Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:484e282c0a66402bec08b9dae0bae91c005f57102b6fbfbae572dea0d94b384b
+oid sha256:eea15d7566bd7197515d9762a5473ea3bcbed3b7906921fc8d33ddc0bbc8ddef
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35cd03979f9708bca4cec5927202aadf807567edb21e1cbd6a410c4ada2bd2f6
+oid sha256:c6fb38f3b020934cf31a9c284167b7a525d4c2bc4cd8bb7db58411be7e2dff3d
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:331a4467a0fb8d7c7043e0d01950edf1318f2469a2c92d77e8707753895f8570
+oid sha256:4a3ee0df8ae3f3710d7e6012d842b99060b5081b956292b04cad73b7407f4814
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3f09bce229f84b3565d50040684fe7069ee1bad767a6ba250f069eec89e6cb4
+oid sha256:f0f0153e03aaa71f7e967a9c9a74134b48f243625453ae0b015d53122f1472e4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdddb5f821e6354ac5d8c737380f36aa544f5abf74f41df56884d4365fb6b9fa
+oid sha256:774a2575168544de029cc3ac19466ea94ad914274a9391f66988621012a3f63c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5748009a5fb799698a7a4139d7543db090c1c58c48263b84ae3e1d58ef0523dd
+oid sha256:37ef54575fa8a0808eafbf4ffc2ed0dd1f38175ac08409ace4c02664f79ec32b
 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": 0.6584460139274597,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.031039031582214636,
+  "best_metric": 0.6459671854972839,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06207806316442927,
   "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": 116.151,
       "eval_steps_per_second": 14.535,
       "step": 25
+    },
+    {
+      "epoch": 0.03228059284550322,
+      "grad_norm": 0.23359929025173187,
+      "learning_rate": 5e-05,
+      "loss": 0.7075,
+      "step": 26
+    },
+    {
+      "epoch": 0.03352215410879181,
+      "grad_norm": 0.15845683217048645,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.6823,
+      "step": 27
+    },
+    {
+      "epoch": 0.03476371537208039,
+      "grad_norm": 0.15037257969379425,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.6786,
+      "step": 28
+    },
+    {
+      "epoch": 0.036005276635368975,
+      "grad_norm": 0.15445923805236816,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7396,
+      "step": 29
+    },
+    {
+      "epoch": 0.03724683789865756,
+      "grad_norm": 0.15990139544010162,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7291,
+      "step": 30
+    },
+    {
+      "epoch": 0.03848839916194615,
+      "grad_norm": 0.139845073223114,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.6508,
+      "step": 31
+    },
+    {
+      "epoch": 0.03972996042523473,
+      "grad_norm": 0.14541897177696228,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.679,
+      "step": 32
+    },
+    {
+      "epoch": 0.04097152168852332,
+      "grad_norm": 0.1448265165090561,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6659,
+      "step": 33
+    },
+    {
+      "epoch": 0.042213082951811906,
+      "grad_norm": 0.14122691750526428,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6712,
+      "step": 34
+    },
+    {
+      "epoch": 0.04345464421510049,
+      "grad_norm": 0.157490074634552,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.6074,
+      "step": 35
+    },
+    {
+      "epoch": 0.044696205478389074,
+      "grad_norm": 0.16067852079868317,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.5234,
+      "step": 36
+    },
+    {
+      "epoch": 0.04593776674167766,
+      "grad_norm": 0.1827419102191925,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4291,
+      "step": 37
+    },
+    {
+      "epoch": 0.04717932800496624,
+      "grad_norm": 0.4607616364955902,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7925,
+      "step": 38
+    },
+    {
+      "epoch": 0.04842088926825483,
+      "grad_norm": 0.1292809545993805,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6489,
+      "step": 39
+    },
+    {
+      "epoch": 0.04966245053154342,
+      "grad_norm": 0.13788002729415894,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7076,
+      "step": 40
+    },
+    {
+      "epoch": 0.050904011794832,
+      "grad_norm": 0.13166581094264984,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7163,
+      "step": 41
+    },
+    {
+      "epoch": 0.052145573058120585,
+      "grad_norm": 0.13151279091835022,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7093,
+      "step": 42
+    },
+    {
+      "epoch": 0.05338713432140917,
+      "grad_norm": 0.13615787029266357,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6487,
+      "step": 43
+    },
+    {
+      "epoch": 0.05462869558469776,
+      "grad_norm": 0.14063283801078796,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6809,
+      "step": 44
+    },
+    {
+      "epoch": 0.05587025684798634,
+      "grad_norm": 0.13367421925067902,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6908,
+      "step": 45
+    },
+    {
+      "epoch": 0.05711181811127493,
+      "grad_norm": 0.138374924659729,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6654,
+      "step": 46
+    },
+    {
+      "epoch": 0.058353379374563516,
+      "grad_norm": 0.15195026993751526,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.6068,
+      "step": 47
+    },
+    {
+      "epoch": 0.0595949406378521,
+      "grad_norm": 0.15703357756137848,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5665,
+      "step": 48
+    },
+    {
+      "epoch": 0.060836501901140684,
+      "grad_norm": 0.16355907917022705,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4578,
+      "step": 49
+    },
+    {
+      "epoch": 0.06207806316442927,
+      "grad_norm": 0.2248668223619461,
+      "learning_rate": 0.0,
+      "loss": 0.3556,
+      "step": 50
+    },
+    {
+      "epoch": 0.06207806316442927,
+      "eval_loss": 0.6459671854972839,
+      "eval_runtime": 46.181,
+      "eval_samples_per_second": 117.494,
+      "eval_steps_per_second": 14.703,
+      "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": 4.216566050298266e+16,
+  "total_flos": 8.42792324479058e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null