Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4101f234614ce54ff92c80a506835c6078e2dc9075aedace9e3263b35447960d
+oid sha256:f73a59124353740ec934cb7d7ba41397f2b481bc5c4f0004adaa19dd670cd32e
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c7a6f519a255481a274373199e118b30afae8389301811131efe60541fdcdd0
+oid sha256:52779d72d44bc4bc1b120ac66c4ee431fdb69d1f210c82e7c0ad70d0f6c49d27
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dda3af2248874a0f9a00c1f98ebb77a74dc31995702b3fbbf23321caa729d381
+oid sha256:6cd5ed66edbd4215b3d660a8d788ed4fc2a39d68027f402a3ac10db07d2e242a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b88819e9e1683e3210eb505db68222c1c582ceb0f16170f0aca4659a77e6cd
+oid sha256:f4bb9563b349cb547b9dccc8b6d6202b4476052b430e64451f67c2d69e5cad8f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a33ae8762b08ca3fa5d08b3e2225f7b3943d0d03a24ca0a0f6816ab2cb2f5ebd
+oid sha256:d1f3d8a4b809ef043fd6861112776dbec94303e24c4b26271f608f880596ec23
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02bebfe78e1d5363a5a92dd178d33b1c82a80be9ca22758446bcceb83dbdae60
+oid sha256:e82c4d420887c0121254fb566c085601bbf3d109498ee98e9588a2a258d91291
 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": 11.907405853271484,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.408450704225352,
+  "best_metric": 11.903162002563477,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.816901408450704,
   "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": 252.807,
       "eval_steps_per_second": 31.601,
       "step": 25
+    },
+    {
+      "epoch": 1.4647887323943662,
+      "grad_norm": 0.19581171870231628,
+      "learning_rate": 5e-05,
+      "loss": 11.9039,
+      "step": 26
+    },
+    {
+      "epoch": 1.5211267605633803,
+      "grad_norm": 0.17904254794120789,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.9073,
+      "step": 27
+    },
+    {
+      "epoch": 1.5774647887323945,
+      "grad_norm": 0.17740856111049652,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.9064,
+      "step": 28
+    },
+    {
+      "epoch": 1.6338028169014085,
+      "grad_norm": 0.18188264966011047,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.9041,
+      "step": 29
+    },
+    {
+      "epoch": 1.6901408450704225,
+      "grad_norm": 0.21682192385196686,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.9039,
+      "step": 30
+    },
+    {
+      "epoch": 1.7464788732394365,
+      "grad_norm": 0.20323139429092407,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.9058,
+      "step": 31
+    },
+    {
+      "epoch": 1.8028169014084507,
+      "grad_norm": 0.18855667114257812,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9021,
+      "step": 32
+    },
+    {
+      "epoch": 1.8591549295774648,
+      "grad_norm": 0.19645343720912933,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.907,
+      "step": 33
+    },
+    {
+      "epoch": 1.915492957746479,
+      "grad_norm": 0.20963948965072632,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.9042,
+      "step": 34
+    },
+    {
+      "epoch": 1.971830985915493,
+      "grad_norm": 0.22430875897407532,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 12.8947,
+      "step": 35
+    },
+    {
+      "epoch": 2.028169014084507,
+      "grad_norm": 0.23213434219360352,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 13.8829,
+      "step": 36
+    },
+    {
+      "epoch": 2.084507042253521,
+      "grad_norm": 0.2037564367055893,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.901,
+      "step": 37
+    },
+    {
+      "epoch": 2.140845070422535,
+      "grad_norm": 0.2237176150083542,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.8982,
+      "step": 38
+    },
+    {
+      "epoch": 2.1971830985915495,
+      "grad_norm": 0.22813087701797485,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.8981,
+      "step": 39
+    },
+    {
+      "epoch": 2.2535211267605635,
+      "grad_norm": 0.23737770318984985,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.9021,
+      "step": 40
+    },
+    {
+      "epoch": 2.3098591549295775,
+      "grad_norm": 0.20191168785095215,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.8988,
+      "step": 41
+    },
+    {
+      "epoch": 2.3661971830985915,
+      "grad_norm": 0.2275736927986145,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.9019,
+      "step": 42
+    },
+    {
+      "epoch": 2.4225352112676055,
+      "grad_norm": 0.23269234597682953,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.9011,
+      "step": 43
+    },
+    {
+      "epoch": 2.4788732394366195,
+      "grad_norm": 0.27122339606285095,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.8984,
+      "step": 44
+    },
+    {
+      "epoch": 2.535211267605634,
+      "grad_norm": 0.20346561074256897,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.9046,
+      "step": 45
+    },
+    {
+      "epoch": 2.591549295774648,
+      "grad_norm": 0.21024282276630402,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.9059,
+      "step": 46
+    },
+    {
+      "epoch": 2.647887323943662,
+      "grad_norm": 0.24199335277080536,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.8993,
+      "step": 47
+    },
+    {
+      "epoch": 2.704225352112676,
+      "grad_norm": 0.22599415481090546,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.9033,
+      "step": 48
+    },
+    {
+      "epoch": 2.76056338028169,
+      "grad_norm": 0.2118520885705948,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.904,
+      "step": 49
+    },
+    {
+      "epoch": 2.816901408450704,
+      "grad_norm": 0.1982305496931076,
+      "learning_rate": 0.0,
+      "loss": 11.9034,
+      "step": 50
+    },
+    {
+      "epoch": 2.816901408450704,
+      "eval_loss": 11.903162002563477,
+      "eval_runtime": 0.4797,
+      "eval_samples_per_second": 250.132,
+      "eval_steps_per_second": 31.266,
+      "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": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null