Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a40cd0979e65032f19f1de74a75db8dd137dc29ae527f9f00994aa49b544d9f
+oid sha256:f30d5faa68e15fc23a304748781f726b4cb5de4c10e7cb9f7e6936e06062bd15
 size 261131840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd305cf12b6914c13ebc5daa6ac7546a24e2ce30699352d6e90a0610697c331b
+oid sha256:0f5bf5156157beab687d635e43d6a5a2511115c5b4ca71798e26bf4f26b99897
 size 522406650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2db9490ed0061ec4649a6907ee3385d20901969cc3995ed543d870c1d99dd1c
+oid sha256:688ad9bef1d295a6b2b4989a03c193a9bd5dfbe8226b17b27410a595faaf7807
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cf726151b3fa27e0d864f1aa44069fba59d21d5fce5cc65643319b5eb994cd6
+oid sha256:86b4507b08c7b5933ea23541f3876105e3f49ec3955469805f32787f71280bf4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24639ba7cd1b06cdb05eb7338068a79aa2c5c48ab54ccde3d9b54aa014273891
+oid sha256:06de16b3c04a1423448a48e49f61c53fb20b2749cc7cd8a1c6b8aa136555d06b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95bbc892702c6b90e62de20bb84110ed681c7c9e8e95070b941ee8c55cb01e85
+oid sha256:7f5910f1e61f2c4103985d9e211326b5822988db58c8f9aa4018f7bdc1a22f1e
 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": 3.751025676727295,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.005759373380176237,
+  "best_metric": 3.3264994621276855,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.011518746760352474,
   "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": 18.737,
       "eval_steps_per_second": 2.343,
       "step": 25
+    },
+    {
+      "epoch": 0.005989748315383286,
+      "grad_norm": 189.20632934570312,
+      "learning_rate": 5e-05,
+      "loss": 63.6113,
+      "step": 26
+    },
+    {
+      "epoch": 0.006220123250590336,
+      "grad_norm": 177.3588409423828,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 62.7124,
+      "step": 27
+    },
+    {
+      "epoch": 0.006450498185797385,
+      "grad_norm": 135.85980224609375,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 62.7468,
+      "step": 28
+    },
+    {
+      "epoch": 0.006680873121004435,
+      "grad_norm": 84.16732788085938,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 60.7165,
+      "step": 29
+    },
+    {
+      "epoch": 0.006911248056211484,
+      "grad_norm": 71.33744812011719,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 56.777,
+      "step": 30
+    },
+    {
+      "epoch": 0.0071416229914185335,
+      "grad_norm": 72.3608169555664,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 59.9207,
+      "step": 31
+    },
+    {
+      "epoch": 0.0073719979266255835,
+      "grad_norm": 66.34757232666016,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 52.6005,
+      "step": 32
+    },
+    {
+      "epoch": 0.007602372861832633,
+      "grad_norm": 71.25404357910156,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 57.5288,
+      "step": 33
+    },
+    {
+      "epoch": 0.007832747797039682,
+      "grad_norm": 68.51131439208984,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 53.9669,
+      "step": 34
+    },
+    {
+      "epoch": 0.008063122732246731,
+      "grad_norm": 65.51441955566406,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 55.8962,
+      "step": 35
+    },
+    {
+      "epoch": 0.008293497667453782,
+      "grad_norm": 60.33618927001953,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 50.4908,
+      "step": 36
+    },
+    {
+      "epoch": 0.008523872602660831,
+      "grad_norm": 77.44511413574219,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 55.3199,
+      "step": 37
+    },
+    {
+      "epoch": 0.00875424753786788,
+      "grad_norm": 54.78342056274414,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 53.1404,
+      "step": 38
+    },
+    {
+      "epoch": 0.00898462247307493,
+      "grad_norm": 83.0269775390625,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 52.3299,
+      "step": 39
+    },
+    {
+      "epoch": 0.009214997408281978,
+      "grad_norm": 87.23737335205078,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 52.0134,
+      "step": 40
+    },
+    {
+      "epoch": 0.009445372343489028,
+      "grad_norm": 75.3519515991211,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 53.1972,
+      "step": 41
+    },
+    {
+      "epoch": 0.009675747278696079,
+      "grad_norm": 61.294090270996094,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 48.7823,
+      "step": 42
+    },
+    {
+      "epoch": 0.009906122213903128,
+      "grad_norm": 63.34431076049805,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 53.6702,
+      "step": 43
+    },
+    {
+      "epoch": 0.010136497149110177,
+      "grad_norm": 44.3028678894043,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 55.0122,
+      "step": 44
+    },
+    {
+      "epoch": 0.010366872084317226,
+      "grad_norm": 49.571224212646484,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 55.7552,
+      "step": 45
+    },
+    {
+      "epoch": 0.010597247019524275,
+      "grad_norm": 43.006446838378906,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 55.4966,
+      "step": 46
+    },
+    {
+      "epoch": 0.010827621954731326,
+      "grad_norm": 47.070701599121094,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 55.856,
+      "step": 47
+    },
+    {
+      "epoch": 0.011057996889938375,
+      "grad_norm": 48.78907012939453,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 52.8863,
+      "step": 48
+    },
+    {
+      "epoch": 0.011288371825145424,
+      "grad_norm": 59.8986701965332,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 54.6934,
+      "step": 49
+    },
+    {
+      "epoch": 0.011518746760352474,
+      "grad_norm": 86.94013214111328,
+      "learning_rate": 0.0,
+      "loss": 55.1274,
+      "step": 50
+    },
+    {
+      "epoch": 0.011518746760352474,
+      "eval_loss": 3.3264994621276855,
+      "eval_runtime": 1140.7657,
+      "eval_samples_per_second": 25.635,
+      "eval_steps_per_second": 3.205,
+      "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": 2.631214808694784e+17,
+  "total_flos": 5.262429617389568e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null