Upload 10 files
Browse filesfull model upload
- config.json +29 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +64 -0
- trainer_state.json +368 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "pdelobelle/robbert-v2-dutch-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 514,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"output_past": true,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"position_embedding_type": "absolute",
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.29.2",
|
| 26 |
+
"type_vocab_size": 1,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 40000
|
| 29 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4627ac8e6ae84197f5c472f6c45a6ad25547367138b56c1f46f16c483dd710a
|
| 3 |
+
size 467288313
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f22fa5b10476747198575aa16cf8ef6cbf85c812575cf45e380952f7881c8a0
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82a5fc6b2925cf5b50f528912e65dc00ca27ee30fb5ac6d39c8654c7c9ba863c
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"__type": "AddedToken",
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false
|
| 10 |
+
},
|
| 11 |
+
"clean_up_tokenization_spaces": true,
|
| 12 |
+
"cls_token": {
|
| 13 |
+
"__type": "AddedToken",
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"eos_token": {
|
| 21 |
+
"__type": "AddedToken",
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
},
|
| 28 |
+
"errors": "replace",
|
| 29 |
+
"mask_token": {
|
| 30 |
+
"__type": "AddedToken",
|
| 31 |
+
"content": "<mask>",
|
| 32 |
+
"lstrip": true,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"model_max_length": 512,
|
| 38 |
+
"pad_token": {
|
| 39 |
+
"__type": "AddedToken",
|
| 40 |
+
"content": "<pad>",
|
| 41 |
+
"lstrip": false,
|
| 42 |
+
"normalized": true,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"single_word": false
|
| 45 |
+
},
|
| 46 |
+
"sep_token": {
|
| 47 |
+
"__type": "AddedToken",
|
| 48 |
+
"content": "</s>",
|
| 49 |
+
"lstrip": false,
|
| 50 |
+
"normalized": true,
|
| 51 |
+
"rstrip": false,
|
| 52 |
+
"single_word": false
|
| 53 |
+
},
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": {
|
| 57 |
+
"__type": "AddedToken",
|
| 58 |
+
"content": "<unk>",
|
| 59 |
+
"lstrip": false,
|
| 60 |
+
"normalized": true,
|
| 61 |
+
"rstrip": false,
|
| 62 |
+
"single_word": false
|
| 63 |
+
}
|
| 64 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,368 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 17.71217712177122,
|
| 5 |
+
"global_step": 18000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.49,
|
| 12 |
+
"learning_rate": 5e-05,
|
| 13 |
+
"loss": 7.6438,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.98,
|
| 18 |
+
"learning_rate": 0.0001,
|
| 19 |
+
"loss": 5.7351,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.0,
|
| 24 |
+
"eval_loss": 4.940077781677246,
|
| 25 |
+
"eval_runtime": 528.7918,
|
| 26 |
+
"eval_samples_per_second": 134.174,
|
| 27 |
+
"eval_steps_per_second": 4.194,
|
| 28 |
+
"step": 1016
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 1.48,
|
| 32 |
+
"learning_rate": 9.705882352941177e-05,
|
| 33 |
+
"loss": 4.4237,
|
| 34 |
+
"step": 1500
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 1.97,
|
| 38 |
+
"learning_rate": 9.411764705882353e-05,
|
| 39 |
+
"loss": 3.5768,
|
| 40 |
+
"step": 2000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 2.0,
|
| 44 |
+
"eval_loss": 3.184535503387451,
|
| 45 |
+
"eval_runtime": 528.8582,
|
| 46 |
+
"eval_samples_per_second": 134.157,
|
| 47 |
+
"eval_steps_per_second": 4.194,
|
| 48 |
+
"step": 2032
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 2.46,
|
| 52 |
+
"learning_rate": 9.11764705882353e-05,
|
| 53 |
+
"loss": 3.133,
|
| 54 |
+
"step": 2500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 2.95,
|
| 58 |
+
"learning_rate": 8.823529411764706e-05,
|
| 59 |
+
"loss": 2.8394,
|
| 60 |
+
"step": 3000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 3.0,
|
| 64 |
+
"eval_loss": 2.624265432357788,
|
| 65 |
+
"eval_runtime": 528.7795,
|
| 66 |
+
"eval_samples_per_second": 134.177,
|
| 67 |
+
"eval_steps_per_second": 4.195,
|
| 68 |
+
"step": 3048
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 3.44,
|
| 72 |
+
"learning_rate": 8.529411764705883e-05,
|
| 73 |
+
"loss": 2.6312,
|
| 74 |
+
"step": 3500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 3.94,
