Training in progress, epoch 5, checkpoint
Browse files- checkpoint-7640/config.json +59 -0
- checkpoint-7640/generation_config.json +12 -0
- checkpoint-7640/model.safetensors +3 -0
- checkpoint-7640/optimizer.pt +3 -0
- checkpoint-7640/rng_state.pth +3 -0
- checkpoint-7640/scheduler.pt +3 -0
- checkpoint-7640/sentencepiece.bpe.model +3 -0
- checkpoint-7640/special_tokens_map.json +15 -0
- checkpoint-7640/tokenizer.json +0 -0
- checkpoint-7640/tokenizer_config.json +55 -0
- checkpoint-7640/trainer_state.json +193 -0
- checkpoint-7640/training_args.bin +3 -0
checkpoint-7640/config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "nour4286/ArabartModel",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": true,
|
7 |
+
"architectures": [
|
8 |
+
"MBartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 768,
|
15 |
+
"decoder_attention_heads": 12,
|
16 |
+
"decoder_ffn_dim": 3072,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"do_blenderbot_90_layernorm": false,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"early_stopping": true,
|
23 |
+
"encoder_attention_heads": 12,
|
24 |
+
"encoder_ffn_dim": 3072,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 6,
|
27 |
+
"eos_token_id": 2,
|
28 |
+
"extra_pos_embeddings": 2,
|
29 |
+
"force_bos_token_to_be_generated": false,
|
30 |
+
"forced_eos_token_id": 2,
|
31 |
+
"gradient_checkpointing": false,
|
32 |
+
"id2label": {
|
33 |
+
"0": "LABEL_0",
|
34 |
+
"1": "LABEL_1",
|
35 |
+
"2": "LABEL_2"
|
36 |
+
},
|
37 |
+
"init_std": 0.02,
|
38 |
+
"is_encoder_decoder": true,
|
39 |
+
"label2id": {
|
40 |
+
"LABEL_0": 0,
|
41 |
+
"LABEL_1": 1,
|
42 |
+
"LABEL_2": 2
|
43 |
+
},
|
44 |
+
"max_position_embeddings": 1024,
|
45 |
+
"model_type": "mbart",
|
46 |
+
"no_repeat_ngram_size": 3,
|
47 |
+
"normalize_before": true,
|
48 |
+
"normalize_embedding": true,
|
49 |
+
"num_beams": 4,
|
50 |
+
"num_hidden_layers": 6,
|
51 |
+
"pad_token_id": 1,
|
52 |
+
"scale_embedding": false,
|
53 |
+
"static_position_embeddings": false,
|
54 |
+
"tokenizer_class": "BarthezTokenizer",
|
55 |
+
"torch_dtype": "float32",
|
56 |
+
"transformers_version": "4.41.2",
|
57 |
+
"use_cache": true,
|
58 |
+
"vocab_size": 50002
|
59 |
+
}
|
checkpoint-7640/generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 0,
|
3 |
+
"decoder_start_token_id": 2,
|
4 |
+
"early_stopping": true,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"forced_eos_token_id": 2,
|
7 |
+
"max_new_tokens": 100,
|
8 |
+
"no_repeat_ngram_size": 3,
|
9 |
+
"num_beams": 4,
|
10 |
+
"pad_token_id": 1,
|
11 |
+
"transformers_version": "4.41.2"
|
12 |
+
}
|
checkpoint-7640/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cbd3e57639f497dfe9a3709369680166af1dd6718cbb3290e9740eb1cd80739
|
3 |
+
size 557116312
|
checkpoint-7640/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fbd3d4707adad7a67285fdc5feab4e781ebc6423626e2d82982f4ad5c285bc2
|
3 |
+
size 1113991930
|
checkpoint-7640/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4829a631756d0d19b28fac2001aac34027fc5a4cf4a589cac247aa7d301b1d48
|
3 |
+
size 14244
|
checkpoint-7640/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc7cf011554c4867936295c5b14789c148f6a5d9269777211c9459a71223d9ca
|
3 |
+
size 1064
|
checkpoint-7640/sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbb59d772bc9bb2da5dc4a73a00c61c0912c6d2596aad970fa2cd3d69898b245
