Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a2ea0f26bf07a77a2092c418d51bf646b623c34e4593663a83408a837d774ae
+oid sha256:7d7f681200f13f5b2627ed1961146c158e23aa1df044bbe0b01ffb2db20744e5
 size 4525640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc5d5c56d0cbbe2949f390a2067a323e5ddc3944e1ba411d65ab5d9d1af04809
+oid sha256:f8049ab003d1414f33fa1aeaaaef1755e8718171df999b77eb2de300beded638
 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": 6.080567359924316,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06122761365375785,
+  "best_metric": 4.985250949859619,
+  "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": 474.806,
       "eval_steps_per_second": 59.372,
       "step": 25
+    },
+    {
+      "epoch": 0.06367671819990815,
+      "grad_norm": 7.234199523925781,
+      "learning_rate": 5e-05,
+      "loss": 5.7224,
+      "step": 26
+    },
+    {
+      "epoch": 0.06612582274605847,
+      "grad_norm": 7.271491050720215,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 5.6061,
+      "step": 27
+    },
+    {
+      "epoch": 0.06857492729220879,
+      "grad_norm": 6.81791353225708,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 5.5909,
+      "step": 28
+    },
+    {
+      "epoch": 0.0710240318383591,
+      "grad_norm": 7.6534423828125,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 5.388,
+      "step": 29
+    },
+    {
+      "epoch": 0.07347313638450942,
+      "grad_norm": 7.172658443450928,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 5.4519,
+      "step": 30
+    },
+    {
+      "epoch": 0.07592224093065973,
+      "grad_norm": 7.6117048263549805,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 5.3257,
+      "step": 31
+    },
+    {
+      "epoch": 0.07837134547681004,
+      "grad_norm": 7.242852687835693,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 5.291,
+      "step": 32
+    },
+    {
+      "epoch": 0.08082045002296036,
+      "grad_norm": 8.312119483947754,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 5.1802,
+      "step": 33
+    },
+    {
+      "epoch": 0.08326955456911067,
+      "grad_norm": 7.4992523193359375,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 5.2752,
+      "step": 34
+    },
+    {
+      "epoch": 0.08571865911526098,
+      "grad_norm": 6.869739532470703,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 5.1967,
+      "step": 35
+    },
+    {
+      "epoch": 0.0881677636614113,
+      "grad_norm": 6.3787736892700195,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 5.2088,
+      "step": 36
+    },
+    {
+      "epoch": 0.09061686820756161,
+      "grad_norm": 6.979067802429199,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 5.3134,
+      "step": 37
+    },
+    {
+      "epoch": 0.09306597275371192,
+      "grad_norm": 7.202182292938232,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 5.3527,
+      "step": 38
+    },
+    {
+      "epoch": 0.09551507729986224,
+      "grad_norm": 8.028775215148926,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 5.085,
+      "step": 39
+    },
+    {
+      "epoch": 0.09796418184601255,
+      "grad_norm": 7.695888042449951,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 4.9146,
+      "step": 40
+    },
+    {
+      "epoch": 0.10041328639216286,
+      "grad_norm": 7.480747699737549,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 4.853,
+      "step": 41
+    },
+    {
+      "epoch": 0.10286239093831318,
+      "grad_norm": 6.339000225067139,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 4.8266,
+      "step": 42
+    },
+    {
+      "epoch": 0.10531149548446349,
+      "grad_norm": 6.702110767364502,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 5.0874,
+      "step": 43
+    },
+    {
+      "epoch": 0.1077606000306138,
+      "grad_norm": 6.588842868804932,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.7769,
+      "step": 44
+    },
+    {
+      "epoch": 0.11020970457676411,
+      "grad_norm": 6.282130718231201,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 4.992,
+      "step": 45
+    },
+    {
+      "epoch": 0.11265880912291444,
+      "grad_norm": 6.139161586761475,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 4.8116,
+      "step": 46
+    },
+    {
+      "epoch": 0.11510791366906475,
+      "grad_norm": 6.040432453155518,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 4.8607,
+      "step": 47
+    },
+    {
+      "epoch": 0.11755701821521507,
+      "grad_norm": 6.295772552490234,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 5.179,
+      "step": 48
+    },
+    {
+      "epoch": 0.12000612276136538,
+      "grad_norm": 6.335700035095215,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 5.0151,
+      "step": 49
+    },
+    {
+      "epoch": 0.1224552273075157,
+      "grad_norm": 7.427189826965332,
+      "learning_rate": 0.0,
+      "loss": 5.1183,
+      "step": 50
+    },
+    {
+      "epoch": 0.1224552273075157,
+      "eval_loss": 4.985250949859619,
+      "eval_runtime": 5.7172,
+      "eval_samples_per_second": 481.181,
+      "eval_steps_per_second": 60.169,
+      "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