Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34a0cf6fb5abe1be29c9bdfc7e0ed743a6ece20cc79574d2f178b51378f4119b
+oid sha256:1475272f3440cb336263b413ee4d5329dcb277dac21c72c0f0a7fc0a42f03371
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d05520e86f38ec2a1f1f25d2556d9ab851aadd7377b266a9e936cb627844b31
+oid sha256:e3c4751e81e362b8f39f7649b79fc5078434e5924467447b79b57945e6ccac73
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf50df02d00f03e9274426cf160adf25c5d61e27a8f6d71a4c8c5d9531392acd
+oid sha256:b60806d9eb74645038e95d587478bbb819f8874e5bfc07240dac2b31b5be74ab
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64890e6f36dc9134ec86afcf574c4a0323d4453600c7bac0237fa02e607ce3d3
+oid sha256:2c3b503957ab4202d6b69d3be7c840126f1715d893c04b2a9db32e2f934c88d9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:762d145cf2d2c53c65bdd193e21c2ca22d6a007eee6ad5b23de5974ffdb72ad8
+oid sha256:73063f6a316d680eb29d574e26024c11cd3de61aaeb6e78155209ebcfe81c8d9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9de9ad323d6255f4f22a886c990fbd02d14f7a792a344089ffcb43792578d23e
+oid sha256:a8466bb20895b5e3f9921f222956751b32211f06e127da813c3b9a266991ca0f
 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": 0.08991359174251556,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.3498349834983498,
+  "best_metric": 0.03536833077669144,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.6996699669966997,
   "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": 28.034,
       "eval_steps_per_second": 3.504,
       "step": 25
+    },
+    {
+      "epoch": 1.4026402640264026,
+      "grad_norm": 49.3033561706543,
+      "learning_rate": 5e-05,
+      "loss": 0.6019,
+      "step": 26
+    },
+    {
+      "epoch": 1.4554455445544554,
+      "grad_norm": 40.293243408203125,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.6071,
+      "step": 27
+    },
+    {
+      "epoch": 1.5082508250825084,
+      "grad_norm": 52.87701416015625,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.4937,
+      "step": 28
+    },
+    {
+      "epoch": 1.561056105610561,
+      "grad_norm": 46.945491790771484,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7908,
+      "step": 29
+    },
+    {
+      "epoch": 1.613861386138614,
+      "grad_norm": 58.49090576171875,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5764,
+      "step": 30
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 34.49781036376953,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2,
+      "step": 31
+    },
+    {
+      "epoch": 1.7194719471947195,
+      "grad_norm": 45.59718704223633,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.6603,
+      "step": 32
+    },
+    {
+      "epoch": 1.7722772277227723,
+      "grad_norm": 26.68146324157715,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.685,
+      "step": 33
+    },
+    {
+      "epoch": 1.825082508250825,
+      "grad_norm": 29.098257064819336,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.4208,
+      "step": 34
+    },
+    {
+      "epoch": 1.8778877887788779,
+      "grad_norm": 36.968624114990234,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.17,
+      "step": 35
+    },
+    {
+      "epoch": 1.9306930693069306,
+      "grad_norm": 20.257652282714844,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1213,
+      "step": 36
+    },
+    {
+      "epoch": 2.0132013201320134,
+      "grad_norm": 20.416902542114258,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3783,
+      "step": 37
+    },
+    {
+      "epoch": 2.066006600660066,
+      "grad_norm": 14.051177978515625,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1184,
+      "step": 38
+    },
+    {
+      "epoch": 2.118811881188119,
+      "grad_norm": 9.072379112243652,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.07,
+      "step": 39
+    },
+    {
+      "epoch": 2.1716171617161715,
+      "grad_norm": 14.456093788146973,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0421,
+      "step": 40
+    },
+    {
+      "epoch": 2.2244224422442245,
+      "grad_norm": 8.208637237548828,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0268,
+      "step": 41
+    },
+    {
+      "epoch": 2.2772277227722775,
+      "grad_norm": 33.25442886352539,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2891,
+      "step": 42
+    },
+    {
+      "epoch": 2.33003300330033,
+      "grad_norm": 8.580497741699219,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0713,
+      "step": 43
+    },
+    {
+      "epoch": 2.382838283828383,
+      "grad_norm": 5.246236801147461,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0203,
+      "step": 44
+    },
+    {
+      "epoch": 2.4356435643564356,
+      "grad_norm": 3.4388229846954346,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0178,
+      "step": 45
+    },
+    {
+      "epoch": 2.4884488448844886,
+      "grad_norm": 18.330442428588867,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4954,
+      "step": 46
+    },
+    {
+      "epoch": 2.541254125412541,
+      "grad_norm": 10.584196090698242,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1212,
+      "step": 47
+    },
+    {
+      "epoch": 2.594059405940594,
+      "grad_norm": 19.070772171020508,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0592,
+      "step": 48
+    },
+    {
+      "epoch": 2.6468646864686467,
+      "grad_norm": 24.324411392211914,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0942,
+      "step": 49
+    },
+    {
+      "epoch": 2.6996699669966997,
+      "grad_norm": 9.229938507080078,
+      "learning_rate": 0.0,
+      "loss": 0.2343,
+      "step": 50
+    },
+    {
+      "epoch": 2.6996699669966997,
+      "eval_loss": 0.03536833077669144,
+      "eval_runtime": 4.8433,
+      "eval_samples_per_second": 26.428,
+      "eval_steps_per_second": 3.304,
+      "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": 2.975768971501896e+17,
+  "total_flos": 5.932088473514148e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null