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:bc2f9dad5e3294ee97347a6f6802c09fd3736adc5742fe8c448e800f375a055a
+oid sha256:05e7414837a27b5640b12af9857e2249eee2f2942a01fc1dbafd75661e42eded
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff8059a35e12ff343af97ec703af329724193101f949484a203105b41c26e55
+oid sha256:19ae4178fbf899f0ac4b1d94a66334f50c35220e3b090e085e0cd50c57078df9
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d26d3046659bab6f022660165070407e2c256280653ed1376ca89db8c92176e
+oid sha256:2729cf7f97fc8c454cd995893e338a34249c2f88f3f239abdedc1d32c36d0d4c
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86cbff278f5a4ae09d0b116f1d935b2abbd326fa413fc68f6862d519132a7dbc
+oid sha256:5256a0963d822816d4fba388818296fe267e8e1ec6c0f00c6f4203b87c085eb9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b29fe32e3ba865a0620b4321f227bca627c11d4172a43a2dbf6bc0c70164acb4
+oid sha256:163edec43530e09d4de92821f59e5355a77bd89a8f047ce7839a91024bc7e21c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf59e4c700afda8381e7b99bd939305e254334bcd0613ff028a01fb3dbbfd962
+oid sha256:71ff258ce6de5aad51a473fad6e81d13e70bbf07d625012a6dfbb4ed54d0c21d
 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": 0.03601743280887604,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.20080321285140562,
+  "best_metric": 0.03248881921172142,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.40160642570281124,
   "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": 9.191,
       "eval_steps_per_second": 2.39,
       "step": 25
+    },
+    {
+      "epoch": 0.20883534136546184,
+      "grad_norm": 0.546523928642273,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.1084,
+      "step": 26
+    },
+    {
+      "epoch": 0.21686746987951808,
+      "grad_norm": 0.4799603223800659,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.9756,
+      "step": 27
+    },
+    {
+      "epoch": 0.2248995983935743,
+      "grad_norm": 0.5448339581489563,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.2519,
+      "step": 28
+    },
+    {
+      "epoch": 0.23293172690763053,
+      "grad_norm": 0.4197559952735901,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.6386,
+      "step": 29
+    },
+    {
+      "epoch": 0.24096385542168675,
+      "grad_norm": 0.5254598259925842,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.1602,
+      "step": 30
+    },
+    {
+      "epoch": 0.24899598393574296,
+      "grad_norm": 0.5117546319961548,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.896,
+      "step": 31
+    },
+    {
+      "epoch": 0.2570281124497992,
+      "grad_norm": 0.7296671271324158,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.3107,
+      "step": 32
+    },
+    {
+      "epoch": 0.26506024096385544,
+      "grad_norm": 1.1409062147140503,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.4452,
+      "step": 33
+    },
+    {
+      "epoch": 0.27309236947791166,
+      "grad_norm": 2.794985055923462,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.6358,
+      "step": 34
+    },
+    {
+      "epoch": 0.28112449799196787,
+      "grad_norm": 14.123102188110352,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.8044,
+      "step": 35
+    },
+    {
+      "epoch": 0.2891566265060241,
+      "grad_norm": 0.567223310470581,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0429,
+      "step": 36
+    },
+    {
+      "epoch": 0.2971887550200803,
+      "grad_norm": 0.49257692694664,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0362,
+      "step": 37
+    },
+    {
+      "epoch": 0.30522088353413657,
+      "grad_norm": 1.7930783033370972,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.5118,
+      "step": 38
+    },
+    {
+      "epoch": 0.3132530120481928,
+      "grad_norm": 0.8841942548751831,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4644,
+      "step": 39
+    },
+    {
+      "epoch": 0.321285140562249,
+      "grad_norm": 0.30380862951278687,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.3108,
+      "step": 40
+    },
+    {
+      "epoch": 0.3293172690763052,
+      "grad_norm": 0.4109308421611786,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.8338,
+      "step": 41
+    },
+    {
+      "epoch": 0.3373493975903614,
+      "grad_norm": 0.37386301159858704,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.1962,
+      "step": 42
+    },
+    {
+      "epoch": 0.3453815261044177,
+      "grad_norm": 0.5806508660316467,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.1743,
+      "step": 43
+    },
+    {
+      "epoch": 0.3534136546184739,
+      "grad_norm": 0.7219189405441284,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.6337,
+      "step": 44
+    },
+    {
+      "epoch": 0.3614457831325301,
+      "grad_norm": 0.889197826385498,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.6495,
+      "step": 45
+    },
+    {
+      "epoch": 0.36947791164658633,
+      "grad_norm": 2.914224863052368,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.9181,
+      "step": 46
+    },
+    {
+      "epoch": 0.37751004016064255,
+      "grad_norm": 3.432201862335205,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.3767,
+      "step": 47
+    },
+    {
+      "epoch": 0.3855421686746988,
+      "grad_norm": 0.26241597533226013,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.028,
+      "step": 48
+    },
+    {
+      "epoch": 0.39357429718875503,
+      "grad_norm": 0.29001384973526,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0255,
+      "step": 49
+    },
+    {
+      "epoch": 0.40160642570281124,
+      "grad_norm": 0.43991392850875854,
+      "learning_rate": 1e-05,
+      "loss": 0.0338,
+      "step": 50
+    },
+    {
+      "epoch": 0.40160642570281124,
+      "eval_loss": 0.03248881921172142,
+      "eval_runtime": 5.4412,
+      "eval_samples_per_second": 9.189,
+      "eval_steps_per_second": 2.389,
+      "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": 2.5406115984860774e+17,
+  "total_flos": 5.0840048862285005e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null