End of training

README.md

@@ -1,4 +1,6 @@
 ---
+license: mit
+base_model: gpt2
 tags:
 - generated_from_trainer
 model-index:
@@ -11,14 +13,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # controlled-food-recipe-generation
 
-This model was trained from scratch on an unknown dataset.
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.6176
-- eval_runtime: 0.0198
-- eval_samples_per_second: 50.41
-- eval_steps_per_second: 50.41
-- epoch: 65.0
-- step: 65
+- eval_loss: 1.0261
+- eval_runtime: 1432.5553
+- eval_samples_per_second: 104.708
+- eval_steps_per_second: 1.636
+- epoch: 1.19
+- step: 50000
 
 ## Model description
 

config.json

@@ -1,5 +1,5 @@
 {
- "_name_or_path": "/kaggle/working/controlled-food-recipe-generation",
+ "_name_or_path": "gpt2",
  "activation_function": "gelu_new",
  "architectures": [
  "GPT2LMHeadModel"

logs/events.out.tfevents.1707056479.6b8ef76803b7.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a955400898c05287b5b58720427850d09aa1706c6a220d4c70d8cc3f13652102
+size 5081

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da4205de6c9b412522e8795d80c3b85811b3e3b76a381747df431aa887d43f3b
+oid sha256:167443881e7d10287201ffedb2a2f6354b36719d8c5ceb86c2538e5de6b97c7b
 size 497918592

trainer_state.json

@@ -1,930 +1,34 @@
 {
- "best_metric": 1.5992611646652222,
- "best_model_checkpoint": "controlled-food-recipe-generation/checkpoint-53",
- "epoch": 65.0,
- "eval_steps": 1,
- "global_step": 65,
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 1.18517113871243,
+ "eval_steps": 50000,
+ "global_step": 50000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
  {
- "epoch": 1.0,
- "learning_rate": 5e-05,
- "loss": 78.014,
- "step": 1
+ "epoch": 1.19,
+ "learning_rate": 4.940766331658292e-05,
+ "loss": 1.1651,
+ "step": 50000
  },
  {
- "epoch": 1.0,
- "eval_loss": 76.51811981201172,
- "eval_runtime": 0.0422,
- "eval_samples_per_second": 23.686,
- "eval_steps_per_second": 23.686,
- "step": 1
- },
- {
- "epoch": 2.0,
- "learning_rate": 5e-05,
- "loss": 78.2388,
- "step": 2
- },
- {
- "epoch": 2.0,
- "eval_loss": 76.51811981201172,
- "eval_runtime": 0.0201,
- "eval_samples_per_second": 49.811,
- "eval_steps_per_second": 49.811,
- "step": 2
- },
- {
- "epoch": 3.0,
- "learning_rate": 5e-05,
- "loss": 77.0195,
- "step": 3
- },
- {
- "epoch": 3.0,
- "eval_loss": 76.51811981201172,
- "eval_runtime": 0.0202,
- "eval_samples_per_second": 49.475,
- "eval_steps_per_second": 49.475,
- "step": 3
- },
- {
- "epoch": 4.0,
- "learning_rate": 5e-05,
- "loss": 77.6197,
- "step": 4
- },
- {
- "epoch": 4.0,
- "eval_loss": 76.51811981201172,
- "eval_runtime": 0.0199,
- "eval_samples_per_second": 50.171,
- "eval_steps_per_second": 50.171,
- "step": 4
- },
- {
- "epoch": 5.0,
