Hubert commit
Browse files- config.json +33 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +11 -0
- trainer_state.json +416 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sdadas/polish-gpt2-small",
|
| 3 |
+
"activation_function": "gelu_fast",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_embd": 768,
|
| 15 |
+
"n_head": 12,
|
| 16 |
+
"n_inner": 3072,
|
| 17 |
+
"n_layer": 12,
|
| 18 |
+
"n_positions": 2048,
|
| 19 |
+
"reorder_and_upcast_attn": false,
|
| 20 |
+
"resid_pdrop": 0.1,
|
| 21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 22 |
+
"scale_attn_weights": true,
|
| 23 |
+
"summary_activation": null,
|
| 24 |
+
"summary_first_dropout": 0.1,
|
| 25 |
+
"summary_proj_to_labels": true,
|
| 26 |
+
"summary_type": "cls_index",
|
| 27 |
+
"summary_use_proj": true,
|
| 28 |
+
"tokenizer_class": "GPT2TokenizerFast",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.27.0.dev0",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 51200
|
| 33 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.27.0.dev0"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f710ee421e9692d4657fc57c31c9abe2564100cc08e791e2273ea79e6c255966
|
| 3 |
+
size 1007690437
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44172502dc260ed58b7c5bdca63f4d1e2b4ae3329d205a511cf410db81808542
|
| 3 |
+
size 554189373
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:840e41187a9efdb8fb051986823a8130f419ca1fc19d194e0ed3575236246701
|
| 3 |
+
size 14575
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45e4df22341441d04078822b3eea276fc839579c2847943df3b1cd2dec611f9d
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33c0f46ebd623bad71c10c220553997e329d77909df57f614e50893b392a627b
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
+
"special_tokens_map_file": "original/polish-gpt2-small/special_tokens_map.json",
|
| 9 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 10 |
+
"unk_token": "<unk>"
|
| 11 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,416 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"global_step": 10000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.5,
|
| 12 |
+
"learning_rate": 0.0002954545454545454,
|
| 13 |
+
"loss": 0.71,
|
| 14 |
+
"step": 250
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"learning_rate": 0.00028787878787878786,
|
| 19 |
+
"loss": 0.5325,
|
| 20 |
+
"step": 500
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.0,
|
| 24 |
+
"eval_loss": 0.5033329725265503,
|
| 25 |
+
"eval_runtime": 9.0003,
|
| 26 |
+
"eval_samples_per_second": 888.861,
|
| 27 |
+
"eval_steps_per_second": 27.777,
|
| 28 |
+
"step": 500
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 1.5,
|
| 32 |
+
"learning_rate": 0.0002803030303030303,
|
| 33 |
+
"loss": 0.4322,
|
| 34 |
+
"step": 750
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 2.0,
|
| 38 |
+
"learning_rate": 0.0002727272727272727,
|
| 39 |
+
"loss": 0.441,
|
| 40 |
+
"step": 1000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 2.0,
|
| 44 |
+
"eval_loss": 0.4973089098930359,
|
| 45 |
+
"eval_runtime": 9.0771,
|
| 46 |
+
"eval_samples_per_second": 881.341,
|
| 47 |
+
"eval_steps_per_second": 27.542,
|
| 48 |
+
"step": 1000
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 2.5,
|
| 52 |
+
"learning_rate": 0.0002651515151515151,
|
| 53 |
+
"loss": 0.352,
|
| 54 |
+
"step": 1250
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.0,
|
| 58 |
+
"learning_rate": 0.00025757575757575756,
|
| 59 |
+
"loss": 0.372,
|
| 60 |
+
