Upload folder using huggingface_hub
Browse files- config.json +29 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
- trainer_state.json +410 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"hidden_act": "gelu",
|
| 7 |
+
"hidden_dropout_prob": 0.1,
|
| 8 |
+
"hidden_size": 1536,
|
| 9 |
+
"initializer_range": 0.02,
|
| 10 |
+
"intermediate_size": 6144,
|
| 11 |
+
"layer_norm_eps": 1e-07,
|
| 12 |
+
"legacy": true,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"max_relative_positions": -1,
|
| 15 |
+
"model_type": "deberta-v2",
|
| 16 |
+
"num_attention_heads": 24,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"pooler_dropout": 0,
|
| 20 |
+
"pooler_hidden_act": "gelu",
|
| 21 |
+
"pooler_hidden_size": 1536,
|
| 22 |
+
"pos_att_type": null,
|
| 23 |
+
"position_biased_input": true,
|
| 24 |
+
"relative_attention": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.47.0",
|
| 27 |
+
"type_vocab_size": 0,
|
| 28 |
+
"vocab_size": 7118
|
| 29 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d1fd6fd81e440daec3f421dcb58c5ebdd1f52b3b050b9ec7e007c3a789b411a
|
| 3 |
+
size 2776250200
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0bdc60ba278b2aaada0ceb3bbff71779426b7613cb9ea81b83b3c46f4172a97
|
| 3 |
+
size 5552738773
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dca1ebd4029c642140f53a557dd76f33d7b77ae315fc79ae62c06e26f04258f9
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb2b48a881416424368779eb036d46a0986387f3a29f511abab9c39d0a27edae
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": {
|
| 3 |
+
"content": "[EOS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_state.json
ADDED
|
@@ -0,0 +1,410 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 5.093143939971924,
|
| 3 |
+
"best_model_checkpoint": "2024-12-03-roberta-evacun/checkpoint-16456",
|
| 4 |
+
"epoch": 17.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 16456,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.5167958656330749,
|
| 13 |
+
"grad_norm": 5.255120277404785,
|
| 14 |
+
"learning_rate": 4.974146845915202e-05,
|
| 15 |
+
"loss": 5.2027,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.21748133776447606,
|
| 21 |
+
"eval_loss": 5.119329929351807,
|
| 22 |
+
"eval_runtime": 571.3565,
|
| 23 |
+
"eval_samples_per_second": 54.166,
|
| 24 |
+
"eval_steps_per_second": 3.387,
|
| 25 |
+
"step": 968
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.0330749354005169,
|
| 29 |
+
"grad_norm": 5.84419584274292,
|
| 30 |
+
"learning_rate": 4.948293691830403e-05,
|
| 31 |
+
"loss": 5.0886,
|
| 32 |
+
"step": 1000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.5498708010335918,
|
| 36 |
+
"grad_norm": 4.444571495056152,
|
| 37 |
+
"learning_rate": 4.922440537745605e-05,
|
| 38 |
+
"loss": 5.0616,
|
| 39 |
+
"step": 1500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.0,
|
| 43 |
+
"eval_accuracy": 0.2174891710390481,
|
| 44 |
+
"eval_loss": 5.119706153869629,
|
| 45 |
+
"eval_runtime": 570.6419,
|
| 46 |
+
"eval_samples_per_second": 54.234,
|
| 47 |
+
"eval_steps_per_second": 3.391,
|
| 48 |
+
"step": 1936
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 2.0661498708010337,
|
| 52 |
+
"grad_norm": 3.8420157432556152,
|
| 53 |
+
"learning_rate": 4.896587383660807e-05,
|
| 54 |
+
"loss": 5.0698,
|
| 55 |
+
"step": 2000
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 2.5829457364341084,
|
| 59 |
+
"grad_norm": 6.509148120880127,
|
| 60 |
+
"learning_rate": 4.870734229576008e-05,
|
| 61 |
+
"loss": 5.0702,
|
| 62 |
+
"step": 2500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 3.0,
|
| 66 |
+
"eval_accuracy": 0.21680529124469344,
|
| 67 |
+
"eval_loss": 5.109970569610596,
|
| 68 |
+
"eval_runtime": 570.6566,
|
| 69 |
+
