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:e10f0478e61cfc14a1617096d7107f6839ebde19611cafa795e032f2063b362d
+oid sha256:df62fb31362aa6a0484230ba907e144fcd31ad7ab088ed845e734ec8347333e5
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fd8cbeacfecf504f4ffb998337b97f0a9c7189987bedd2531d715812cc727b3
+oid sha256:2464877886e8e93d252c0f32477c5833c47e768f9d0ee5e9273f35948908c6af
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aa32a0b3a041486153b8c3380c82f009b55a79501221d21d11c19e726f1f718
+oid sha256:1b5bc949910f844da9d6e50414f0861790e3bb5deef8f785335f366a915911a3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3aa711a38a24090fc40c12a9bb19fec0c7b90cb181304d3343636c74127ec0f
+oid sha256:9de9ec06bc87c55c17ad5670a042beb07fd3c58412089f6b566b4adb03d3244a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d331c68bb0f81d78d68a99251eea5e0dfa6f3a682bf960d73eb4e50687ac3b
+oid sha256:e2050a0872ad269fb75908b9310a90ce8dbc285177ec08db25cbd5b9c2921f71
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f19f8dddfee3e8a7b0cf1283a0d12bfa0e8c3f816bda78f692378194a98e332
+oid sha256:225b2689ed0b39d17dbc420eb5abb310cdc4a87fc1c6a36e9e6c5ec29dbae2b2
 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": 1.1196023225784302,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.31695721077654515,
+  "best_metric": 1.1063793897628784,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6339144215530903,
   "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": 39.196,
       "eval_steps_per_second": 4.936,
       "step": 25
+    },
+    {
+      "epoch": 0.329635499207607,
+      "grad_norm": 0.5885714888572693,
+      "learning_rate": 5e-05,
+      "loss": 0.9911,
+      "step": 26
+    },
+    {
+      "epoch": 0.34231378763866877,
+      "grad_norm": 0.5115616917610168,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9497,
+      "step": 27
+    },
+    {
+      "epoch": 0.3549920760697306,
+      "grad_norm": 0.46000874042510986,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.8997,
+      "step": 28
+    },
+    {
+      "epoch": 0.3676703645007924,
+      "grad_norm": 0.5111604332923889,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9888,
+      "step": 29
+    },
+    {
+      "epoch": 0.3803486529318542,
+      "grad_norm": 0.4380592107772827,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.0359,
+      "step": 30
+    },
+    {
+      "epoch": 0.393026941362916,
+      "grad_norm": 0.5161916613578796,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.1325,
+      "step": 31
+    },
+    {
+      "epoch": 0.40570522979397783,
+      "grad_norm": 0.4770544171333313,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.0698,
+      "step": 32
+    },
+    {
+      "epoch": 0.4183835182250396,
+      "grad_norm": 0.46398866176605225,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.163,
+      "step": 33
+    },
+    {
+      "epoch": 0.43106180665610144,
+      "grad_norm": 0.46868574619293213,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.1508,
+      "step": 34
+    },
+    {
+      "epoch": 0.4437400950871632,
+      "grad_norm": 0.46707800030708313,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.0802,
+      "step": 35
+    },
+    {
+      "epoch": 0.45641838351822506,
+      "grad_norm": 0.5554302334785461,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.3675,
+      "step": 36
+    },
+    {
+      "epoch": 0.46909667194928684,
+      "grad_norm": 0.6314070224761963,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.3372,
+      "step": 37
+    },
+    {
+      "epoch": 0.48177496038034867,
+      "grad_norm": 0.5946652293205261,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0386,
+      "step": 38
+    },
+    {
+      "epoch": 0.49445324881141045,
+      "grad_norm": 0.49788543581962585,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8803,
+      "step": 39
+    },
+    {
+      "epoch": 0.5071315372424723,
+      "grad_norm": 0.4571117162704468,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8767,
+      "step": 40
+    },
+    {
+      "epoch": 0.5198098256735341,
+      "grad_norm": 0.5018003582954407,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.9184,
+      "step": 41
+    },
+    {
+      "epoch": 0.5324881141045958,
+      "grad_norm": 0.43872758746147156,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9728,
+      "step": 42
+    },
+    {
+      "epoch": 0.5451664025356577,
+      "grad_norm": 0.4173322319984436,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.9579,
+      "step": 43
+    },
+    {
+      "epoch": 0.5578446909667195,
+      "grad_norm": 0.45682182908058167,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1821,
+      "step": 44
+    },
+    {
+      "epoch": 0.5705229793977813,
+      "grad_norm": 0.4728223383426666,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.1452,
+      "step": 45
+    },
+    {
+      "epoch": 0.5832012678288431,
+      "grad_norm": 0.5024501085281372,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.1376,
+      "step": 46
+    },
+    {
+      "epoch": 0.595879556259905,
+      "grad_norm": 0.5152183771133423,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.0496,
+      "step": 47
+    },
+    {
+      "epoch": 0.6085578446909667,
+      "grad_norm": 0.4861810505390167,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.1751,
+      "step": 48
+    },
+    {
+      "epoch": 0.6212361331220285,
+      "grad_norm": 0.568422794342041,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.2367,
+      "step": 49
+    },
+    {
+      "epoch": 0.6339144215530903,
+      "grad_norm": 0.6207615733146667,
+      "learning_rate": 0.0,
+      "loss": 1.4686,
+      "step": 50
+    },
+    {
+      "epoch": 0.6339144215530903,
+      "eval_loss": 1.1063793897628784,
+      "eval_runtime": 13.5724,
+      "eval_samples_per_second": 39.197,
+      "eval_steps_per_second": 4.936,
+      "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": 2.8137864274169037e+17,
+  "total_flos": 5.625815332741448e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null