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:aa54acbae13b542c0a44a2df9e8d9bc6910b4bfc0e1e72b4a1f5d31f2aa7535f
+oid sha256:4c6bda209bf4102e03291eab3ccba89bfc39754127f356b51764387d1efa117b
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69bfe5eb1b9ac7d5621367d5756e3b934b0c07a345c3b297c22199373b289413
+oid sha256:0666cb92f2a999c470a0896e5b3ccc9e5d0046d90b54ed9118eafb7752924531
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb407202bbcf1c0e8e88edfebb19feaed744e54b180e5617ade49956433eb099
+oid sha256:50b4fdce6aa2564c3f8e19f937f7eac065cfe1f987f8acab5b04d3aa4451f8ed
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a9422ed0ba7efd63f8bb85a58f63aab48d3cc7faa7458846d7e794325280d10
+oid sha256:3f7f5a62f7b9a97c4d6e85bb1b7e622074e8cfd37f021fac5afdb14e95dac214
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11ef8648f92511a0b6896f8f73ed395046d781b21635cc3b50fbdf69358efa45
+oid sha256:3cf5bae2da0d9737562b1ff22054a3eded69cb41f807cc7651e42fca078d5751
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5413b46c45f1bcddff958a622dbf892d22de4c0b0bee77779945545e2f6e409
+oid sha256:229a0e00c53b4eed544a113742cde616e3d4d1de2d3d56fea109bf237513be9d
 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": 1.097769021987915,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2059732234809475,
+  "best_metric": 0.9942613244056702,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.411946446961895,
   "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": 14.676,
       "eval_steps_per_second": 1.848,
       "step": 25
+    },
+    {
+      "epoch": 0.21421215242018538,
+      "grad_norm": 0.7587965130805969,
+      "learning_rate": 5e-05,
+      "loss": 1.5869,
+      "step": 26
+    },
+    {
+      "epoch": 0.22245108135942326,
+      "grad_norm": 1.1132606267929077,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.675,
+      "step": 27
+    },
+    {
+      "epoch": 0.23069001029866118,
+      "grad_norm": 0.47598445415496826,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.8052,
+      "step": 28
+    },
+    {
+      "epoch": 0.23892893923789907,
+      "grad_norm": 0.21603046357631683,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7202,
+      "step": 29
+    },
+    {
+      "epoch": 0.24716786817713698,
+      "grad_norm": 0.20677191019058228,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.9717,
+      "step": 30
+    },
+    {
+      "epoch": 0.2554067971163749,
+      "grad_norm": 0.2395070493221283,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.0057,
+      "step": 31
+    },
+    {
+      "epoch": 0.26364572605561276,
+      "grad_norm": 0.29304394125938416,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1178,
+      "step": 32
+    },
+    {
+      "epoch": 0.27188465499485065,
+      "grad_norm": 0.3763979375362396,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.2607,
+      "step": 33
+    },
+    {
+      "epoch": 0.2801235839340886,
+      "grad_norm": 0.559607207775116,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.4018,
+      "step": 34
+    },
+    {
+      "epoch": 0.2883625128733265,
+      "grad_norm": 0.6080499887466431,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.4868,
+      "step": 35
+    },
+    {
+      "epoch": 0.29660144181256437,
+      "grad_norm": 0.8854095339775085,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.7051,
+      "step": 36
+    },
+    {
+      "epoch": 0.30484037075180226,
+      "grad_norm": 1.4029868841171265,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.7953,
+      "step": 37
+    },
+    {
+      "epoch": 0.31307929969104015,
+      "grad_norm": 1.171069860458374,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0933,
+      "step": 38
+    },
+    {
+      "epoch": 0.3213182286302781,
+      "grad_norm": 0.9004032015800476,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4541,
+      "step": 39
+    },
+    {
+      "epoch": 0.329557157569516,
+      "grad_norm": 0.4076178967952728,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.503,
+      "step": 40
+    },
+    {
+      "epoch": 0.33779608650875387,
+      "grad_norm": 0.3803941011428833,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5107,
+      "step": 41
+    },
+    {
+      "epoch": 0.34603501544799176,
+      "grad_norm": 0.1711903065443039,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9551,
+      "step": 42
+    },
+    {
+      "epoch": 0.35427394438722964,
+      "grad_norm": 0.17743289470672607,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0498,
+      "step": 43
+    },
+    {
+      "epoch": 0.36251287332646753,
+      "grad_norm": 0.19017276167869568,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0787,
+      "step": 44
+    },
+    {
+      "epoch": 0.3707518022657055,
+      "grad_norm": 0.16853924095630646,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.0387,
+      "step": 45
+    },
+    {
+      "epoch": 0.37899073120494337,
+      "grad_norm": 0.21631433069705963,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.246,
+      "step": 46
+    },
+    {
+      "epoch": 0.38722966014418125,
+      "grad_norm": 0.29879626631736755,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.3496,
+      "step": 47
+    },
+    {
+      "epoch": 0.39546858908341914,
+      "grad_norm": 0.5076752305030823,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.6251,
+      "step": 48
+    },
+    {
+      "epoch": 0.40370751802265703,
+      "grad_norm": 0.8596004247665405,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.7919,
+      "step": 49
+    },
+    {
+      "epoch": 0.411946446961895,
+      "grad_norm": 3.706777572631836,
+      "learning_rate": 0.0,
+      "loss": 1.6232,
+      "step": 50
+    },
+    {
+      "epoch": 0.411946446961895,
+      "eval_loss": 0.9942613244056702,
+      "eval_runtime": 56.5648,
+      "eval_samples_per_second": 14.461,
+      "eval_steps_per_second": 1.821,
+      "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": 3.0358346152699494e+17,
+  "total_flos": 6.04008059433386e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null