Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cb15f7497c1bf71c5a600052787c5219bd0d84562ac42eae2395310e773072a
+oid sha256:a19a62b2ba44f3b51fd6582d8026c86d413fe4ee144fb4b9e9c340fd2ac90f2b
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f05574c1ac504b2b6c15582120d5051f937d81f5917a0d17c96eb844cd629210
+oid sha256:04bf15685e87900452ec97e8abb9b3096693f5703ab0768b8f40e73764f393dc
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc47bb419b27f319e07623c8e78002cc7e23a41471a2c91ecd01ceafc7125f44
+oid sha256:2ed5457bfa08da8246eac2b7dbb4448cd5d202e14c558ee96602969ee7dfd2cc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2373739149b5a18a4e74e44703db733ec2ccd3ff66b41c1be9abfa0d33a5b236
+oid sha256:d04d998cf9c55cc12116a62123c235e4b06347813186da18fc654f280a1bbd2b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19e60f5a0ec22521b0e4a0e746a14a7a280341e4acecb0b18c090234481429ce
+oid sha256:ae08f5c783c1dd72fa08217b8798c7e29f937cf2e739e74e27a18625c942f9b6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8866ae441496b79135b784cb349089cdf61175a47486cdda9166e909a24d512
+oid sha256:d8785856d5fd84921ec274092503304eb51db99ba8efdb2a13761c8192b8ac9b
 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": 1.709513545036316,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.11477761836441894,
+  "best_metric": 0.9616518616676331,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.22955523672883787,
   "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": 33.928,
       "eval_steps_per_second": 4.253,
       "step": 25
+    },
+    {
+      "epoch": 0.1193687230989957,
+      "grad_norm": 74.11042022705078,
+      "learning_rate": 5e-05,
+      "loss": 0.7463,
+      "step": 26
+    },
+    {
+      "epoch": 0.12395982783357246,
+      "grad_norm": 34.46171569824219,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3697,
+      "step": 27
+    },
+    {
+      "epoch": 0.1285509325681492,
+      "grad_norm": 21.73426628112793,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2139,
+      "step": 28
+    },
+    {
+      "epoch": 0.13314203730272597,
+      "grad_norm": 10.719658851623535,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1253,
+      "step": 29
+    },
+    {
+      "epoch": 0.13773314203730272,
+      "grad_norm": 14.40205192565918,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1023,
+      "step": 30
+    },
+    {
+      "epoch": 0.1423242467718795,
+      "grad_norm": 28.01376724243164,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0992,
+      "step": 31
+    },
+    {
+      "epoch": 0.14691535150645624,
+      "grad_norm": 740.5331420898438,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 4.7911,
+      "step": 32
+    },
+    {
+      "epoch": 0.151506456241033,
+      "grad_norm": 1348.0220947265625,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 6.519,
+      "step": 33
+    },
+    {
+      "epoch": 0.15609756097560976,
+      "grad_norm": 1065.9749755859375,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.5851,
+      "step": 34
+    },
+    {
+      "epoch": 0.1606886657101865,
+      "grad_norm": 732.408447265625,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.0265,
+      "step": 35
+    },
+    {
+      "epoch": 0.16527977044476327,
+      "grad_norm": 716.4056396484375,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.8283,
+      "step": 36
+    },
+    {
+      "epoch": 0.16987087517934002,
+      "grad_norm": 457.7398376464844,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.1625,
+      "step": 37
+    },
+    {
+      "epoch": 0.1744619799139168,
+      "grad_norm": 105.070068359375,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1766,
+      "step": 38
+    },
+    {
+      "epoch": 0.17905308464849354,
+      "grad_norm": 31.545076370239258,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3267,
+      "step": 39
+    },
+    {
+      "epoch": 0.1836441893830703,
+      "grad_norm": 23.66084098815918,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2023,
+      "step": 40
+    },
+    {
+      "epoch": 0.18823529411764706,
+      "grad_norm": 11.72018814086914,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1194,
+      "step": 41
+    },
+    {
+      "epoch": 0.19282639885222383,
+      "grad_norm": 8.387150764465332,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0795,
+      "step": 42
+    },
+    {
+      "epoch": 0.19741750358680057,
+      "grad_norm": 9.269184112548828,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0675,
+      "step": 43
+    },
+    {
+      "epoch": 0.20200860832137732,
+      "grad_norm": 47.77657699584961,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6034,
+      "step": 44
+    },
+    {
+      "epoch": 0.2065997130559541,
+      "grad_norm": 180.4890899658203,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.0342,
+      "step": 45
+    },
+    {
+      "epoch": 0.21119081779053084,
+      "grad_norm": 320.1153564453125,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.859,
+      "step": 46
+    },
+    {
+      "epoch": 0.2157819225251076,
+      "grad_norm": 491.2322998046875,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.6845,
+      "step": 47
+    },
+    {
+      "epoch": 0.22037302725968436,
+      "grad_norm": 501.812744140625,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.8207,
+      "step": 48
+    },
+    {
+      "epoch": 0.22496413199426113,
+      "grad_norm": 318.70819091796875,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.6314,
+      "step": 49
+    },
+    {
+      "epoch": 0.22955523672883787,
+      "grad_norm": 515.6896362304688,
+      "learning_rate": 0.0,
+      "loss": 1.5723,
+      "step": 50
+    },
+    {
+      "epoch": 0.22955523672883787,
+      "eval_loss": 0.9616518616676331,
+      "eval_runtime": 43.2639,
+      "eval_samples_per_second": 33.931,
+      "eval_steps_per_second": 4.253,
+      "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": 2.8325501516906496e+17,
+  "total_flos": 5.6633321727197184e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null