Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee41b9b4612c6e22740b56d928486b447441af09f94b7b26af3234d87b01bfa
+oid sha256:8eec7b86cc08727138af61c05b2cbb0629cc6fdb86ded9e5e99837d2678d2dd4
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82216ff0e830dc15595b941198f99a5c1c29be997505b99d58fa7654ffa6014e
+oid sha256:ad9f80e884f1cfd7dbfc579938f1f30d12821d76d9f216e04c2cb0cec46d5e31
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95fb48fd22e6c2a376769b4dbb15d468a6a253676a538f44df0b135f67fbbc41
+oid sha256:56216a6c58bc6ab3a1dfc75f31768d606f47c1006e7fa6dbe6575b10dfff1c28
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af0153594cc6d980b75778b7926f1dc7aad8f6cfaa494fef6200f9489aa4082
+oid sha256:99dd115d4304a37d308ad84e7b4bcd429693d63cf0ccda0df88328ba71d9f298
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5f35d2221559e61bf5d837b931a6b3dc1911559d490b8418d64138f6c19888e
+oid sha256:2e331ca5a81d68b4da49b6e4557e6306ef4d62f7e5131d2272125b0eba17d7a4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7414c99693e5554f6d248a904992a9312b6da10ca0a3b3a44f192dd6dd92e1a2
+oid sha256:aab9a08d28f671bc1d7a0dbbd5d6d65f25ae2f84d71fdc06449224f823b74309
 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": 3.5030836443183944e-05,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08131734092295181,
+  "best_metric": 2.398091419308912e-05,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.16263468184590363,
   "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": 16.682,
       "eval_steps_per_second": 4.337,
       "step": 25
+    },
+    {
+      "epoch": 0.08457003455986989,
+      "grad_norm": 0.5809001326560974,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0041,
+      "step": 26
+    },
+    {
+      "epoch": 0.08782272819678796,
+      "grad_norm": 0.7393910884857178,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0034,
+      "step": 27
+    },
+    {
+      "epoch": 0.09107542183370604,
+      "grad_norm": 0.7353512644767761,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0025,
+      "step": 28
+    },
+    {
+      "epoch": 0.09432811547062411,
+      "grad_norm": 0.04128008335828781,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0018,
+      "step": 29
+    },
+    {
+      "epoch": 0.09758080910754219,
+      "grad_norm": 0.007420813199132681,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0006,
+      "step": 30
+    },
+    {
+      "epoch": 0.10083350274446026,
+      "grad_norm": 0.03794967010617256,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0009,
+      "step": 31
+    },
+    {
+      "epoch": 0.10408619638137832,
+      "grad_norm": 0.15001359581947327,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0019,
+      "step": 32
+    },
+    {
+      "epoch": 0.1073388900182964,
+      "grad_norm": 0.011495936661958694,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0009,
+      "step": 33
+    },
+    {
+      "epoch": 0.11059158365521447,
+      "grad_norm": 0.030072197318077087,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0011,
+      "step": 34
+    },
+    {
+      "epoch": 0.11384427729213255,
+      "grad_norm": 0.01134544238448143,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0008,
+      "step": 35
+    },
+    {
+      "epoch": 0.11709697092905062,
+      "grad_norm": 0.055174022912979126,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.002,
+      "step": 36
+    },
+    {
+      "epoch": 0.1203496645659687,
+      "grad_norm": 0.048915062099695206,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0015,
+      "step": 37
+    },
+    {
+      "epoch": 0.12360235820288677,
+      "grad_norm": 2.390549659729004,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.1271,
+      "step": 38
+    },
+    {
+      "epoch": 0.12685505183980483,
+      "grad_norm": 0.6761870980262756,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0114,
+      "step": 39
+    },
+    {
+      "epoch": 0.1301077454767229,
+      "grad_norm": 0.011089229956269264,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0007,
+      "step": 40
+    },
+    {
+      "epoch": 0.13336043911364098,
+      "grad_norm": 0.00595944095402956,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0006,
+      "step": 41
+    },
+    {
+      "epoch": 0.13661313275055906,
+      "grad_norm": 0.011473946273326874,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0006,
+      "step": 42
+    },
+    {
+      "epoch": 0.13986582638747713,
+      "grad_norm": 0.08607928454875946,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0021,
+      "step": 43
+    },
+    {
+      "epoch": 0.1431185200243952,
+      "grad_norm": 0.0036287973634898663,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0004,
+      "step": 44
+    },
+    {
+      "epoch": 0.14637121366131328,
+      "grad_norm": 0.008640116080641747,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0007,
+      "step": 45
+    },
+    {
+      "epoch": 0.14962390729823136,
+      "grad_norm": 0.010114687494933605,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0007,
+      "step": 46
+    },
+    {
+      "epoch": 0.15287660093514943,
+      "grad_norm": 7.031486988067627,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0345,
+      "step": 47
+    },
+    {
+      "epoch": 0.1561292945720675,
+      "grad_norm": 0.1903190314769745,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0009,
+      "step": 48
+    },
+    {
+      "epoch": 0.15938198820898555,
+      "grad_norm": 0.00516266655176878,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0005,
+      "step": 49
+    },
+    {
+      "epoch": 0.16263468184590363,
+      "grad_norm": 0.008884044364094734,
+      "learning_rate": 1e-05,
+      "loss": 0.0006,
+      "step": 50
+    },
+    {
+      "epoch": 0.16263468184590363,
+      "eval_loss": 2.398091419308912e-05,
+      "eval_runtime": 2.9987,
+      "eval_samples_per_second": 16.674,
+      "eval_steps_per_second": 4.335,
+      "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": 2.629578157719552e+17,
+  "total_flos": 5.259156315439104e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null