Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:567fe1d7570c11768089a96392f7a4d88a8af85db9241d5204fc041789647aa5
+oid sha256:5a187c5ddcff9d60015e2fb5d1bcb71391bcd98c58681f1947d08533a8d3256d
 size 4525640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca6501c207bbc6a8f163761e8c863544ee8586d6b339ecfdb9faf7870ab027cb
+oid sha256:6404b6158d41b15341ace998abc1a9ca36c7700dab7c1c82796db9c3b11fc257
 size 9067978

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f029c7efa77a937fb4437869c4595af13f53d35423b56867c81cb68ec31311f
+oid sha256:5b44968fd98555851572613b784164b4242cb8f8b9f6009241806af18231246f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd05427f26b1d6bc35ef38919e1a491f34bbf78cd67d6bed3a032c3dfb012989
+oid sha256:877e75222306085929ae1c82711509dfb50951844ecdae75782aecf080be8b5d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c223085c2d9011860169a2eab4e5aeab93233464e12e57da24559ae98dd91078
+oid sha256:515c03c83902321bc4da8d9cfc232599e147fe9d6687a3484311736eff6a69a2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7701d0f3dbc6c10b3de185adc1f82221076d8ca71e0fd0cb599288bc2756e03
+oid sha256:55ad54de765b92aadf8f3b49f9a2374a1f1cafa336a72807be57f93e34a0e15b
 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": 5.9959306716918945,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06122761365375785,
+  "best_metric": 4.964861869812012,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1224552273075157,
   "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": 942.031,
       "eval_steps_per_second": 117.797,
       "step": 25
+    },
+    {
+      "epoch": 0.06367671819990815,
+      "grad_norm": 7.211130142211914,
+      "learning_rate": 5e-05,
+      "loss": 5.6802,
+      "step": 26
+    },
+    {
+      "epoch": 0.06612582274605847,
+      "grad_norm": 7.553848743438721,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 5.5996,
+      "step": 27
+    },
+    {
+      "epoch": 0.06857492729220879,
+      "grad_norm": 7.340853691101074,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 5.5839,
+      "step": 28
+    },
+    {
+      "epoch": 0.0710240318383591,
+      "grad_norm": 8.36943244934082,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 5.3825,
+      "step": 29
+    },
+    {
+      "epoch": 0.07347313638450942,
+      "grad_norm": 7.856369495391846,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 5.4483,
+      "step": 30
+    },
+    {
+      "epoch": 0.07592224093065973,
+      "grad_norm": 8.200360298156738,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 5.32,
+      "step": 31
+    },
+    {
+      "epoch": 0.07837134547681004,
+      "grad_norm": 7.550553798675537,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 5.2876,
+      "step": 32
+    },
+    {
+      "epoch": 0.08082045002296036,
+      "grad_norm": 8.68742561340332,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 5.1647,
+      "step": 33
+    },
+    {
+      "epoch": 0.08326955456911067,
+      "grad_norm": 7.59812068939209,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 5.2607,
+      "step": 34
+    },
+    {
+      "epoch": 0.08571865911526098,
+      "grad_norm": 6.922670364379883,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 5.166,
+      "step": 35
+    },
+    {
+      "epoch": 0.0881677636614113,
+      "grad_norm": 6.234425067901611,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 5.1715,
+      "step": 36
+    },
+    {
+      "epoch": 0.09061686820756161,
+      "grad_norm": 7.038822650909424,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 5.2705,
+      "step": 37
+    },
+    {
+      "epoch": 0.09306597275371192,
+      "grad_norm": 7.074505805969238,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 5.3434,
+      "step": 38
+    },
+    {
+      "epoch": 0.09551507729986224,
+      "grad_norm": 8.038344383239746,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 5.0634,
+      "step": 39
+    },
+    {
+      "epoch": 0.09796418184601255,
+      "grad_norm": 7.753593444824219,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 4.8933,
+      "step": 40
+    },
+    {
+      "epoch": 0.10041328639216286,
+      "grad_norm": 7.461465358734131,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 4.8374,
+      "step": 41
+    },
+    {
+      "epoch": 0.10286239093831318,
+      "grad_norm": 6.135587215423584,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 4.8073,
+      "step": 42
+    },
+    {
+      "epoch": 0.10531149548446349,
+      "grad_norm": 6.440159797668457,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 5.0602,
+      "step": 43
+    },
+    {
+      "epoch": 0.1077606000306138,
+      "grad_norm": 6.288998603820801,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.7457,
+      "step": 44
+    },
+    {
+      "epoch": 0.11020970457676411,
+      "grad_norm": 6.0663957595825195,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 4.9725,
+      "step": 45
+    },
+    {
+      "epoch": 0.11265880912291444,
+      "grad_norm": 5.9057817459106445,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 4.7998,
+      "step": 46
+    },
+    {
+      "epoch": 0.11510791366906475,
+      "grad_norm": 5.905740261077881,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 4.836,
+      "step": 47
+    },
+    {
+      "epoch": 0.11755701821521507,
+      "grad_norm": 6.103787899017334,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 5.1476,
+      "step": 48
+    },
+    {
+      "epoch": 0.12000612276136538,
+      "grad_norm": 6.240080833435059,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 4.9798,
+      "step": 49
+    },
+    {
+      "epoch": 0.1224552273075157,
+      "grad_norm": 7.454318046569824,
+      "learning_rate": 0.0,
+      "loss": 5.0739,
+      "step": 50
+    },
+    {
+      "epoch": 0.1224552273075157,
+      "eval_loss": 4.964861869812012,
+      "eval_runtime": 2.9286,
+      "eval_samples_per_second": 939.347,
+      "eval_steps_per_second": 117.461,
+      "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": 1753141896806400.0,
+  "total_flos": 3506283793612800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null