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:dd4d6d17784d64c6decf5c0fe971acb41b635e1b16c5f0c42f6887d672201a35
+oid sha256:f77b6e0218fc19d1c970d2a929dc8c7c3598fb3d2c4d959118ba5a4aa5efab47
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2716da832c327e6da4476b90bfd2d0ec987a13b706c6b06df8fd8e502d8a3a0
+oid sha256:1a1c296964f8e553b9952ae02cffea7e26b58bca8d858c25b9d55c6c52383257
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e097d9f6454831dff8a1a933d7ea6bfb79fe751b5bd7634b15d02e56b82c7dca
+oid sha256:40579a9deeb556132312bb7eee3e1f7d9b89cf12f5d1c9dd5c2206947bc9eefc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d62e9e5db138dc6872e092294d02175f5392caa0ac410eac23cb40fa47d9e8
+oid sha256:4c91b66366b2d7bbc2ab60f67f6cf110c717846b350c919b2113ac38826b7b83
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5f957c0475dbca2432de5298aaacb046f21ed89393d8336b0187f192f3c4128
+oid sha256:2661aa807af39293746e7b57a62ba4e17e53c1cecc04329899de692e3fb2b4fe
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10be70e87252a8c20155484b3f8b60fe75765a80d8c4d62d172591492e561e59
+oid sha256:2b811be01d6907d27d7372cbbe28e45508597e1dd2ed49a4c9270d6015874776
 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": 10.34911823272705,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.34934497816593885,
+  "best_metric": 10.344432830810547,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6986899563318777,
   "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": 478.469,
       "eval_steps_per_second": 124.402,
       "step": 25
+    },
+    {
+      "epoch": 0.36331877729257644,
+      "grad_norm": 0.11566270887851715,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3624,
+      "step": 26
+    },
+    {
+      "epoch": 0.377292576419214,
+      "grad_norm": 0.12949135899543762,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.358,
+      "step": 27
+    },
+    {
+      "epoch": 0.39126637554585153,
+      "grad_norm": 0.140901580452919,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3559,
+      "step": 28
+    },
+    {
+      "epoch": 0.4052401746724891,
+      "grad_norm": 0.14029686152935028,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3539,
+      "step": 29
+    },
+    {
+      "epoch": 0.4192139737991266,
+      "grad_norm": 0.15310536324977875,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.3534,
+      "step": 30
+    },
+    {
+      "epoch": 0.4331877729257642,
+      "grad_norm": 0.13963443040847778,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.3492,
+      "step": 31
+    },
+    {
+      "epoch": 0.44716157205240176,
+      "grad_norm": 0.15991738438606262,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3449,
+      "step": 32
+    },
+    {
+      "epoch": 0.4611353711790393,
+      "grad_norm": 0.16402499377727509,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.3439,
+      "step": 33
+    },
+    {
+      "epoch": 0.47510917030567684,
+      "grad_norm": 0.17659306526184082,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.3394,
+      "step": 34
+    },
+    {
+      "epoch": 0.4890829694323144,
+      "grad_norm": 0.19355088472366333,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.3369,
+      "step": 35
+    },
+    {
+      "epoch": 0.503056768558952,
+      "grad_norm": 0.19989122450351715,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.331,
+      "step": 36
+    },
+    {
+      "epoch": 0.5170305676855895,
+      "grad_norm": 0.267549604177475,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3273,
+      "step": 37
+    },
+    {
+      "epoch": 0.5310043668122271,
+      "grad_norm": 0.11852973699569702,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3526,
+      "step": 38
+    },
+    {
+      "epoch": 0.5449781659388646,
+      "grad_norm": 0.11729513853788376,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.3553,
+      "step": 39
+    },
+    {
+      "epoch": 0.5589519650655022,
+      "grad_norm": 0.11852356791496277,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.3543,
+      "step": 40
+    },
+    {
+      "epoch": 0.5729257641921397,
+      "grad_norm": 0.12188510596752167,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.3498,
+      "step": 41
+    },
+    {
+      "epoch": 0.5868995633187772,
+      "grad_norm": 0.12156735360622406,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.353,
+      "step": 42
+    },
+    {
+      "epoch": 0.6008733624454149,
+      "grad_norm": 0.1305505484342575,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.3478,
+      "step": 43
+    },
+    {
+      "epoch": 0.6148471615720524,
+      "grad_norm": 0.15021030604839325,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.3479,
+      "step": 44
+    },
+    {
+      "epoch": 0.62882096069869,
+      "grad_norm": 0.13688212633132935,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.3464,
+      "step": 45
+    },
+    {
+      "epoch": 0.6427947598253275,
+      "grad_norm": 0.16216903924942017,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.3426,
+      "step": 46
+    },
+    {
+      "epoch": 0.6567685589519651,
+      "grad_norm": 0.15822577476501465,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.3397,
+      "step": 47
+    },
+    {
+      "epoch": 0.6707423580786026,
+      "grad_norm": 0.18622951209545135,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.336,
+      "step": 48
+    },
+    {
+      "epoch": 0.6847161572052402,
+      "grad_norm": 0.2275187373161316,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.3309,
+      "step": 49
+    },
+    {
+      "epoch": 0.6986899563318777,
+      "grad_norm": 0.29126372933387756,
+      "learning_rate": 1e-05,
+      "loss": 10.3213,
+      "step": 50
+    },
+    {
+      "epoch": 0.6986899563318777,
+      "eval_loss": 10.344432830810547,
+      "eval_runtime": 0.0972,
+      "eval_samples_per_second": 514.324,
+      "eval_steps_per_second": 133.724,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null