- "learning_rate": 5e-05,
- "loss": 77.8364,
- "step": 5
- },
- {
- "epoch": 5.0,
- "eval_loss": 76.51811981201172,
- "eval_runtime": 0.02,
- "eval_samples_per_second": 50.05,
- "eval_steps_per_second": 50.05,
- "step": 5
- },
- {
- "epoch": 6.0,
- "learning_rate": 5e-05,
- "loss": 77.9326,
- "step": 6
- },
- {
- "epoch": 6.0,
- "eval_loss": 76.51811981201172,
- "eval_runtime": 0.02,
- "eval_samples_per_second": 49.998,
- "eval_steps_per_second": 49.998,
- "step": 6
- },
- {
- "epoch": 7.0,
- "learning_rate": 5e-05,
- "loss": 77.1428,
- "step": 7
- },
- {
- "epoch": 7.0,
- "eval_loss": 76.51811981201172,
- "eval_runtime": 0.0203,
- "eval_samples_per_second": 49.376,
- "eval_steps_per_second": 49.376,
- "step": 7
- },
- {
- "epoch": 8.0,
- "learning_rate": 5e-05,
- "loss": 77.9131,
- "step": 8
- },
- {
- "epoch": 8.0,
- "eval_loss": 76.51811981201172,
- "eval_runtime": 0.0197,
- "eval_samples_per_second": 50.657,
- "eval_steps_per_second": 50.657,
- "step": 8
- },
- {
- "epoch": 9.0,
- "learning_rate": 4.9500000000000004e-05,
- "loss": 77.8046,
- "step": 9
- },
- {
- "epoch": 9.0,
- "eval_loss": 46.12736129760742,
- "eval_runtime": 0.0203,
- "eval_samples_per_second": 49.335,
- "eval_steps_per_second": 49.335,
- "step": 9
- },
- {
- "epoch": 10.0,
- "learning_rate": 4.9e-05,
- "loss": 35.9262,
- "step": 10
- },
- {
- "epoch": 10.0,
- "eval_loss": 42.20186233520508,
- "eval_runtime": 0.0212,
- "eval_samples_per_second": 47.156,
- "eval_steps_per_second": 47.156,
- "step": 10
- },
- {
- "epoch": 11.0,
- "learning_rate": 4.85e-05,
- "loss": 24.7783,
- "step": 11
- },
- {
- "epoch": 11.0,
- "eval_loss": 21.848590850830078,
- "eval_runtime": 0.0209,
- "eval_samples_per_second": 47.862,
- "eval_steps_per_second": 47.862,
- "step": 11
- },
- {
- "epoch": 12.0,
- "learning_rate": 4.8e-05,
- "loss": 11.8436,
- "step": 12
- },
- {
- "epoch": 12.0,
- "eval_loss": 10.201495170593262,
- "eval_runtime": 0.0205,
- "eval_samples_per_second": 48.692,
- "eval_steps_per_second": 48.692,
- "step": 12
- },
- {
- "epoch": 13.0,
- "learning_rate": 4.75e-05,
- "loss": 8.908,
- "step": 13
- },
- {
- "epoch": 13.0,
- "eval_loss": 11.220573425292969,
- "eval_runtime": 0.0213,
- "eval_samples_per_second": 46.959,
- "eval_steps_per_second": 46.959,
- "step": 13
- },
- {
- "epoch": 14.0,
- "learning_rate": 4.7e-05,
- "loss": 7.022,
- "step": 14
- },
- {
- "epoch": 14.0,
- "eval_loss": 9.170014381408691,
- "eval_runtime": 0.0227,
- "eval_samples_per_second": 44.006,
- "eval_steps_per_second": 44.006,
- "step": 14
- },
- {
- "epoch": 15.0,
- "learning_rate": 4.6500000000000005e-05,
- "loss": 6.3525,
- "step": 15
- },
- {
- "epoch": 15.0,
- "eval_loss": 6.997350215911865,
- "eval_runtime": 0.0211,
- "eval_samples_per_second": 47.457,