"step": 1500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 3.0,
|
| 64 |
+
"eval_loss": 0.5114700198173523,
|
| 65 |
+
"eval_runtime": 9.3118,
|
| 66 |
+
"eval_samples_per_second": 859.12,
|
| 67 |
+
"eval_steps_per_second": 26.848,
|
| 68 |
+
"step": 1500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 3.5,
|
| 72 |
+
"learning_rate": 0.00025,
|
| 73 |
+
"loss": 0.2921,
|
| 74 |
+
"step": 1750
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 4.0,
|
| 78 |
+
"learning_rate": 0.0002424242424242424,
|
| 79 |
+
"loss": 0.3107,
|
| 80 |
+
"step": 2000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 4.0,
|
| 84 |
+
"eval_loss": 0.5385135412216187,
|
| 85 |
+
"eval_runtime": 9.7573,
|
| 86 |
+
"eval_samples_per_second": 819.896,
|
| 87 |
+
"eval_steps_per_second": 25.622,
|
| 88 |
+
"step": 2000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 4.5,
|
| 92 |
+
"learning_rate": 0.00023484848484848483,
|
| 93 |
+
"loss": 0.2439,
|
| 94 |
+
"step": 2250
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 5.0,
|
| 98 |
+
"learning_rate": 0.00022727272727272725,
|
| 99 |
+
"loss": 0.2619,
|
| 100 |
+
"step": 2500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 5.0,
|
| 104 |
+
"eval_loss": 0.5607308149337769,
|
| 105 |
+
"eval_runtime": 9.0142,
|
| 106 |
+
"eval_samples_per_second": 887.492,
|
| 107 |
+
"eval_steps_per_second": 27.734,
|
| 108 |
+
"step": 2500
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 5.5,
|
| 112 |
+
"learning_rate": 0.00021969696969696969,
|
| 113 |
+
"loss": 0.2105,
|
| 114 |
+
"step": 2750
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 6.0,
|
| 118 |
+
"learning_rate": 0.0002121212121212121,
|
| 119 |
+
"loss": 0.2257,
|
| 120 |
+
"step": 3000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 6.0,
|
| 124 |
+
"eval_loss": 0.5820582509040833,
|
| 125 |
+
"eval_runtime": 22.0785,
|
| 126 |
+
"eval_samples_per_second": 362.343,
|
| 127 |
+
"eval_steps_per_second": 11.323,
|
| 128 |
+
"step": 3000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 6.5,
|
| 132 |
+
"learning_rate": 0.0002045454545454545,
|
| 133 |
+
"loss": 0.1812,
|
| 134 |
+
"step": 3250
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 7.0,
|
| 138 |
+
"learning_rate": 0.00019696969696969695,
|
| 139 |
+
"loss": 0.1947,
|
| 140 |
+
"step": 3500
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 7.0,
|
| 144 |
+
"eval_loss": 0.6063645482063293,
|
| 145 |
+
"eval_runtime": 22.1706,
|
| 146 |
+
"eval_samples_per_second": 360.838,
|
| 147 |
+
"eval_steps_per_second": 11.276,
|
| 148 |
+
"step": 3500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 7.5,
|
| 152 |
+
"learning_rate": 0.00018939393939393937,
|
| 153 |
+
"loss": 0.1597,
|
| 154 |
+
"step": 3750
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 8.0,
|
| 158 |
+
"learning_rate": 0.0001818181818181818,
|
| 159 |
+
"loss": 0.1715,
|
| 160 |
+
"step": 4000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 8.0,
|
| 164 |
+
"eval_loss": 0.6192964911460876,
|
| 165 |
+
"eval_runtime": 22.493,
|
| 166 |
+
"eval_samples_per_second": 355.666,
|
| 167 |
+
"eval_steps_per_second": 11.115,
|
| 168 |
+
"step": 4000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 8.5,
|
| 172 |
+
"learning_rate": 0.00017424242424242422,
|
| 173 |
+
"loss": 0.1439,
|
| 174 |
+
"step": 4250
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 9.0,
|
| 178 |
+
"learning_rate": 0.00016666666666666666,
|
| 179 |
+
"loss": 0.1535,
|
| 180 |
+
"step": 4500
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 9.0,
|
| 184 |
+
