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:a8dfe9ca0d63932998dafae2a9e30f1b782a0f9358fa334b671e4a801597e7f5
+oid sha256:f98ef951633c01399703ab6414e950aee9bb7ee3b79eb7a0862e6231e8e14c75
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:496a2af3381da281f705a52bf7e1e25bcab9a9b35eb5547906fca64f3f0c77c4
+oid sha256:3ad8b009629801c602d717905d50c9d18af0bfe610d3f6b1fffa105bf7e4a8f3
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52f173470e8ba136a19bd8bd44677e1a71ba04e70d18d56cf7ed62d50a3c4e13
+oid sha256:398d202d570348cb3612bda2bd902e6cf5677d1e4c30b987f82ffe1db108cdb9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4390b71d7af64dde19645aad65c80eac1055eb78e8f66bd359bbdafb2b859881
+oid sha256:29dd67dc8ca7b699874389fb88dcedea61d68b6350d38ab9d6f7d05af33938d8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:508ca0d4e54b0df7770e3d0595cf3897910348491e3ea1788e30f775dc81bc7f
+oid sha256:48a59ac1c9cc4b5b125b431bd46a56746308461e0566b60b14a91b33d539de6c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7381d74bbea5eaa1a71bf292d334218d7ccba17d90eb4ff9f68fcb6277efbeee
+oid sha256:adfac5e3716d1c6ab4ad4605e7e3344aa08b4c780d49849cba1ef00c1863042d
 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": 1.1055667400360107,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6451612903225806,
+  "best_metric": 1.0577250719070435,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.2903225806451613,
   "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": 87.462,
       "eval_steps_per_second": 11.016,
       "step": 25
+    },
+    {
+      "epoch": 0.6709677419354839,
+      "grad_norm": 0.595125138759613,
+      "learning_rate": 5e-05,
+      "loss": 0.9649,
+      "step": 26
+    },
+    {
+      "epoch": 0.6967741935483871,
+      "grad_norm": 0.8294361233711243,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.0171,
+      "step": 27
+    },
+    {
+      "epoch": 0.7225806451612903,
+      "grad_norm": 0.9938029050827026,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.8827,
+      "step": 28
+    },
+    {
+      "epoch": 0.7483870967741936,
+      "grad_norm": 0.5188781023025513,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.4422,
+      "step": 29
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": 0.4888777732849121,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.4637,
+      "step": 30
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5658689141273499,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.4176,
+      "step": 31
+    },
+    {
+      "epoch": 0.8258064516129032,
+      "grad_norm": 0.5756728053092957,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1852,
+      "step": 32
+    },
+    {
+      "epoch": 0.8516129032258064,
+      "grad_norm": 0.6184505820274353,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.0945,
+      "step": 33
+    },
+    {
+      "epoch": 0.8774193548387097,
+      "grad_norm": 0.592873215675354,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9161,
+      "step": 34
+    },
+    {
+      "epoch": 0.9032258064516129,
+      "grad_norm": 0.5111616253852844,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.0042,
+      "step": 35
+    },
+    {
+      "epoch": 0.9290322580645162,
+      "grad_norm": 0.47419649362564087,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.0056,
+      "step": 36
+    },
+    {
+      "epoch": 0.9548387096774194,
+      "grad_norm": 0.5003200173377991,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8988,
+      "step": 37
+    },
+    {
+      "epoch": 0.9806451612903225,
+      "grad_norm": 0.9362741112709045,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7959,
+      "step": 38
+    },
+    {
+      "epoch": 1.0064516129032257,
+      "grad_norm": 0.4995446801185608,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.4934,
+      "step": 39
+    },
+    {
+      "epoch": 1.032258064516129,
+      "grad_norm": 0.4925078749656677,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.4401,
+      "step": 40
+    },
+    {
+      "epoch": 1.0580645161290323,
+      "grad_norm": 0.45888611674308777,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.2628,
+      "step": 41
+    },
+    {
+      "epoch": 1.0838709677419356,
+      "grad_norm": 0.512951135635376,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.0872,
+      "step": 42
+    },
+    {
+      "epoch": 1.1096774193548387,
+      "grad_norm": 0.47870081663131714,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0501,
+      "step": 43
+    },
+    {
+      "epoch": 1.135483870967742,
+      "grad_norm": 0.4896996021270752,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9109,
+      "step": 44
+    },
+    {
+      "epoch": 1.1612903225806452,
+      "grad_norm": 0.48330628871917725,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8797,
+      "step": 45
+    },
+    {
+      "epoch": 1.1870967741935483,
+      "grad_norm": 0.5584717392921448,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8834,
+      "step": 46
+    },
+    {
+      "epoch": 1.2129032258064516,
+      "grad_norm": 0.5270745158195496,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.9089,
+      "step": 47
+    },
+    {
+      "epoch": 1.238709677419355,
+      "grad_norm": 0.5363309979438782,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6341,
+      "step": 48
+    },
+    {
+      "epoch": 1.2645161290322582,
+      "grad_norm": 0.5114651918411255,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.8123,
+      "step": 49
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.49089324474334717,
+      "learning_rate": 0.0,
+      "loss": 1.4389,
+      "step": 50
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "eval_loss": 1.0577250719070435,
+      "eval_runtime": 2.9964,
+      "eval_samples_per_second": 87.439,
+      "eval_steps_per_second": 11.013,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null