- "eval_steps_per_second": 47.457,
- "step": 15
- },
- {
- "epoch": 16.0,
- "learning_rate": 4.600000000000001e-05,
- "loss": 5.6621,
- "step": 16
- },
- {
- "epoch": 16.0,
- "eval_loss": 4.715316295623779,
- "eval_runtime": 0.0208,
- "eval_samples_per_second": 48.084,
- "eval_steps_per_second": 48.084,
- "step": 16
- },
- {
- "epoch": 17.0,
- "learning_rate": 5e-05,
- "loss": 5.8038,
- "step": 17
- },
- {
- "epoch": 17.0,
- "eval_loss": 4.024607181549072,
- "eval_runtime": 0.0201,
- "eval_samples_per_second": 49.72,
- "eval_steps_per_second": 49.72,
- "step": 17
- },
- {
- "epoch": 18.0,
- "learning_rate": 5e-05,
- "loss": 5.6281,
- "step": 18
- },
- {
- "epoch": 18.0,
- "eval_loss": 4.024607181549072,
- "eval_runtime": 0.0191,
- "eval_samples_per_second": 52.343,
- "eval_steps_per_second": 52.343,
- "step": 18
- },
- {
- "epoch": 19.0,
- "learning_rate": 5e-05,
- "loss": 5.4614,
- "step": 19
- },
- {
- "epoch": 19.0,
- "eval_loss": 4.024607181549072,
- "eval_runtime": 0.0197,
- "eval_samples_per_second": 50.703,
- "eval_steps_per_second": 50.703,
- "step": 19
- },
- {
- "epoch": 20.0,
- "learning_rate": 5e-05,
- "loss": 5.5227,
- "step": 20
- },
- {
- "epoch": 20.0,
- "eval_loss": 4.024607181549072,
- "eval_runtime": 0.0208,
- "eval_samples_per_second": 48.085,
- "eval_steps_per_second": 48.085,
- "step": 20
- },
- {
- "epoch": 21.0,
- "learning_rate": 4.9500000000000004e-05,
- "loss": 5.2292,
- "step": 21
- },
- {
- "epoch": 21.0,
- "eval_loss": 3.1571905612945557,
- "eval_runtime": 0.02,
- "eval_samples_per_second": 50.062,
- "eval_steps_per_second": 50.062,
- "step": 21
- },
- {
- "epoch": 22.0,
- "learning_rate": 4.9e-05,
- "loss": 4.6673,
- "step": 22
- },
- {
- "epoch": 22.0,
- "eval_loss": 2.9552078247070312,
- "eval_runtime": 0.0218,
- "eval_samples_per_second": 45.876,
- "eval_steps_per_second": 45.876,
- "step": 22
- },
- {
- "epoch": 23.0,
- "learning_rate": 4.85e-05,
- "loss": 4.9696,
- "step": 23
- },
- {
- "epoch": 23.0,
- "eval_loss": 2.9095003604888916,
- "eval_runtime": 0.0216,
- "eval_samples_per_second": 46.366,
- "eval_steps_per_second": 46.366,
- "step": 23
- },
- {
- "epoch": 24.0,
- "learning_rate": 4.8e-05,
- "loss": 4.1183,
- "step": 24
- },
- {
- "epoch": 24.0,
- "eval_loss": 2.6673200130462646,
- "eval_runtime": 0.0208,
- "eval_samples_per_second": 48.003,
- "eval_steps_per_second": 48.003,
- "step": 24
- },
- {
- "epoch": 25.0,
- "learning_rate": 4.75e-05,
- "loss": 3.8033,
- "step": 25
- },
- {
- "epoch": 25.0,
- "eval_loss": 2.3663747310638428,
- "eval_runtime": 0.0208,
- "eval_samples_per_second": 47.966,
- "eval_steps_per_second": 47.966,
- "step": 25
- },
- {
- "epoch": 26.0,
- "learning_rate": 4.7e-05,
- "loss": 3.6167,
- "step": 26
- },
- {
- "epoch": 26.0,