"eval_samples_per_second": 54.232,
|
| 70 |
+
"eval_steps_per_second": 3.391,
|
| 71 |
+
"step": 2904
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 3.0992248062015504,
|
| 75 |
+
"grad_norm": 6.749443531036377,
|
| 76 |
+
"learning_rate": 4.84488107549121e-05,
|
| 77 |
+
"loss": 5.0508,
|
| 78 |
+
"step": 3000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.616020671834625,
|
| 82 |
+
"grad_norm": 3.7069902420043945,
|
| 83 |
+
"learning_rate": 4.819027921406412e-05,
|
| 84 |
+
"loss": 5.0692,
|
| 85 |
+
"step": 3500
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 4.0,
|
| 89 |
+
"eval_accuracy": 0.21822890079972776,
|
| 90 |
+
"eval_loss": 5.109030246734619,
|
| 91 |
+
"eval_runtime": 570.6551,
|
| 92 |
+
"eval_samples_per_second": 54.232,
|
| 93 |
+
"eval_steps_per_second": 3.391,
|
| 94 |
+
"step": 3872
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 4.1322997416020675,
|
| 98 |
+
"grad_norm": 4.267265319824219,
|
| 99 |
+
"learning_rate": 4.793174767321613e-05,
|
| 100 |
+
"loss": 5.0638,
|
| 101 |
+
"step": 4000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 4.649095607235142,
|
| 105 |
+
"grad_norm": 4.44468879699707,
|
| 106 |
+
"learning_rate": 4.7673216132368156e-05,
|
| 107 |
+
"loss": 5.0761,
|
| 108 |
+
"step": 4500
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 5.0,
|
| 112 |
+
"eval_accuracy": 0.21750397926781473,
|
| 113 |
+
"eval_loss": 5.103179931640625,
|
| 114 |
+
"eval_runtime": 570.6875,
|
| 115 |
+
"eval_samples_per_second": 54.229,
|
| 116 |
+
"eval_steps_per_second": 3.391,
|
| 117 |
+
"step": 4840
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 5.165374677002584,
|
| 121 |
+
"grad_norm": 4.793745994567871,
|
| 122 |
+
"learning_rate": 4.741468459152017e-05,
|
| 123 |
+
"loss": 5.0508,
|
| 124 |
+
"step": 5000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 5.682170542635659,
|
| 128 |
+
"grad_norm": 4.304242134094238,
|
| 129 |
+
"learning_rate": 4.7156153050672187e-05,
|
| 130 |
+
"loss": 5.053,
|
| 131 |
+
"step": 5500
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 6.0,
|
| 135 |
+
"eval_accuracy": 0.21806737555634184,
|
| 136 |
+
"eval_loss": 5.103706359863281,
|
| 137 |
+
"eval_runtime": 570.7022,
|
| 138 |
+
"eval_samples_per_second": 54.228,
|
| 139 |
+
"eval_steps_per_second": 3.391,
|
| 140 |
+
"step": 5808
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 6.198449612403101,
|
| 144 |
+
"grad_norm": 5.248096466064453,
|
| 145 |
+
"learning_rate": 4.6897621509824205e-05,
|
| 146 |
+
"loss": 5.0451,
|
| 147 |
+
"step": 6000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 6.715245478036175,
|
| 151 |
+
"grad_norm": 4.274606227874756,
|
| 152 |
+
"learning_rate": 4.663908996897622e-05,
|
| 153 |
+
"loss": 5.0631,
|
| 154 |
+
"step": 6500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 7.0,
|
| 158 |
+
"eval_accuracy": 0.21671510548702227,
|
| 159 |
+
"eval_loss": 5.111293315887451,
|
| 160 |
+
"eval_runtime": 570.6785,
|
| 161 |
+
"eval_samples_per_second": 54.23,
|
| 162 |
+
"eval_steps_per_second": 3.391,
|
| 163 |
+
"step": 6776
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 7.231524547803618,
|
| 167 |
+
"grad_norm": 4.097196102142334,
|
| 168 |
+
"learning_rate": 4.6380558428128236e-05,
|
| 169 |
+
"loss": 5.0515,
|
| 170 |
+
"step": 7000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 7.7483204134366925,
|
| 174 |
+
"grad_norm": 5.150557994842529,
|
| 175 |
+
"learning_rate": 4.6122026887280254e-05,
|
| 176 |
+
"loss": 5.0643,
|
| 177 |
+
"step": 7500
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 8.0,
|
| 181 |
+
"eval_accuracy": 0.21643664071910304,
|
| 182 |
+
"eval_loss": 5.104173183441162,
|
| 183 |
+
"eval_runtime": 570.7404,
|
| 184 |
+
"eval_samples_per_second": 54.224,
