Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01064f8ee8969a5b4aca947682204224c9ee25adf3b9c4d4e20eabb113fc39e7
+oid sha256:6df988f54ce34d8b66c18ae683f341c66a1f787dc4f537dcceb08e1f6df51526
 size 4525640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:add00e6a7286b69c9f8e4f109a8fd00d51303189b45c0fb1d3b216e66122bf59
+oid sha256:fd37b80b4c43a9735c6e719126e0d5e6abe64d99f87bcf0de935767d26074be5
 size 9067978

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05c0adc2b57704611d9fbc6ccfefc69d2e2089bfea3dd819257a19fc9fd84d57
+oid sha256:264c7973cda668f25430c69e0e6a25eaecfb29131d7c00a7160087cc3f667777
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:589335cca8c6cb47a6cf07a1f2778386584ce7ffa89748f01a3df069868367f4
+oid sha256:5deabfff3b23dfbf6fc8a51b8c036452186baec01cdee84298face520d271037
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:179c97ad50cf4e6eafac8f8bfe7539669ce827a4b209b43099e40185e2914224
+oid sha256:1a08b64666e0cb8c126124f50aa0aa84267a978d7af15e7eecaa1998ccd6e18d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8814d167e03cfa4c4f2f78f880b7f45e2b429405d561bc5086f3c5a2b7fd52e5
+oid sha256:d9503e75d07b82ced9adba1e4281d0be5a2b743441746d72d8325ace2fd349de
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.283140182495117,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.23432923257176333,
+  "best_metric": 2.15939998626709,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.46865846514352666,
   "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": 975.695,
       "eval_steps_per_second": 122.132,
       "step": 25
+    },
+    {
+      "epoch": 0.24370240187463385,
+      "grad_norm": 12.770657539367676,
+      "learning_rate": 5e-05,
+      "loss": 4.2317,
+      "step": 26
+    },
+    {
+      "epoch": 0.2530755711775044,
+      "grad_norm": 12.256872177124023,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.9734,
+      "step": 27
+    },
+    {
+      "epoch": 0.2624487404803749,
+      "grad_norm": 12.620009422302246,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.7845,
+      "step": 28
+    },
+    {
+      "epoch": 0.27182190978324544,
+      "grad_norm": 13.734941482543945,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.6367,
+      "step": 29
+    },
+    {
+      "epoch": 0.281195079086116,
+      "grad_norm": 13.673043251037598,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.554,
+      "step": 30
+    },
+    {
+      "epoch": 0.29056824838898654,
+      "grad_norm": 13.149415969848633,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.2785,
+      "step": 31
+    },
+    {
+      "epoch": 0.29994141769185706,
+      "grad_norm": 13.390870094299316,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.2042,
+      "step": 32
+    },
+    {
+      "epoch": 0.3093145869947276,
+      "grad_norm": 12.210992813110352,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.0077,
+      "step": 33
+    },
+    {
+      "epoch": 0.3186877562975981,
+      "grad_norm": 11.547277450561523,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.8702,
+      "step": 34
+    },
+    {
+      "epoch": 0.3280609256004687,
+      "grad_norm": 11.762548446655273,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.8338,
+      "step": 35
+    },
+    {
+      "epoch": 0.3374340949033392,
+      "grad_norm": 10.924531936645508,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.6657,
+      "step": 36
+    },
+    {
+      "epoch": 0.3468072642062097,
+      "grad_norm": 11.15406322479248,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.4972,
+      "step": 37
+    },
+    {
+      "epoch": 0.35618043350908024,
+      "grad_norm": 10.379179000854492,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.6364,
+      "step": 38
+    },
+    {
+      "epoch": 0.3655536028119508,
+      "grad_norm": 10.591771125793457,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.4719,
+      "step": 39
+    },
+    {
+      "epoch": 0.37492677211482134,
+      "grad_norm": 10.571476936340332,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.3302,
+      "step": 40
+    },
+    {
+      "epoch": 0.38429994141769186,
+      "grad_norm": 10.627779006958008,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.2841,
+      "step": 41
+    },
+    {
+      "epoch": 0.3936731107205624,
+      "grad_norm": 10.701957702636719,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.2543,
+      "step": 42
+    },
+    {
+      "epoch": 0.4030462800234329,
+      "grad_norm": 10.787554740905762,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.2541,
+      "step": 43
+    },
+    {
+      "epoch": 0.4124194493263035,
+      "grad_norm": 10.766562461853027,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.2785,
+      "step": 44
+    },
+    {
+      "epoch": 0.421792618629174,
+      "grad_norm": 10.696857452392578,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.1263,
+      "step": 45
+    },
+    {
+      "epoch": 0.4311657879320445,
+      "grad_norm": 10.436224937438965,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.1326,
+      "step": 46
+    },
+    {
+      "epoch": 0.44053895723491504,
+      "grad_norm": 10.621663093566895,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.185,
+      "step": 47
+    },
+    {
+      "epoch": 0.44991212653778556,
+      "grad_norm": 10.477226257324219,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.1113,
+      "step": 48
+    },
+    {
+      "epoch": 0.45928529584065614,
+      "grad_norm": 10.463092803955078,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.1375,
+      "step": 49
+    },
+    {
+      "epoch": 0.46865846514352666,
+      "grad_norm": 10.640161514282227,
+      "learning_rate": 0.0,
+      "loss": 2.155,
+      "step": 50
+    },
+    {
+      "epoch": 0.46865846514352666,
+      "eval_loss": 2.15939998626709,
+      "eval_runtime": 0.7372,
+      "eval_samples_per_second": 975.261,
+      "eval_steps_per_second": 122.077,
+      "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": 1753141896806400.0,
+  "total_flos": 3506283793612800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null