- "eval_loss": 2.278635025024414,
- "eval_runtime": 0.0194,
- "eval_samples_per_second": 51.613,
- "eval_steps_per_second": 51.613,
- "step": 26
- },
- {
- "epoch": 27.0,
- "learning_rate": 4.6500000000000005e-05,
- "loss": 3.4501,
- "step": 27
- },
- {
- "epoch": 27.0,
- "eval_loss": 2.2132723331451416,
- "eval_runtime": 0.0197,
- "eval_samples_per_second": 50.812,
- "eval_steps_per_second": 50.812,
- "step": 27
- },
- {
- "epoch": 28.0,
- "learning_rate": 4.600000000000001e-05,
- "loss": 3.2932,
- "step": 28
- },
- {
- "epoch": 28.0,
- "eval_loss": 2.1897881031036377,
- "eval_runtime": 0.0192,
- "eval_samples_per_second": 52.029,
- "eval_steps_per_second": 52.029,
- "step": 28
- },
- {
- "epoch": 29.0,
- "learning_rate": 4.55e-05,
- "loss": 3.1358,
- "step": 29
- },
- {
- "epoch": 29.0,
- "eval_loss": 2.131443738937378,
- "eval_runtime": 0.0209,
- "eval_samples_per_second": 47.849,
- "eval_steps_per_second": 47.849,
- "step": 29
- },
- {
- "epoch": 30.0,
- "learning_rate": 4.5e-05,
- "loss": 3.1239,
- "step": 30
- },
- {
- "epoch": 30.0,
- "eval_loss": 2.0433859825134277,
- "eval_runtime": 0.0229,
- "eval_samples_per_second": 43.73,
- "eval_steps_per_second": 43.73,
- "step": 30
- },
- {
- "epoch": 31.0,
- "learning_rate": 4.4500000000000004e-05,
- "loss": 2.9609,
- "step": 31
- },
- {
- "epoch": 31.0,
- "eval_loss": 1.9398747682571411,
- "eval_runtime": 0.0205,
- "eval_samples_per_second": 48.772,
- "eval_steps_per_second": 48.772,
- "step": 31
- },
- {
- "epoch": 32.0,
- "learning_rate": 4.4000000000000006e-05,
- "loss": 2.8511,
- "step": 32
- },
- {
- "epoch": 32.0,
- "eval_loss": 1.8651390075683594,
- "eval_runtime": 0.0254,
- "eval_samples_per_second": 39.429,
- "eval_steps_per_second": 39.429,
- "step": 32
- },
- {
- "epoch": 33.0,
- "learning_rate": 4.35e-05,
- "loss": 2.8323,
- "step": 33
- },
- {
- "epoch": 33.0,
- "eval_loss": 1.8202353715896606,
- "eval_runtime": 0.0198,
- "eval_samples_per_second": 50.491,
- "eval_steps_per_second": 50.491,
- "step": 33
- },
- {
- "epoch": 34.0,
- "learning_rate": 4.3e-05,
- "loss": 2.7235,
- "step": 34
- },
- {
- "epoch": 34.0,
- "eval_loss": 1.7782583236694336,
- "eval_runtime": 0.0204,
- "eval_samples_per_second": 49.011,
- "eval_steps_per_second": 49.011,
- "step": 34
- },
- {
- "epoch": 35.0,
- "learning_rate": 4.25e-05,
- "loss": 2.534,
- "step": 35
- },
- {
- "epoch": 35.0,
- "eval_loss": 1.7466678619384766,
- "eval_runtime": 0.0204,
- "eval_samples_per_second": 48.995,
- "eval_steps_per_second": 48.995,
- "step": 35
- },
- {
- "epoch": 36.0,
- "learning_rate": 4.2e-05,
- "loss": 2.4176,
- "step": 36
- },
- {
- "epoch": 36.0,
- "eval_loss": 1.7186834812164307,
- "eval_runtime": 0.0197,
- "eval_samples_per_second": 50.712,
- "eval_steps_per_second": 50.712,
