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:e26df5c043a4451c744a102172895df11ee17a9df068cbd6657f7b6d3f5efa1f
+oid sha256:ccee4f2292deff33f1f548addfecef8c67e40df6cfdf4de8531b22afc8715de4
 size 2436967616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fac1cec4a04b7cd27fe93dfc22832f8528108eb5b29e9cc665c4daaecfd6f5c9
+oid sha256:e23c4f41fb20965924dabfd18ea2736f1ced678833b5da8100329ea8487e0601
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b593acd436729feb2a98621651ca5d0d04a27ae13409045a9e353e5e77dfd132
+oid sha256:840f524a0807fc7fd540f467b68d4b7cad5379fcd998a8362e2bc459eed238f1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2205b6379a84cecabd7972728c3bb901f98c9d9f8ac05437fdf3882ba90c477
+oid sha256:b4de4e03717042b09ecbf5a9d3a0024dabcf1c6af253a7d6c944fa91e0b209ad
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcfb2f646ec7ea3562db7b2b41c8bfc058e45bf2906904193fe151791bcfd0ff
+oid sha256:490b2e72d912d0533e710382855478240a124f271fbdc6434532427260c6f2b7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78d5919f234a903d34bc38dcfd1259f554413b87915309456c20628f721749dd
+oid sha256:952a6149b7c82c6fa6435899610aad998ba2edec5f12e4703e24e0256ba5d666
 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": 1.3463994264602661,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.013509405923874498,
+  "best_metric": 1.3384273052215576,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.027018811847748996,
   "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": 12.907,
       "eval_steps_per_second": 3.356,
       "step": 25
+    },
+    {
+      "epoch": 0.014049782160829477,
+      "grad_norm": 0.21748431026935577,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.2172,
+      "step": 26
+    },
+    {
+      "epoch": 0.014590158397784457,
+      "grad_norm": 0.29222214221954346,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.249,
+      "step": 27
+    },
+    {
+      "epoch": 0.015130534634739437,
+      "grad_norm": 0.29130834341049194,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.3289,
+      "step": 28
+    },
+    {
+      "epoch": 0.015670910871694418,
+      "grad_norm": 0.29046890139579773,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.2298,
+      "step": 29
+    },
+    {
+      "epoch": 0.016211287108649396,
+      "grad_norm": 0.31192153692245483,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.2679,
+      "step": 30
+    },
+    {
+      "epoch": 0.01675166334560438,
+      "grad_norm": 0.32285210490226746,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.3251,
+      "step": 31
+    },
+    {
+      "epoch": 0.017292039582559357,
+      "grad_norm": 0.31385868787765503,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.2645,
+      "step": 32
+    },
+    {
+      "epoch": 0.017832415819514336,
+      "grad_norm": 0.32815828919410706,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.3109,
+      "step": 33
+    },
+    {
+      "epoch": 0.018372792056469318,
+      "grad_norm": 0.3067333400249481,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.2784,
+      "step": 34
+    },
+    {
+      "epoch": 0.018913168293424296,
+      "grad_norm": 0.3107113540172577,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.3586,
+      "step": 35
+    },
+    {
+      "epoch": 0.019453544530379275,
+      "grad_norm": 0.3673906922340393,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.2515,
+      "step": 36
+    },
+    {
+      "epoch": 0.019993920767334257,
+      "grad_norm": 0.3637937903404236,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.2213,
+      "step": 37
+    },
+    {
+      "epoch": 0.020534297004289236,
+      "grad_norm": 0.24307753145694733,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.2029,
+      "step": 38
+    },
+    {
+      "epoch": 0.021074673241244218,
+      "grad_norm": 0.21791911125183105,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.1932,
+      "step": 39
+    },
+    {
+      "epoch": 0.021615049478199196,
+      "grad_norm": 0.24849295616149902,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.2393,
+      "step": 40
+    },
+    {
+      "epoch": 0.022155425715154175,
+      "grad_norm": 0.24978457391262054,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.2362,
+      "step": 41
+    },
+    {
+      "epoch": 0.022695801952109157,
+      "grad_norm": 0.2769562304019928,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.3149,
+      "step": 42
+    },
+    {
+      "epoch": 0.023236178189064136,
+      "grad_norm": 0.2753388285636902,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.2839,
+      "step": 43
+    },
+    {
+      "epoch": 0.023776554426019114,
+      "grad_norm": 0.3100898861885071,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.2743,
+      "step": 44
+    },
+    {
+      "epoch": 0.024316930662974096,
+      "grad_norm": 0.2863754332065582,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.2911,
+      "step": 45
+    },
+    {
+      "epoch": 0.024857306899929075,
+      "grad_norm": 0.2963234782218933,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.2549,
+      "step": 46
+    },
+    {
+      "epoch": 0.025397683136884057,
+      "grad_norm": 0.3099575340747833,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.2917,
+      "step": 47
+    },
+    {
+      "epoch": 0.025938059373839036,
+      "grad_norm": 0.32685086131095886,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.3653,
+      "step": 48
+    },
+    {
+      "epoch": 0.026478435610794014,
+      "grad_norm": 0.34813255071640015,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.3915,
+      "step": 49
+    },
+    {
+      "epoch": 0.027018811847748996,
+      "grad_norm": 0.3984713852405548,
+      "learning_rate": 1e-05,
+      "loss": 1.3408,
+      "step": 50
+    },
+    {
+      "epoch": 0.027018811847748996,
+      "eval_loss": 1.3384273052215576,
+      "eval_runtime": 3.8377,
+      "eval_samples_per_second": 13.029,
+      "eval_steps_per_second": 3.387,
+      "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": 3.023208989820191e+17,
+  "total_flos": 6.061338191368028e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null