Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55e9827ef8cc91c97db840cad2f239b6b71d35f5ea90d086d5067d2b3deb1ede
+oid sha256:856364850102f377f0062d0e9c84143feb1c022737174642049a9cc55dd62ad9
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29b33acf0a973a143175747a962ad9fe67cf71076dd0a78608f7dffc398bdd9f
+oid sha256:af2d3b4aec821562c8ac54c21cb4c4d16607ac4310ff2299b825a59e8e7c3771
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d6cdd65c8165fde81d3663c9f84b702e4335d40d869ca61535d14ef3a2ce201
+oid sha256:ebbb161ad9fee5d3318aed5f3b97a5ddadad1c3e50981ab882c5e6f917156fb4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca6e44dab8ec5d376552b2a0bc9c569003e58c353795e6646ddfb7f18ee86910
+oid sha256:b4fa4cf79a90071f090174dd057b7e7b83416ae2530d86a9dd53b9de88603d60
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94db75d9369a475d5cce29399e6c856e832925a56be67ed0e79f9db674f7da1b
+oid sha256:4ca3dfa99d10aab5d84fb8926336da17714b6566eb2b9c08b42a34806fb0a501
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27a6f38089934418ed0e6718ed9d3f4491dfaf35c458aac37318721f735393b0
+oid sha256:11f33d26a340a5279c04e5dfb5a843a9bff561aea658bed7ee23187f7dee4f8a
 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": 0.8179048299789429,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06532745386248572,
+  "best_metric": 0.7647556662559509,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13065490772497143,
   "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": 31.841,
       "eval_steps_per_second": 3.989,
       "step": 25
+    },
+    {
+      "epoch": 0.06794055201698514,
+      "grad_norm": 19.688880920410156,
+      "learning_rate": 5e-05,
+      "loss": 0.6132,
+      "step": 26
+    },
+    {
+      "epoch": 0.07055365017148457,
+      "grad_norm": 17.49786376953125,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.727,
+      "step": 27
+    },
+    {
+      "epoch": 0.073166748325984,
+      "grad_norm": 11.093067169189453,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7427,
+      "step": 28
+    },
+    {
+      "epoch": 0.07577984648048343,
+      "grad_norm": 9.140443801879883,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7637,
+      "step": 29
+    },
+    {
+      "epoch": 0.07839294463498285,
+      "grad_norm": 8.738513946533203,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7804,
+      "step": 30
+    },
+    {
+      "epoch": 0.08100604278948229,
+      "grad_norm": 9.069628715515137,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7579,
+      "step": 31
+    },
+    {
+      "epoch": 0.0836191409439817,
+      "grad_norm": 10.622302055358887,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7312,
+      "step": 32
+    },
+    {
+      "epoch": 0.08623223909848114,
+      "grad_norm": 14.509358406066895,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.7611,
+      "step": 33
+    },
+    {
+      "epoch": 0.08884533725298056,
+      "grad_norm": 21.554981231689453,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8172,
+      "step": 34
+    },
+    {
+      "epoch": 0.09145843540748,
+      "grad_norm": 30.103410720825195,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8458,
+      "step": 35
+    },
+    {
+      "epoch": 0.09407153356197942,
+      "grad_norm": 27.34261131286621,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.9454,
+      "step": 36
+    },
+    {
+      "epoch": 0.09668463171647886,
+      "grad_norm": 33.892723083496094,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9864,
+      "step": 37
+    },
+    {
+      "epoch": 0.09929772987097828,
+      "grad_norm": 35.015785217285156,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7745,
+      "step": 38
+    },
+    {
+      "epoch": 0.10191082802547771,
+      "grad_norm": 6.347834587097168,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6495,
+      "step": 39
+    },
+    {
+      "epoch": 0.10452392617997713,
+      "grad_norm": 6.344296455383301,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6931,
+      "step": 40
+    },
+    {
+      "epoch": 0.10713702433447657,
+      "grad_norm": 6.151936054229736,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7352,
+      "step": 41
+    },
+    {
+      "epoch": 0.10975012248897599,
+      "grad_norm": 6.7457661628723145,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7606,
+      "step": 42
+    },
+    {
+      "epoch": 0.11236322064347543,
+      "grad_norm": 7.498371124267578,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.7645,
+      "step": 43
+    },
+    {
+      "epoch": 0.11497631879797485,
+      "grad_norm": 8.821335792541504,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7449,
+      "step": 44
+    },
+    {
+      "epoch": 0.11758941695247428,
+      "grad_norm": 11.02287483215332,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.722,
+      "step": 45
+    },
+    {
+      "epoch": 0.1202025151069737,
+      "grad_norm": 15.275715827941895,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.693,
+      "step": 46
+    },
+    {
+      "epoch": 0.12281561326147314,
+      "grad_norm": 22.680950164794922,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7993,
+      "step": 47
+    },
+    {
+      "epoch": 0.12542871141597256,
+      "grad_norm": 31.55802345275879,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.8813,
+      "step": 48
+    },
+    {
+      "epoch": 0.12804180957047198,
+      "grad_norm": 43.83702850341797,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8113,
+      "step": 49
+    },
+    {
+      "epoch": 0.13065490772497143,
+      "grad_norm": 50.75833511352539,
+      "learning_rate": 0.0,
+      "loss": 1.0654,
+      "step": 50
+    },
+    {
+      "epoch": 0.13065490772497143,
+      "eval_loss": 0.7647556662559509,
+      "eval_runtime": 81.2616,
+      "eval_samples_per_second": 31.725,
+      "eval_steps_per_second": 3.975,
+      "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": 2.8626573248272794e+17,
+  "total_flos": 5.727082812528394e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null