"eval_loss": 0.6339118480682373,
|
| 185 |
+
"eval_runtime": 17.7948,
|
| 186 |
+
"eval_samples_per_second": 449.57,
|
| 187 |
+
"eval_steps_per_second": 14.049,
|
| 188 |
+
"step": 4500
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 9.5,
|
| 192 |
+
"learning_rate": 0.00015909090909090907,
|
| 193 |
+
"loss": 0.1322,
|
| 194 |
+
"step": 4750
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 10.0,
|
| 198 |
+
"learning_rate": 0.00015151515151515152,
|
| 199 |
+
"loss": 0.1403,
|
| 200 |
+
"step": 5000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 10.0,
|
| 204 |
+
"eval_loss": 0.648122251033783,
|
| 205 |
+
"eval_runtime": 22.0949,
|
| 206 |
+
"eval_samples_per_second": 362.074,
|
| 207 |
+
"eval_steps_per_second": 11.315,
|
| 208 |
+
"step": 5000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 10.5,
|
| 212 |
+
"learning_rate": 0.00014393939393939393,
|
| 213 |
+
"loss": 0.1229,
|
| 214 |
+
"step": 5250
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 11.0,
|
| 218 |
+
"learning_rate": 0.00013636363636363634,
|
| 219 |
+
"loss": 0.1297,
|
| 220 |
+
"step": 5500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 11.0,
|
| 224 |
+
"eval_loss": 0.6578399538993835,
|
| 225 |
+
"eval_runtime": 22.4161,
|
| 226 |
+
"eval_samples_per_second": 356.887,
|
| 227 |
+
"eval_steps_per_second": 11.153,
|
| 228 |
+
"step": 5500
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 11.5,
|
| 232 |
+
"learning_rate": 0.00012878787878787878,
|
| 233 |
+
"loss": 0.1158,
|
| 234 |
+
"step": 5750
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 12.0,
|
| 238 |
+
"learning_rate": 0.0001212121212121212,
|
| 239 |
+
"loss": 0.1217,
|
| 240 |
+
"step": 6000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 12.0,
|
| 244 |
+
"eval_loss": 0.6666226983070374,
|
| 245 |
+
"eval_runtime": 17.8264,
|
| 246 |
+
"eval_samples_per_second": 448.773,
|
| 247 |
+
"eval_steps_per_second": 14.024,
|
| 248 |
+
"step": 6000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 12.5,
|
| 252 |
+
"learning_rate": 0.00011363636363636362,
|
| 253 |
+
"loss": 0.1106,
|
| 254 |
+
"step": 6250
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 13.0,
|
| 258 |
+
"learning_rate": 0.00010606060606060605,
|
| 259 |
+
"loss": 0.1152,
|
| 260 |
+
"step": 6500
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 13.0,
|
| 264 |
+
"eval_loss": 0.6757141351699829,
|
| 265 |
+
"eval_runtime": 15.3201,
|
| 266 |
+
"eval_samples_per_second": 522.191,
|
| 267 |
+
"eval_steps_per_second": 16.318,
|
| 268 |
+
"step": 6500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 13.5,
|
| 272 |
+
"learning_rate": 9.848484848484848e-05,
|
| 273 |
+
"loss": 0.1061,
|
| 274 |
+
"step": 6750
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 14.0,
|
| 278 |
+
"learning_rate": 9.09090909090909e-05,
|
| 279 |
+
"loss": 0.1101,
|
| 280 |
+
"step": 7000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 14.0,
|
| 284 |
+
"eval_loss": 0.687734842300415,
|
| 285 |
+
"eval_runtime": 21.8339,
|
| 286 |
+
"eval_samples_per_second": 366.402,
|
| 287 |
+
"eval_steps_per_second": 11.45,
|
| 288 |
+
"step": 7000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 14.5,
|
| 292 |
+
"learning_rate": 8.333333333333333e-05,
|
| 293 |
+
"loss": 0.1024,
|
| 294 |
+
"step": 7250
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 15.0,
|
| 298 |
+
"learning_rate": 7.575757575757576e-05,
|
| 299 |
+
"loss": 0.1059,
|
| 300 |
+
"step": 7500
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 15.0,
|
| 304 |
+
