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:f7a102a43b3e7e8d1bd576eea4f0a13aa5d6edc1f76ef6e0ec902bbf96299321
+oid sha256:750e00d49844e96c8027d23f8536c4df3216b61565c16fa02c4294ea7501dd93
 size 188794608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc1a636b0cb336341fa533a35538429deccb6f356418d7b847f0aae4937913aa
+oid sha256:46b1d0e505a9948c5ea934a03e50f64300ef136373946972ee379f74a1d43537
 size 377811346

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4054ec666b47604b2244d298212479ae83c1844f829d9f0d50ec0eee8a2043c
+oid sha256:30344dcb8091e3ac3981af190141ddbf4db8d670d2ca86ae4d279cf64b25fb9c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c7d13b95c0de9a890d7b432a21be08870fe34e0a6d2ea67df6c7b0239ddcf5c
+oid sha256:58e26151478fb42a24eb53b49714f8d705daeaaa4d904f6fedc3556d40c23a88
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:768097166735e28bdff41d1e82ef884b3a868c6d5f04950bb1953cb6638a1f9f
+oid sha256:10e661c3ae33b82b7b928c29b2c7fd0415e7f2d41fd2ad6512393061b3dd400d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16822411893622941bd0a3fdbdb17a1204d5e31c7f9bf2baf2a1b604b0657720
+oid sha256:8ebfb6f967674f0d6d3a4300199fed9137ebcd51812f45c34b6e8b8cdf29daef
 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": 0.15215370059013367,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.43010752688172044,
+  "best_metric": 0.13815657794475555,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.8602150537634409,
   "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": 21.954,
       "eval_steps_per_second": 2.744,
       "step": 25
+    },
+    {
+      "epoch": 0.44731182795698926,
+      "grad_norm": 2.2613651752471924,
+      "learning_rate": 5e-05,
+      "loss": 0.1028,
+      "step": 26
+    },
+    {
+      "epoch": 0.4645161290322581,
+      "grad_norm": 2.2889270782470703,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0973,
+      "step": 27
+    },
+    {
+      "epoch": 0.4817204301075269,
+      "grad_norm": 2.6887969970703125,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1141,
+      "step": 28
+    },
+    {
+      "epoch": 0.4989247311827957,
+      "grad_norm": 3.2376677989959717,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1339,
+      "step": 29
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 4.061950206756592,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.135,
+      "step": 30
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 3.4201228618621826,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.1264,
+      "step": 31
+    },
+    {
+      "epoch": 0.5505376344086022,
+      "grad_norm": 4.734947681427002,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.1528,
+      "step": 32
+    },
+    {
+      "epoch": 0.567741935483871,
+      "grad_norm": 4.872422695159912,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1697,
+      "step": 33
+    },
+    {
+      "epoch": 0.5849462365591398,
+      "grad_norm": 5.908591270446777,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1368,
+      "step": 34
+    },
+    {
+      "epoch": 0.6021505376344086,
+      "grad_norm": 4.6872239112854,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.1701,
+      "step": 35
+    },
+    {
+      "epoch": 0.6193548387096774,
+      "grad_norm": 6.91821813583374,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.213,
+      "step": 36
+    },
+    {
+      "epoch": 0.6365591397849463,
+      "grad_norm": 13.22769546508789,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.2258,
+      "step": 37
+    },
+    {
+      "epoch": 0.6537634408602151,
+      "grad_norm": 2.782428026199341,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0929,
+      "step": 38
+    },
+    {
+      "epoch": 0.6709677419354839,
+      "grad_norm": 2.596815586090088,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0904,
+      "step": 39
+    },
+    {
+      "epoch": 0.6881720430107527,
+      "grad_norm": 3.7397048473358154,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0981,
+      "step": 40
+    },
+    {
+      "epoch": 0.7053763440860215,
+      "grad_norm": 3.0771331787109375,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.102,
+      "step": 41
+    },
+    {
+      "epoch": 0.7225806451612903,
+      "grad_norm": 3.060393810272217,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1055,
+      "step": 42
+    },
+    {
+      "epoch": 0.7397849462365591,
+      "grad_norm": 3.0696990489959717,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1203,
+      "step": 43
+    },
+    {
+      "epoch": 0.7569892473118279,
+      "grad_norm": 3.046893835067749,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1459,
+      "step": 44
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": 3.663743257522583,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1479,
+      "step": 45
+    },
+    {
+      "epoch": 0.7913978494623656,
+      "grad_norm": 4.7457194328308105,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1345,
+      "step": 46
+    },
+    {
+      "epoch": 0.8086021505376344,
+      "grad_norm": 4.900630474090576,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1678,
+      "step": 47
+    },
+    {
+      "epoch": 0.8258064516129032,
+      "grad_norm": 8.411827087402344,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1862,
+      "step": 48
+    },
+    {
+      "epoch": 0.843010752688172,
+      "grad_norm": 6.233442783355713,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2265,
+      "step": 49
+    },
+    {
+      "epoch": 0.8602150537634409,
+      "grad_norm": 10.054956436157227,
+      "learning_rate": 0.0,
+      "loss": 0.2782,
+      "step": 50
+    },
+    {
+      "epoch": 0.8602150537634409,
+      "eval_loss": 0.13815657794475555,
+      "eval_runtime": 17.8416,
+      "eval_samples_per_second": 21.971,
+      "eval_steps_per_second": 2.746,
+      "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": 1.06003081199616e+17,
+  "total_flos": 2.12006162399232e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null