|
| 185 |
+
"eval_steps_per_second": 3.39,
|
| 186 |
+
"step": 7744
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 8.264599483204135,
|
| 190 |
+
"grad_norm": 4.464865684509277,
|
| 191 |
+
"learning_rate": 4.5863495346432266e-05,
|
| 192 |
+
"loss": 5.0575,
|
| 193 |
+
"step": 8000
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 8.78139534883721,
|
| 197 |
+
"grad_norm": 4.509471893310547,
|
| 198 |
+
"learning_rate": 4.5604963805584284e-05,
|
| 199 |
+
"loss": 5.0641,
|
| 200 |
+
"step": 8500
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 9.0,
|
| 204 |
+
"eval_accuracy": 0.2164407022306587,
|
| 205 |
+
"eval_loss": 5.1050801277160645,
|
| 206 |
+
"eval_runtime": 570.7609,
|
| 207 |
+
"eval_samples_per_second": 54.222,
|
| 208 |
+
"eval_steps_per_second": 3.39,
|
| 209 |
+
"step": 8712
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 9.29767441860465,
|
| 213 |
+
"grad_norm": 4.612584114074707,
|
| 214 |
+
"learning_rate": 4.5346432264736296e-05,
|
| 215 |
+
"loss": 5.0507,
|
| 216 |
+
"step": 9000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 9.814470284237727,
|
| 220 |
+
"grad_norm": 5.6399335861206055,
|
| 221 |
+
"learning_rate": 4.5087900723888315e-05,
|
| 222 |
+
"loss": 5.0477,
|
| 223 |
+
"step": 9500
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 10.0,
|
| 227 |
+
"eval_accuracy": 0.2173244230825529,
|
| 228 |
+
"eval_loss": 5.097902297973633,
|
| 229 |
+
"eval_runtime": 570.8859,
|
| 230 |
+
"eval_samples_per_second": 54.21,
|
| 231 |
+
"eval_steps_per_second": 3.389,
|
| 232 |
+
"step": 9680
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 10.330749354005167,
|
| 236 |
+
"grad_norm": 4.067675590515137,
|
| 237 |
+
"learning_rate": 4.4829369183040333e-05,
|
| 238 |
+
"loss": 5.0538,
|
| 239 |
+
"step": 10000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 10.847545219638242,
|
| 243 |
+
"grad_norm": 3.6515378952026367,
|
| 244 |
+
"learning_rate": 4.4570837642192345e-05,
|
| 245 |
+
"loss": 5.0516,
|
| 246 |
+
"step": 10500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 11.0,
|
| 250 |
+
"eval_accuracy": 0.21694436479870868,
|
| 251 |
+
"eval_loss": 5.105097770690918,
|
| 252 |
+
"eval_runtime": 570.8353,
|
| 253 |
+
"eval_samples_per_second": 54.215,
|
| 254 |
+
"eval_steps_per_second": 3.39,
|
| 255 |
+
"step": 10648
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 11.363824289405684,
|
| 259 |
+
"grad_norm": 3.8045644760131836,
|
| 260 |
+
"learning_rate": 4.4312306101344364e-05,
|
| 261 |
+
"loss": 5.0503,
|
| 262 |
+
"step": 11000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 11.88062015503876,
|
| 266 |
+
"grad_norm": 6.31251859664917,
|
| 267 |
+
"learning_rate": 4.405377456049638e-05,
|
| 268 |
+
"loss": 5.0535,
|
| 269 |
+
"step": 11500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 12.0,
|
| 273 |
+
"eval_accuracy": 0.21655864853378665,
|
| 274 |
+
"eval_loss": 5.102573394775391,
|
| 275 |
+
"eval_runtime": 570.862,
|
| 276 |
+
"eval_samples_per_second": 54.213,
|
| 277 |
+
"eval_steps_per_second": 3.39,
|
| 278 |
+
"step": 11616
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 12.396899224806202,
|
| 282 |
+
"grad_norm": 7.145920276641846,
|
| 283 |
+
"learning_rate": 4.3795243019648394e-05,
|
| 284 |
+
"loss": 5.0599,
|
| 285 |
+
"step": 12000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 12.913695090439276,
|
| 289 |
+
"grad_norm": 4.022646427154541,
|
| 290 |
+
"learning_rate": 4.353671147880042e-05,
|
| 291 |
+
"loss": 5.0491,
|
| 292 |
+
"step": 12500
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 13.0,
|
| 296 |
+
"eval_accuracy": 0.21710994508587633,
|
| 297 |
+
"eval_loss": 5.104992866516113,
|
| 298 |
+
"eval_runtime": 570.798,
|
| 299 |