- "step": 36
- },
- {
- "epoch": 37.0,
- "learning_rate": 4.15e-05,
- "loss": 2.3308,
- "step": 37
- },
- {
- "epoch": 37.0,
- "eval_loss": 1.6936513185501099,
- "eval_runtime": 0.021,
- "eval_samples_per_second": 47.662,
- "eval_steps_per_second": 47.662,
- "step": 37
- },
- {
- "epoch": 38.0,
- "learning_rate": 4.1e-05,
- "loss": 2.2995,
- "step": 38
- },
- {
- "epoch": 38.0,
- "eval_loss": 1.666297197341919,
- "eval_runtime": 0.0199,
- "eval_samples_per_second": 50.261,
- "eval_steps_per_second": 50.261,
- "step": 38
- },
- {
- "epoch": 39.0,
- "learning_rate": 4.05e-05,
- "loss": 2.202,
- "step": 39
- },
- {
- "epoch": 39.0,
- "eval_loss": 1.6525242328643799,
- "eval_runtime": 0.0201,
- "eval_samples_per_second": 49.718,
- "eval_steps_per_second": 49.718,
- "step": 39
- },
- {
- "epoch": 40.0,
- "learning_rate": 4e-05,
- "loss": 2.1826,
- "step": 40
- },
- {
- "epoch": 40.0,
- "eval_loss": 1.6410127878189087,
- "eval_runtime": 0.0198,
- "eval_samples_per_second": 50.533,
- "eval_steps_per_second": 50.533,
- "step": 40
- },
- {
- "epoch": 41.0,
- "learning_rate": 3.9500000000000005e-05,
- "loss": 2.0815,
- "step": 41
- },
- {
- "epoch": 41.0,
- "eval_loss": 1.6258727312088013,
- "eval_runtime": 0.0204,
- "eval_samples_per_second": 49.053,
- "eval_steps_per_second": 49.053,
- "step": 41
- },
- {
- "epoch": 42.0,
- "learning_rate": 3.9000000000000006e-05,
- "loss": 2.0493,
- "step": 42
- },
- {
- "epoch": 42.0,
- "eval_loss": 1.6132334470748901,
- "eval_runtime": 0.0199,
- "eval_samples_per_second": 50.174,
- "eval_steps_per_second": 50.174,
- "step": 42
- },
- {
- "epoch": 43.0,
- "learning_rate": 3.85e-05,
- "loss": 1.9386,
- "step": 43
- },
- {
- "epoch": 43.0,
- "eval_loss": 1.6055489778518677,
- "eval_runtime": 0.0202,
- "eval_samples_per_second": 49.408,
- "eval_steps_per_second": 49.408,
- "step": 43
- },
- {
- "epoch": 44.0,
- "learning_rate": 3.8e-05,
- "loss": 1.8849,
- "step": 44
- },
- {
- "epoch": 44.0,
- "eval_loss": 1.6034255027770996,
- "eval_runtime": 0.0195,
- "eval_samples_per_second": 51.165,
- "eval_steps_per_second": 51.165,
- "step": 44
- },
- {
- "epoch": 45.0,
- "learning_rate": 3.7500000000000003e-05,
- "loss": 1.783,
- "step": 45
- },
- {
- "epoch": 45.0,
- "eval_loss": 1.607292890548706,
- "eval_runtime": 0.0198,
- "eval_samples_per_second": 50.498,
- "eval_steps_per_second": 50.498,
- "step": 45
- },
- {
- "epoch": 46.0,
- "learning_rate": 3.7e-05,
- "loss": 1.8884,
- "step": 46
- },
- {
- "epoch": 46.0,
- "eval_loss": 1.612091302871704,
- "eval_runtime": 0.0214,
- "eval_samples_per_second": 46.624,
- "eval_steps_per_second": 46.624,
- "step": 46
- },
- {
- "epoch": 47.0,
- "learning_rate": 3.65e-05,
- "loss": 1.7434,
- "step": 47
- },
- {
- "epoch": 47.0,
