      "epoch": 0.35520731309174014,
+      "grad_norm": 0.053896188735961914,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.3738,
+      "step": 34
+    },
+    {
+      "epoch": 0.36565458700620307,
+      "grad_norm": 0.05971045047044754,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.3765,
+      "step": 35
+    },
+    {
+      "epoch": 0.376101860920666,
+      "grad_norm": 0.06172914803028107,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.3769,
+      "step": 36
+    },
+    {
+      "epoch": 0.386549134835129,
+      "grad_norm": 0.07987114787101746,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3756,
+      "step": 37
+    },
+    {
+      "epoch": 0.3969964087495919,
+      "grad_norm": 0.05999770760536194,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3754,
+      "step": 38
+    },
+    {
+      "epoch": 0.40744368266405484,
+      "grad_norm": 0.05834446847438812,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.3746,
+      "step": 39
+    },
+    {
+      "epoch": 0.41789095657851777,
+      "grad_norm": 0.056418679654598236,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.3735,
+      "step": 40
+    },
+    {
+      "epoch": 0.42833823049298075,
+      "grad_norm": 0.06561548262834549,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.3724,
+      "step": 41
+    },
+    {
+      "epoch": 0.4387855044074437,
+      "grad_norm": 0.064185731112957,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.3736,
+      "step": 42
+    },
+    {
+      "epoch": 0.4492327783219066,
+      "grad_norm": 0.06568823754787445,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.3738,
+      "step": 43
+    },
+    {
+      "epoch": 0.4596800522363696,
+      "grad_norm": 0.05658630281686783,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.3741,
+      "step": 44
+    },
+    {
+      "epoch": 0.4701273261508325,
+      "grad_norm": 0.05986878648400307,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.3735,
+      "step": 45
+    },
+    {
+      "epoch": 0.48057460006529545,
+      "grad_norm": 0.05994442105293274,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.3764,
+      "step": 46
+    },
+    {
+      "epoch": 0.4910218739797584,
+      "grad_norm": 0.06321598589420319,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.3727,
+      "step": 47
+    },
+    {
+      "epoch": 0.5014691478942214,
+      "grad_norm": 0.06735363602638245,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.3738,
+      "step": 48
+    },
+    {
+      "epoch": 0.5119164218086842,
+      "grad_norm": 0.08081047981977463,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.3738,
+      "step": 49
+    },
+    {
+      "epoch": 0.5223636957231472,
+      "grad_norm": 0.0807819813489914,
+      "learning_rate": 1e-05,
+      "loss": 10.3769,
+      "step": 50
+    },
+    {
+      "epoch": 0.5223636957231472,
+      "eval_loss": 10.373831748962402,
+      "eval_runtime": 0.1835,
+      "eval_samples_per_second": 272.468,
+      "eval_steps_per_second": 70.842,
+      "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": 21424124854272.0,
+  "total_flos": 42821519671296.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null