Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:713195626c140ca78fab14e958fd96067f6288a7127f7108372817b8d1503e30
+oid sha256:65e8875236ef10bc11dcfb8ef1f93b7e62f08a0e099dc21147e7224bb2af5eea
 size 119975656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ced00978e0a206731054bad3079b3c9fe08a9bbce68e0b25b7ce2c4fb9d98ff
+oid sha256:b2708833653f82edccd8114b2a284210c643af7cb736712a4b479fbbe7bc5fa4
 size 240145026

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b22d6b8adeb769ea05f31f6e26b64773bb368b2bff4d7a92324be8295a319a8
+oid sha256:d2e6171c3a4121763613624bd8790606df9865eb83836e36ed2f079c13a6c5d8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55d359c84c5ab934d98a583b93abf6d578aff9073b3add3e764975951ef78164
+oid sha256:57ae96fde3ac9abe692305b3013eaefa88bdc3610a37859f712da31f3dc8e39f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b43e62f6d3feeba13ab124a6702cbbb1a7394abd0937e90ae36b6732b950dd7e
+oid sha256:cd80fcb5fffb8dfef8466d823cd6c79e08d2ed91293f2189fbea635198ab1951
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c45c0e63270e65b9547396c63f293652e57c0094e0e6c5d53d519f857984eaa
+oid sha256:9b5f94f3eba3ed7b9be9bb573e15df84f52d2592fac1c462a0bedac3c4bd39f1
 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": 3.6116292476654053,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.004958165478772854,
+  "best_metric": 3.370908737182617,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.009916330957545709,
   "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": 100.475,
       "eval_steps_per_second": 12.562,
       "step": 25
+    },
+    {
+      "epoch": 0.005156492097923768,
+      "grad_norm": 2.5998353958129883,
+      "learning_rate": 5e-05,
+      "loss": 3.692,
+      "step": 26
+    },
+    {
+      "epoch": 0.0053548187170746825,
+      "grad_norm": 3.094146490097046,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.6696,
+      "step": 27
+    },
+    {
+      "epoch": 0.005553145336225597,
+      "grad_norm": 2.0906548500061035,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.6558,
+      "step": 28
+    },
+    {
+      "epoch": 0.005751471955376511,
+      "grad_norm": 1.7006161212921143,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.6573,
+      "step": 29
+    },
+    {
+      "epoch": 0.005949798574527425,
+      "grad_norm": 1.2891594171524048,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.6426,
+      "step": 30
+    },
+    {
+      "epoch": 0.006148125193678339,
+      "grad_norm": 1.0862585306167603,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.5521,
+      "step": 31
+    },
+    {
+      "epoch": 0.006346451812829253,
+      "grad_norm": 0.9556162357330322,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.5382,
+      "step": 32
+    },
+    {
+      "epoch": 0.006544778431980167,
+      "grad_norm": 1.0089380741119385,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.5278,
+      "step": 33
+    },
+    {
+      "epoch": 0.006743105051131081,
+      "grad_norm": 1.2211027145385742,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.5093,
+      "step": 34
+    },
+    {
+      "epoch": 0.006941431670281995,
+      "grad_norm": 1.4732834100723267,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.457,
+      "step": 35
+    },
+    {
+      "epoch": 0.0071397582894329095,
+      "grad_norm": 2.1709494590759277,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.2197,
+      "step": 36
+    },
+    {
+      "epoch": 0.0073380849085838236,
+      "grad_norm": 3.6302006244659424,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.1921,
+      "step": 37
+    },
+    {
+      "epoch": 0.0075364115277347385,
+      "grad_norm": 0.9204977750778198,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.4635,
+      "step": 38
+    },
+    {
+      "epoch": 0.007734738146885653,
+      "grad_norm": 0.9252189993858337,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.4362,
+      "step": 39
+    },
+    {
+      "epoch": 0.007933064766036566,
+      "grad_norm": 0.8253772258758545,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.4837,
+      "step": 40
+    },
+    {
+      "epoch": 0.00813139138518748,
+      "grad_norm": 0.7983177900314331,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.5,
+      "step": 41
+    },
+    {
+      "epoch": 0.008329718004338394,
+      "grad_norm": 0.7896960377693176,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.4902,
+      "step": 42
+    },
+    {
+      "epoch": 0.008528044623489309,
+      "grad_norm": 0.8241143822669983,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.4719,
+      "step": 43
+    },
+    {
+      "epoch": 0.008726371242640222,
+      "grad_norm": 0.9439858794212341,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.5225,
+      "step": 44
+    },
+    {
+      "epoch": 0.008924697861791137,
+      "grad_norm": 0.9598004221916199,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.4675,
+      "step": 45
+    },
+    {
+      "epoch": 0.009123024480942052,
+      "grad_norm": 1.0941156148910522,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.4274,
+      "step": 46
+    },
+    {
+      "epoch": 0.009321351100092965,
+      "grad_norm": 1.3981974124908447,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.3858,
+      "step": 47
+    },
+    {
+      "epoch": 0.00951967771924388,
+      "grad_norm": 1.6733697652816772,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.5181,
+      "step": 48
+    },
+    {
+      "epoch": 0.009718004338394794,
+      "grad_norm": 2.4021451473236084,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.9688,
+      "step": 49
+    },
+    {
+      "epoch": 0.009916330957545709,
+      "grad_norm": 4.111819267272949,
+      "learning_rate": 0.0,
+      "loss": 3.1352,
+      "step": 50
+    },
+    {
+      "epoch": 0.009916330957545709,
+      "eval_loss": 3.370908737182617,
+      "eval_runtime": 338.1749,
+      "eval_samples_per_second": 100.448,
+      "eval_steps_per_second": 12.559,
+      "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": 5.1506187337728e+16,
+  "total_flos": 1.03012374675456e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null