"eval_loss": 0.6898844242095947,
|
| 305 |
+
"eval_runtime": 22.4671,
|
| 306 |
+
"eval_samples_per_second": 356.076,
|
| 307 |
+
"eval_steps_per_second": 11.127,
|
| 308 |
+
"step": 7500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 15.5,
|
| 312 |
+
"learning_rate": 6.818181818181817e-05,
|
| 313 |
+
"loss": 0.0991,
|
| 314 |
+
"step": 7750
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 16.0,
|
| 318 |
+
"learning_rate": 6.06060606060606e-05,
|
| 319 |
+
"loss": 0.1022,
|
| 320 |
+
"step": 8000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 16.0,
|
| 324 |
+
"eval_loss": 0.6962941884994507,
|
| 325 |
+
"eval_runtime": 17.8764,
|
| 326 |
+
"eval_samples_per_second": 447.518,
|
| 327 |
+
"eval_steps_per_second": 13.985,
|
| 328 |
+
"step": 8000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 16.5,
|
| 332 |
+
"learning_rate": 5.3030303030303025e-05,
|
| 333 |
+
"loss": 0.0963,
|
| 334 |
+
"step": 8250
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 17.0,
|
| 338 |
+
"learning_rate": 4.545454545454545e-05,
|
| 339 |
+
"loss": 0.0991,
|
| 340 |
+
"step": 8500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 17.0,
|
| 344 |
+
"eval_loss": 0.702376127243042,
|
| 345 |
+
"eval_runtime": 21.7707,
|
| 346 |
+
"eval_samples_per_second": 367.466,
|
| 347 |
+
"eval_steps_per_second": 11.483,
|
| 348 |
+
"step": 8500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 17.5,
|
| 352 |
+
"learning_rate": 3.790909090909091e-05,
|
| 353 |
+
"loss": 0.0939,
|
| 354 |
+
"step": 8750
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 18.0,
|
| 358 |
+
"learning_rate": 3.033333333333333e-05,
|
| 359 |
+
"loss": 0.0961,
|
| 360 |
+
"step": 9000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 18.0,
|
| 364 |
+
"eval_loss": 0.7053780555725098,
|
| 365 |
+
"eval_runtime": 22.1712,
|
| 366 |
+
"eval_samples_per_second": 360.829,
|
| 367 |
+
"eval_steps_per_second": 11.276,
|
| 368 |
+
"step": 9000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 18.5,
|
| 372 |
+
"learning_rate": 2.2757575757575757e-05,
|
| 373 |
+
"loss": 0.0914,
|
| 374 |
+
"step": 9250
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 19.0,
|
| 378 |
+
"learning_rate": 1.518181818181818e-05,
|
| 379 |
+
"loss": 0.0933,
|
| 380 |
+
"step": 9500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 19.0,
|
| 384 |
+
"eval_loss": 0.7104560732841492,
|
| 385 |
+
"eval_runtime": 22.4548,
|
| 386 |
+
"eval_samples_per_second": 356.271,
|
| 387 |
+
"eval_steps_per_second": 11.133,
|
| 388 |
+
"step": 9500
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 19.5,
|
| 392 |
+
"learning_rate": 7.6060606060606056e-06,
|
| 393 |
+
"loss": 0.0893,
|
| 394 |
+
"step": 9750
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 20.0,
|
| 398 |
+
"learning_rate": 3.03030303030303e-08,
|
| 399 |
+
"loss": 0.0901,
|
| 400 |
+
"step": 10000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 20.0,
|
| 404 |
+
"eval_loss": 0.7170030474662781,
|
| 405 |
+
"eval_runtime": 17.8822,
|
| 406 |
+
"eval_samples_per_second": 447.372,
|
| 407 |
+
"eval_steps_per_second": 13.98,
|
| 408 |
+
"step": 10000
|
| 409 |
+
}
|
| 410 |
+
],
|
| 411 |
+
"max_steps": 10000,
|
| 412 |
+
"num_train_epochs": 20,
|
| 413 |
+
"total_flos": 4.180672512e+16,
|
| 414 |
+
"trial_name": null,
|
| 415 |
+
"trial_params": null
|
| 416 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12ad788ada8ce49fee2a1542b25bae9934d7b25006de0ce420d5f4ca7cd80ef5
|
| 3 |
+
size 3579
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|