Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:943ad7bc86eab307337d43a836783a0dd3124a357dac29637228b02cbc749096
+oid sha256:df3fff7e282e62cc664ddbe3f549002ef510566f3d764770a814290f8fba6473
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ab9d7bf89e35e81c831eb27081ac000ae353a968b90dd0308d4e3bfd704c87e
+oid sha256:b4c6951793ececee6e2fae58689b292f7563c4c4a4add63f17b1349651e806ab
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75effa73bb54992328685206390b6fd0f519441309b6081c8db9350f0f8e4440
+oid sha256:de92ca3a7cf91268157c31c07b8378d81ed31992eaba2a339cbf37c46c499bbf
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:118f94949b467fb1317eda23d585440d4fa85773c2256160a9ac367e61b39bb2
+oid sha256:c46882f9760966d8213f5ec7ad94395036a79afa0a198d0e8dc02fab8d274b75
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d2eeb3ffa5ddfe5f3207e24ab73266212e8c76eadfe74587a8b443feada2468
+oid sha256:38290244260a19a89133d712a5e634ac27c9043591f935a951fb3217b6a3de1f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:130812c5c04cdec27d2e89aea89f9404383d5f01774149c1869814a8645c0393
+oid sha256:e1c0846ec43839b6d25215a4dd0b87e9cce6e98af5efea3e1b5b14cce3f1bff9
 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": 6.847867012023926,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.007767593599502874,
+  "best_metric": 6.804957389831543,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.015535187199005748,
   "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": 585.63,
       "eval_steps_per_second": 152.264,
       "step": 25
+    },
+    {
+      "epoch": 0.008078297343482988,
+      "grad_norm": 0.9630571603775024,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 6.8474,
+      "step": 26
+    },
+    {
+      "epoch": 0.008389001087463105,
+      "grad_norm": 0.9458622932434082,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 6.8424,
+      "step": 27
+    },
+    {
+      "epoch": 0.008699704831443219,
+      "grad_norm": 0.9316064119338989,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 6.8424,
+      "step": 28
+    },
+    {
+      "epoch": 0.009010408575423333,
+      "grad_norm": 0.9313185214996338,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 6.8408,
+      "step": 29
+    },
+    {
+      "epoch": 0.00932111231940345,
+      "grad_norm": 0.9337138533592224,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 6.8354,
+      "step": 30
+    },
+    {
+      "epoch": 0.009631816063383564,
+      "grad_norm": 0.9357588291168213,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 6.8374,
+      "step": 31
+    },
+    {
+      "epoch": 0.009942519807363678,
+      "grad_norm": 0.9744881391525269,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 6.8308,
+      "step": 32
+    },
+    {
+      "epoch": 0.010253223551343794,
+      "grad_norm": 0.9172983765602112,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 6.832,
+      "step": 33
+    },
+    {
+      "epoch": 0.010563927295323908,
+      "grad_norm": 0.9618328213691711,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 6.8243,
+      "step": 34
+    },
+    {
+      "epoch": 0.010874631039304023,
+      "grad_norm": 0.953589141368866,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 6.821,
+      "step": 35
+    },
+    {
+      "epoch": 0.011185334783284139,
+      "grad_norm": 0.9559220671653748,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 6.8221,
+      "step": 36
+    },
+    {
+      "epoch": 0.011496038527264253,
+      "grad_norm": 0.9633547067642212,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 6.8274,
+      "step": 37
+    },
+    {
+      "epoch": 0.01180674227124437,
+      "grad_norm": 0.9454740285873413,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 6.8239,
+      "step": 38
+    },
+    {
+      "epoch": 0.012117446015224484,
+      "grad_norm": 0.9660118818283081,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 6.815,
+      "step": 39
+    },
+    {
+      "epoch": 0.012428149759204598,
+      "grad_norm": 1.0026577711105347,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 6.8159,
+      "step": 40
+    },
+    {
+      "epoch": 0.012738853503184714,
+      "grad_norm": 0.9559350609779358,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 6.8132,
+      "step": 41
+    },
+    {
+      "epoch": 0.013049557247164828,
+      "grad_norm": 0.9687345623970032,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 6.8148,
+      "step": 42
+    },
+    {
+      "epoch": 0.013360260991144943,
+      "grad_norm": 0.9497601985931396,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 6.8111,
+      "step": 43
+    },
+    {
+      "epoch": 0.013670964735125059,
+      "grad_norm": 0.9612035155296326,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 6.8119,
+      "step": 44
+    },
+    {
+      "epoch": 0.013981668479105173,
+      "grad_norm": 0.9472883939743042,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 6.8096,
+      "step": 45
+    },
+    {
+      "epoch": 0.014292372223085287,
+      "grad_norm": 0.940109133720398,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 6.8134,
+      "step": 46
+    },
+    {
+      "epoch": 0.014603075967065404,
+      "grad_norm": 0.9567110538482666,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 6.8083,
+      "step": 47
+    },
+    {
+      "epoch": 0.014913779711045518,
+      "grad_norm": 0.9558574557304382,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 6.808,
+      "step": 48
+    },
+    {
+      "epoch": 0.015224483455025632,
+      "grad_norm": 0.9513011574745178,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 6.8101,
+      "step": 49
+    },
+    {
+      "epoch": 0.015535187199005748,
+      "grad_norm": 0.9502997994422913,
+      "learning_rate": 1e-05,
+      "loss": 6.8095,
+      "step": 50
+    },
+    {
+      "epoch": 0.015535187199005748,
+      "eval_loss": 6.804957389831543,
+      "eval_runtime": 0.0973,
+      "eval_samples_per_second": 513.611,
+      "eval_steps_per_second": 133.539,
+      "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": 2852978688000.0,
+  "total_flos": 5705957376000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null