|
| 78 |
+
"learning_rate": 8.23529411764706e-05,
|
| 79 |
+
"loss": 2.4785,
|
| 80 |
+
"step": 4000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 4.0,
|
| 84 |
+
"eval_loss": 2.317702293395996,
|
| 85 |
+
"eval_runtime": 528.7913,
|
| 86 |
+
"eval_samples_per_second": 134.174,
|
| 87 |
+
"eval_steps_per_second": 4.194,
|
| 88 |
+
"step": 4065
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 4.43,
|
| 92 |
+
"learning_rate": 7.941176470588235e-05,
|
| 93 |
+
"loss": 2.3492,
|
| 94 |
+
"step": 4500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 4.92,
|
| 98 |
+
"learning_rate": 7.647058823529411e-05,
|
| 99 |
+
"loss": 2.2543,
|
| 100 |
+
"step": 5000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 5.0,
|
| 104 |
+
"eval_loss": 2.1236534118652344,
|
| 105 |
+
"eval_runtime": 528.7093,
|
| 106 |
+
"eval_samples_per_second": 134.195,
|
| 107 |
+
"eval_steps_per_second": 4.195,
|
| 108 |
+
"step": 5081
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 5.41,
|
| 112 |
+
"learning_rate": 7.352941176470589e-05,
|
| 113 |
+
"loss": 2.1703,
|
| 114 |
+
"step": 5500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 5.9,
|
| 118 |
+
"learning_rate": 7.058823529411765e-05,
|
| 119 |
+
"loss": 2.0987,
|
| 120 |
+
"step": 6000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 6.0,
|
| 124 |
+
"eval_loss": 1.9984703063964844,
|
| 125 |
+
"eval_runtime": 528.5607,
|
| 126 |
+
"eval_samples_per_second": 134.232,
|
| 127 |
+
"eval_steps_per_second": 4.196,
|
| 128 |
+
"step": 6097
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 6.4,
|
| 132 |
+
"learning_rate": 6.764705882352942e-05,
|
| 133 |
+
"loss": 2.0345,
|
| 134 |
+
"step": 6500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 6.89,
|
| 138 |
+
"learning_rate": 6.470588235294118e-05,
|
| 139 |
+
"loss": 1.9782,
|
| 140 |
+
"step": 7000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 7.0,
|
| 144 |
+
"eval_loss": 1.912542462348938,
|
| 145 |
+
"eval_runtime": 528.7872,
|
| 146 |
+
"eval_samples_per_second": 134.175,
|
| 147 |
+
"eval_steps_per_second": 4.195,
|
| 148 |
+
"step": 7113
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 7.38,
|
| 152 |
+
"learning_rate": 6.176470588235295e-05,
|
| 153 |
+
"loss": 1.9332,
|
| 154 |
+
"step": 7500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 7.87,
|
| 158 |
+
"learning_rate": 5.882352941176471e-05,
|
| 159 |
+
"loss": 1.8975,
|
| 160 |
+
"step": 8000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 8.0,
|
| 164 |
+
"eval_loss": 1.8240903615951538,
|
| 165 |
+
"eval_runtime": 528.7253,
|
| 166 |
+
"eval_samples_per_second": 134.191,
|
| 167 |
+
"eval_steps_per_second": 4.195,
|
| 168 |
+
"step": 8130
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 8.36,
|
| 172 |
+
"learning_rate": 5.588235294117647e-05,
|
| 173 |
+
"loss": 1.8558,
|
| 174 |
+
"step": 8500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 8.86,
|
| 178 |
+
"learning_rate": 5.294117647058824e-05,
|
| 179 |
+
"loss": 1.8258,
|
| 180 |
+
"step": 9000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 9.0,
|
| 184 |
+
"eval_loss": 1.7565855979919434,
|
| 185 |
+
"eval_runtime": 529.8424,
|
| 186 |
+
"eval_samples_per_second": 133.908,
|
| 187 |
+
"eval_steps_per_second": 4.186,
|
| 188 |
+
"step": 9146
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 9.35,
|
| 192 |
+
"learning_rate": 5e-05,
|
| 193 |
+
"loss": 1.7841,
|
| 194 |
+
"step": 9500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 9.84,
|
| 198 |
+
"learning_rate": 4.705882352941177e-05,
|
| 199 |
+
"loss": 1.7621,
|
| 200 |
+
"step": 10000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 10.0,
|
| 204 |
+
"eval_loss": 1.710971713066101,
|
| 205 |
+
"eval_runtime": 529.8142,
|
| 206 |
+
"eval_samples_per_second": 133.915,
|
| 207 |
+
"eval_steps_per_second": 4.186,
|
| 208 |
+
"step": 10162
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 10.33,
|
| 212 |
+
"learning_rate": 4.411764705882353e-05,
|
| 213 |
+
"loss": 1.7383,
|
| 214 |
+
"step": 10500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 10.82,
|
| 218 |
+
"learning_rate": 4.11764705882353e-05,
|
| 219 |
+
"loss": 1.711,
|
| 220 |
+
"step": 11000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 11.0,
|
| 224 |
+
"eval_loss": 1.6690000295639038,
|
| 225 |
+
"eval_runtime": 528.7385,
|
| 226 |
+
"eval_samples_per_second": 134.187,