- "eval_loss": 1.6218953132629395,
- "eval_runtime": 0.0196,
- "eval_samples_per_second": 51.002,
- "eval_steps_per_second": 51.002,
- "step": 47
- },
- {
- "epoch": 48.0,
- "learning_rate": 3.6e-05,
- "loss": 1.6887,
- "step": 48
- },
- {
- "epoch": 48.0,
- "eval_loss": 1.624631404876709,
- "eval_runtime": 0.0227,
- "eval_samples_per_second": 44.127,
- "eval_steps_per_second": 44.127,
- "step": 48
- },
- {
- "epoch": 49.0,
- "learning_rate": 3.55e-05,
- "loss": 1.6335,
- "step": 49
- },
- {
- "epoch": 49.0,
- "eval_loss": 1.6270328760147095,
- "eval_runtime": 0.0199,
- "eval_samples_per_second": 50.273,
- "eval_steps_per_second": 50.273,
- "step": 49
- },
- {
- "epoch": 50.0,
- "learning_rate": 3.5e-05,
- "loss": 1.5708,
- "step": 50
- },
- {
- "epoch": 50.0,
- "eval_loss": 1.621827483177185,
- "eval_runtime": 0.02,
- "eval_samples_per_second": 50.013,
- "eval_steps_per_second": 50.013,
- "step": 50
- },
- {
- "epoch": 51.0,
- "learning_rate": 3.45e-05,
- "loss": 1.5745,
- "step": 51
- },
- {
- "epoch": 51.0,
- "eval_loss": 1.612929344177246,
- "eval_runtime": 0.0203,
- "eval_samples_per_second": 49.29,
- "eval_steps_per_second": 49.29,
- "step": 51
- },
- {
- "epoch": 52.0,
- "learning_rate": 3.4000000000000007e-05,
- "loss": 1.4928,
- "step": 52
- },
- {
- "epoch": 52.0,
- "eval_loss": 1.6025854349136353,
- "eval_runtime": 0.0204,
- "eval_samples_per_second": 49.026,
- "eval_steps_per_second": 49.026,
- "step": 52
- },
- {
- "epoch": 53.0,
- "learning_rate": 3.35e-05,
- "loss": 1.5607,
- "step": 53
- },
- {
- "epoch": 53.0,
- "eval_loss": 1.5992611646652222,
- "eval_runtime": 0.0198,
- "eval_samples_per_second": 50.457,
- "eval_steps_per_second": 50.457,
- "step": 53
- },
- {
- "epoch": 54.0,
- "learning_rate": 3.3e-05,
- "loss": 1.4556,
- "step": 54
- },
- {
- "epoch": 54.0,
- "eval_loss": 1.6017229557037354,
- "eval_runtime": 0.02,
- "eval_samples_per_second": 49.905,
- "eval_steps_per_second": 49.905,
- "step": 54
- },
- {
- "epoch": 55.0,
- "learning_rate": 3.2500000000000004e-05,
- "loss": 1.425,
- "step": 55
- },
- {
- "epoch": 55.0,
- "eval_loss": 1.6151561737060547,
- "eval_runtime": 0.0265,
- "eval_samples_per_second": 37.698,
- "eval_steps_per_second": 37.698,
- "step": 55
- },
- {
- "epoch": 56.0,
- "learning_rate": 3.2000000000000005e-05,
- "loss": 1.3748,
- "step": 56
- },
- {
- "epoch": 56.0,
- "eval_loss": 1.6267999410629272,
- "eval_runtime": 0.0201,
- "eval_samples_per_second": 49.657,
- "eval_steps_per_second": 49.657,
- "step": 56
- },
- {
- "epoch": 57.0,
- "learning_rate": 3.15e-05,
- "loss": 1.3616,
- "step": 57
- },
- {
- "epoch": 57.0,
- "eval_loss": 1.6329103708267212,
- "eval_runtime": 0.0198,
- "eval_samples_per_second": 50.392,
- "eval_steps_per_second": 50.392,