+
"eval_samples_per_second": 54.219,
|
| 300 |
+
"eval_steps_per_second": 3.39,
|
| 301 |
+
"step": 12584
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 13.429974160206719,
|
| 305 |
+
"grad_norm": 3.64132022857666,
|
| 306 |
+
"learning_rate": 4.327817993795243e-05,
|
| 307 |
+
"loss": 5.0419,
|
| 308 |
+
"step": 13000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 13.946770025839793,
|
| 312 |
+
"grad_norm": 4.630414009094238,
|
| 313 |
+
"learning_rate": 4.301964839710445e-05,
|
| 314 |
+
"loss": 5.0547,
|
| 315 |
+
"step": 13500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 14.0,
|
| 319 |
+
"eval_accuracy": 0.21658861456412434,
|
| 320 |
+
"eval_loss": 5.10886287689209,
|
| 321 |
+
"eval_runtime": 570.8383,
|
| 322 |
+
"eval_samples_per_second": 54.215,
|
| 323 |
+
"eval_steps_per_second": 3.39,
|
| 324 |
+
"step": 13552
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 14.463049095607236,
|
| 328 |
+
"grad_norm": 4.112677097320557,
|
| 329 |
+
"learning_rate": 4.276111685625647e-05,
|
| 330 |
+
"loss": 5.0602,
|
| 331 |
+
"step": 14000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 14.97984496124031,
|
| 335 |
+
"grad_norm": 5.0369873046875,
|
| 336 |
+
"learning_rate": 4.250258531540848e-05,
|
| 337 |
+
"loss": 5.055,
|
| 338 |
+
"step": 14500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 15.0,
|
| 342 |
+
"eval_accuracy": 0.21731427174975562,
|
| 343 |
+
"eval_loss": 5.101281642913818,
|
| 344 |
+
"eval_runtime": 570.8524,
|
| 345 |
+
"eval_samples_per_second": 54.214,
|
| 346 |
+
"eval_steps_per_second": 3.39,
|
| 347 |
+
"step": 14520
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 15.496124031007753,
|
| 351 |
+
"grad_norm": 5.0534281730651855,
|
| 352 |
+
"learning_rate": 4.22440537745605e-05,
|
| 353 |
+
"loss": 5.0547,
|
| 354 |
+
"step": 15000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 16.0,
|
| 358 |
+
"eval_accuracy": 0.21727949673638433,
|
| 359 |
+
"eval_loss": 5.1018967628479,
|
| 360 |
+
"eval_runtime": 570.8378,
|
| 361 |
+
"eval_samples_per_second": 54.215,
|
| 362 |
+
"eval_steps_per_second": 3.39,
|
| 363 |
+
"step": 15488
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 16.012403100775195,
|
| 367 |
+
"grad_norm": 5.0263752937316895,
|
| 368 |
+
"learning_rate": 4.198552223371252e-05,
|
| 369 |
+
"loss": 5.0508,
|
| 370 |
+
"step": 15500
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 16.52919896640827,
|
| 374 |
+
"grad_norm": 3.9026286602020264,
|
| 375 |
+
"learning_rate": 4.172699069286453e-05,
|
| 376 |
+
"loss": 5.0532,
|
| 377 |
+
"step": 16000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 17.0,
|
| 381 |
+
"eval_accuracy": 0.21736250405690846,
|
| 382 |
+
"eval_loss": 5.093143939971924,
|
| 383 |
+
"eval_runtime": 570.8413,
|
| 384 |
+
"eval_samples_per_second": 54.215,
|
| 385 |
+
"eval_steps_per_second": 3.39,
|
| 386 |
+
"step": 16456
|
| 387 |
+
}
|
| 388 |
+
],
|
| 389 |
+
"logging_steps": 500,
|
| 390 |
+
"max_steps": 96700,
|
| 391 |
+
"num_input_tokens_seen": 0,
|
| 392 |
+
"num_train_epochs": 100,
|
| 393 |
+
"save_steps": 500,
|
| 394 |
+
"stateful_callbacks": {
|
| 395 |
+
"TrainerControl": {
|
| 396 |
+
"args": {
|
| 397 |
+
"should_epoch_stop": false,
|
| 398 |
+
"should_evaluate": false,
|
| 399 |
+
"should_log": false,
|
| 400 |
+
"should_save": true,
|
| 401 |
+
"should_training_stop": false
|
| 402 |
+
},
|
| 403 |
+
"attributes": {}
|
| 404 |
+
}
|
| 405 |
+
},
|
| 406 |
+
"total_flos": 5.31244216577348e+17,
|
| 407 |
+
"train_batch_size": 16,
|
| 408 |
+
"trial_name": null,
|
| 409 |
+
"trial_params": null
|
| 410 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91d12bff95227ff53637ef76714e7e63db1124e17a30b683660fb63448b8b5f1
|
| 3 |
+
size 5368
|