|
| 227 |
+
"eval_steps_per_second": 4.195,
|
| 228 |
+
"step": 11178
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 11.32,
|
| 232 |
+
"learning_rate": 3.8235294117647055e-05,
|
| 233 |
+
"loss": 1.6908,
|
| 234 |
+
"step": 11500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 11.81,
|
| 238 |
+
"learning_rate": 3.529411764705883e-05,
|
| 239 |
+
"loss": 1.6665,
|
| 240 |
+
"step": 12000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 12.0,
|
| 244 |
+
"eval_loss": 1.6373904943466187,
|
| 245 |
+
"eval_runtime": 528.848,
|
| 246 |
+
"eval_samples_per_second": 134.16,
|
| 247 |
+
"eval_steps_per_second": 4.194,
|
| 248 |
+
"step": 12195
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 12.3,
|
| 252 |
+
"learning_rate": 3.235294117647059e-05,
|
| 253 |
+
"loss": 1.6546,
|
| 254 |
+
"step": 12500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 12.79,
|
| 258 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 259 |
+
"loss": 1.6246,
|
| 260 |
+
"step": 13000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 13.0,
|
| 264 |
+
"eval_loss": 1.5987190008163452,
|
| 265 |
+
"eval_runtime": 528.7748,
|
| 266 |
+
"eval_samples_per_second": 134.178,
|
| 267 |
+
"eval_steps_per_second": 4.195,
|
| 268 |
+
"step": 13211
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 13.28,
|
| 272 |
+
"learning_rate": 2.647058823529412e-05,
|
| 273 |
+
"loss": 1.6166,
|
| 274 |
+
"step": 13500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 13.78,
|
| 278 |
+
"learning_rate": 2.3529411764705884e-05,
|
| 279 |
+
"loss": 1.603,
|
| 280 |
+
"step": 14000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 14.0,
|
| 284 |
+
"eval_loss": 1.5721200704574585,
|
| 285 |
+
"eval_runtime": 528.6668,
|
| 286 |
+
"eval_samples_per_second": 134.206,
|
| 287 |
+
"eval_steps_per_second": 4.195,
|
| 288 |
+
"step": 14227
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 14.27,
|
| 292 |
+
"learning_rate": 2.058823529411765e-05,
|
| 293 |
+
"loss": 1.5918,
|
| 294 |
+
"step": 14500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 14.76,
|
| 298 |
+
"learning_rate": 1.7647058823529414e-05,
|
| 299 |
+
"loss": 1.5762,
|
| 300 |
+
"step": 15000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 15.0,
|
| 304 |
+
"eval_loss": 1.5530680418014526,
|
| 305 |
+
"eval_runtime": 528.7404,
|
| 306 |
+
"eval_samples_per_second": 134.187,
|
| 307 |
+
"eval_steps_per_second": 4.195,
|
| 308 |
+
"step": 15243
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 15.25,
|
| 312 |
+
"learning_rate": 1.4705882352941177e-05,
|
| 313 |
+
"loss": 1.5625,
|
| 314 |
+
"step": 15500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 15.74,
|
| 318 |
+
"learning_rate": 1.1764705882352942e-05,
|
| 319 |
+
"loss": 1.5572,
|
| 320 |
+
"step": 16000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 16.0,
|
| 324 |
+
"eval_loss": 1.535999059677124,
|
| 325 |
+
"eval_runtime": 528.8228,
|
| 326 |
+
"eval_samples_per_second": 134.166,
|
| 327 |
+
"eval_steps_per_second": 4.194,
|
| 328 |
+
"step": 16260
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 16.24,
|
| 332 |
+
"learning_rate": 8.823529411764707e-06,
|
| 333 |
+
"loss": 1.5418,
|
| 334 |
+
"step": 16500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 16.73,
|
| 338 |
+
"learning_rate": 5.882352941176471e-06,
|
| 339 |
+
"loss": 1.5338,
|
| 340 |
+
"step": 17000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 17.0,
|
| 344 |
+
"eval_loss": 1.535353422164917,
|
| 345 |
+
"eval_runtime": 528.5026,
|
| 346 |
+
"eval_samples_per_second": 134.247,
|
| 347 |
+
"eval_steps_per_second": 4.197,
|
| 348 |
+
"step": 17276
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 17.22,
|
| 352 |
+
"learning_rate": 2.9411764705882355e-06,
|
| 353 |
+
"loss": 1.5272,
|
| 354 |
+
"step": 17500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 17.71,
|
| 358 |
+
"learning_rate": 0.0,
|
| 359 |
+
"loss": 1.524,
|
| 360 |
+
"step": 18000
|
| 361 |
+
}
|
| 362 |
+
],
|
| 363 |
+
"max_steps": 18000,
|
| 364 |
+
"num_train_epochs": 18,
|
| 365 |
+
"total_flos": 4.738018441728768e+17,
|
| 366 |
+
"trial_name": null,
|
| 367 |
+
"trial_params": null
|
| 368 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fccdc647fa4a93d663b0ab65aa0e15589a1e0dde8bb144ad70ac144f5caa2edd
|
| 3 |
+
size 3963
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|