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:b1c5e67b61328860321abe11b34d8145790375ddb51c3ca772699b8b7664ff8b
+oid sha256:43c9ffe67c3542cfc35e03a482d8f058af3b1537ca8b7f6bcf437791d5d932a0
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6baf771c06bc1f5ccff65e035cf09a8be35026f4136f60674509c6fcacd9dd5a
+oid sha256:1398f07cfe2c2d0fa78ddc77c07ec65ae47167dd721a70ee2867b7064927ae8b
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92d5ca3549ac694760e6b674a954293f69fff505b8215eebb2a2ff191bc2ac5f
+oid sha256:dcb423f5eb7d3beac4c4c0ff0d0e81fbf93d49c2b7ae1aa50168ca24f187ca0f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:537cab25a38093b28111145673c530054f4af2e83d88473ecd1b8a7b6e349860
+oid sha256:f348539b760ab18f74cb87a5dea2338cc05d7b32aea1de05a89e22d1a6dea900
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c637127920aca2058187b83ded34bb030156a6e01ce3523de1fb1e3639de412
+oid sha256:0cdac2c641d7ead52364f743053cea26ff05cc982002bb9756ef52281e551983
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e494814f542224369a14182c3c5d48414edc0a5e59479d7f76297b50fdee847
+oid sha256:df8ce32811210258c40727caef6ae494ef067a9047d7b5dba396e97d39432163
 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": 4.197577953338623,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.34873583260680036,
+  "best_metric": 4.016265392303467,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6974716652136007,
   "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": 24.077,
       "eval_steps_per_second": 6.26,
       "step": 25
+    },
+    {
+      "epoch": 0.36268526591107236,
+      "grad_norm": 3.973175048828125,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 4.4533,
+      "step": 26
+    },
+    {
+      "epoch": 0.37663469921534437,
+      "grad_norm": 4.574081897735596,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.4782,
+      "step": 27
+    },
+    {
+      "epoch": 0.3905841325196164,
+      "grad_norm": 4.432999610900879,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 4.6537,
+      "step": 28
+    },
+    {
+      "epoch": 0.4045335658238884,
+      "grad_norm": 3.599513530731201,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.4924,
+      "step": 29
+    },
+    {
+      "epoch": 0.4184829991281604,
+      "grad_norm": 3.2482171058654785,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 4.517,
+      "step": 30
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 2.7505600452423096,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 4.4046,
+      "step": 31
+    },
+    {
+      "epoch": 0.44638186573670446,
+      "grad_norm": 2.255084276199341,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 4.154,
+      "step": 32
+    },
+    {
+      "epoch": 0.46033129904097647,
+      "grad_norm": 1.9739567041397095,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 4.3462,
+      "step": 33
+    },
+    {
+      "epoch": 0.4742807323452485,
+      "grad_norm": 1.9505712985992432,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.0326,
+      "step": 34
+    },
+    {
+      "epoch": 0.4882301656495205,
+      "grad_norm": 2.435300350189209,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 4.1367,
+      "step": 35
+    },
+    {
+      "epoch": 0.5021795989537925,
+      "grad_norm": 3.183511257171631,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.8502,
+      "step": 36
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 3.9571962356567383,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 3.8177,
+      "step": 37
+    },
+    {
+      "epoch": 0.5300784655623365,
+      "grad_norm": 1.17935049533844,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 4.0578,
+      "step": 38
+    },
+    {
+      "epoch": 0.5440278988666085,
+      "grad_norm": 1.1350454092025757,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 4.1775,
+      "step": 39
+    },
+    {
+      "epoch": 0.5579773321708805,
+      "grad_norm": 1.0570968389511108,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.1952,
+      "step": 40
+    },
+    {
+      "epoch": 0.5719267654751525,
+      "grad_norm": 1.0743228197097778,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 4.2512,
+      "step": 41
+    },
+    {
+      "epoch": 0.5858761987794245,
+      "grad_norm": 1.1253777742385864,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 4.266,
+      "step": 42
+    },
+    {
+      "epoch": 0.5998256320836965,
+      "grad_norm": 1.2194774150848389,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 4.1919,
+      "step": 43
+    },
+    {
+      "epoch": 0.6137750653879687,
+      "grad_norm": 1.2656453847885132,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 4.2019,
+      "step": 44
+    },
+    {
+      "epoch": 0.6277244986922407,
+      "grad_norm": 1.4768873453140259,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.191,
+      "step": 45
+    },
+    {
+      "epoch": 0.6416739319965127,
+      "grad_norm": 1.5102301836013794,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.0265,
+      "step": 46
+    },
+    {
+      "epoch": 0.6556233653007847,
+      "grad_norm": 1.6276775598526,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.0218,
+      "step": 47
+    },
+    {
+      "epoch": 0.6695727986050567,
+      "grad_norm": 1.962693214416504,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.9513,
+      "step": 48
+    },
+    {
+      "epoch": 0.6835222319093287,
+      "grad_norm": 2.404271364212036,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 3.7333,
+      "step": 49
+    },
+    {
+      "epoch": 0.6974716652136007,
+      "grad_norm": 4.255843639373779,
+      "learning_rate": 1e-05,
+      "loss": 3.6049,
+      "step": 50
+    },
+    {
+      "epoch": 0.6974716652136007,
+      "eval_loss": 4.016265392303467,
+      "eval_runtime": 2.0762,
+      "eval_samples_per_second": 24.082,
+      "eval_steps_per_second": 6.261,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null