- "step": 57
- },
- {
- "epoch": 58.0,
- "learning_rate": 3.1e-05,
- "loss": 1.2908,
- "step": 58
- },
- {
- "epoch": 58.0,
- "eval_loss": 1.630703330039978,
- "eval_runtime": 0.0218,
- "eval_samples_per_second": 45.773,
- "eval_steps_per_second": 45.773,
- "step": 58
- },
- {
- "epoch": 59.0,
- "learning_rate": 3.05e-05,
- "loss": 1.228,
- "step": 59
- },
- {
- "epoch": 59.0,
- "eval_loss": 1.6292531490325928,
- "eval_runtime": 0.0205,
- "eval_samples_per_second": 48.745,
- "eval_steps_per_second": 48.745,
- "step": 59
- },
- {
- "epoch": 60.0,
- "learning_rate": 3e-05,
- "loss": 1.2228,
- "step": 60
- },
- {
- "epoch": 60.0,
- "eval_loss": 1.6247613430023193,
- "eval_runtime": 0.0205,
- "eval_samples_per_second": 48.733,
- "eval_steps_per_second": 48.733,
- "step": 60
- },
- {
- "epoch": 61.0,
- "learning_rate": 2.95e-05,
- "loss": 1.2232,
- "step": 61
- },
- {
- "epoch": 61.0,
- "eval_loss": 1.6152808666229248,
- "eval_runtime": 0.0297,
- "eval_samples_per_second": 33.674,
- "eval_steps_per_second": 33.674,
- "step": 61
- },
- {
- "epoch": 62.0,
- "learning_rate": 2.9e-05,
- "loss": 1.1724,
- "step": 62
- },
- {
- "epoch": 62.0,
- "eval_loss": 1.6111640930175781,
- "eval_runtime": 0.0208,
- "eval_samples_per_second": 48.023,
- "eval_steps_per_second": 48.023,
- "step": 62
- },
- {
- "epoch": 63.0,
- "learning_rate": 2.8499999999999998e-05,
- "loss": 1.1462,
- "step": 63
- },
- {
- "epoch": 63.0,
- "eval_loss": 1.6092727184295654,
- "eval_runtime": 0.0202,
- "eval_samples_per_second": 49.616,
- "eval_steps_per_second": 49.616,
- "step": 63
- },
- {
- "epoch": 64.0,
- "learning_rate": 2.8000000000000003e-05,
- "loss": 1.1083,
- "step": 64
- },
- {
- "epoch": 64.0,
- "eval_loss": 1.6092382669448853,
- "eval_runtime": 0.0205,
- "eval_samples_per_second": 48.823,
- "eval_steps_per_second": 48.823,
- "step": 64
- },
- {
- "epoch": 65.0,
- "learning_rate": 2.7500000000000004e-05,
- "loss": 1.0987,
- "step": 65
- },
- {
- "epoch": 65.0,
- "eval_loss": 1.6176224946975708,
- "eval_runtime": 0.0198,
- "eval_samples_per_second": 50.41,
- "eval_steps_per_second": 50.41,
- "step": 65
+ "epoch": 1.19,
+ "eval_loss": 1.026120662689209,
+ "eval_runtime": 1432.5553,
+ "eval_samples_per_second": 104.708,
+ "eval_steps_per_second": 1.636,
+ "step": 50000
  }
  ],
- "logging_steps": 1,
- "max_steps": 100,
+ "logging_steps": 50000,
+ "max_steps": 4218800,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
- "save_steps": 1,
- "total_flos": 38213959680000.0,
+ "save_steps": 50000,
+ "total_flos": 1.04515767631872e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e11847e74c240616571649a97da406725778726648f4a5d5ba652545c0ac20df
+oid sha256:eb10217ea6ee5a53faf925ba15fc624a98562d0ed446408452fcac3eb4a1b18e
 size 4728