|
3 |
+
size 1315170
|
checkpoint-7640/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 |
+
}
|
checkpoint-7640/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-7640/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"50001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"sp_model_kwargs": {},
|
53 |
+
"tokenizer_class": "BarthezTokenizer",
|
54 |
+
"unk_token": "<unk>"
|
55 |
+
}
|
checkpoint-7640/trainer_state.json
ADDED
@@ -0,0 +1,193 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 26.5258,
|
3 |
+
"best_model_checkpoint": "/content/drive/My Drive/ArabartModel/checkpoint-6112",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 7640,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.32722513089005234,
|
13 |
+
"grad_norm": 1.563672423362732,
|
14 |
+
"learning_rate": 4.6727748691099475e-05,
|
15 |
+
"loss": 0.0195,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.6544502617801047,
|
20 |
+
"grad_norm": 1.7397737503051758,
|
21 |
+
"learning_rate": 4.3455497382198955e-05,
|
22 |
+
"loss": 0.0244,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.981675392670157,
|
27 |
+
"grad_norm": 3.006633758544922,
|
28 |
+
"learning_rate": 4.018324607329843e-05,
|
29 |
+
"loss": 0.0293,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 1.0,
|
34 |
+
"eval_loss": 5.626201629638672,
|
35 |
+
"eval_rouge1": 25.2705,
|
36 |
+
"eval_rouge2": 9.9865,
|
37 |
+
"eval_rougeL": 21.8678,
|
38 |
+
"eval_runtime": 372.5145,
|
39 |
+
"eval_samples_per_second": 5.892,
|
40 |
+
"eval_steps_per_second": 0.591,
|
41 |
+
"step": 1528
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 1.3089005235602094,
|
45 |
+
"grad_norm": 3.4732136726379395,
|
46 |
+
"learning_rate": 4.3455497382198955e-05,
|
47 |
+
"loss": 0.0456,
|
48 |
+
"step": 2000
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 1.6361256544502618,
|
52 |
+
"grad_norm": 2.2575156688690186,
|
53 |
+
"learning_rate": 4.181937172774869e-05,
|
54 |
+
"loss": 0.0619,
|
55 |
+
"step": 2500
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 1.9633507853403143,
|
59 |
+
"grad_norm": 6.030032157897949,
|
60 |
+
"learning_rate": 4.018324607329843e-05,
|
61 |
+
"loss": 0.0993,
|
62 |
+
"step": 3000
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 2.0,
|
66 |
+
"eval_loss": 5.542174339294434,
|
67 |
+
"eval_rouge1": 25.0744,
|
68 |
+
"eval_rouge2": 9.8534,
|
69 |
+
"eval_rougeL": 21.6992,
|
70 |
+
"eval_runtime": 411.9676,
|
71 |
+
"eval_samples_per_second": 5.328,
|
72 |
+
"eval_steps_per_second": 0.534,
|
73 |
+
"step": 3056
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 2.2905759162303667,
|
77 |
+
"grad_norm": 6.401626110076904,
|
78 |
+
"learning_rate": 3.8547120418848174e-05,
|
79 |
+
"loss": 0.21,
|
80 |
+
"step": 3500
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 2.6178010471204187,
|
84 |
+
"grad_norm": 5.806931495666504,
|
85 |
+
"learning_rate": 3.691099476439791e-05,
|
86 |
+
"loss": 0.3595,
|
87 |
+
"step": 4000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 2.945026178010471,
|
91 |
+
"grad_norm": 5.840355396270752,
|
92 |
+
"learning_rate": 3.5274869109947647e-05,
|
93 |
+
"loss": 0.6436,
|
94 |
+
"step": 4500
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 3.0,
|
98 |
+
"eval_loss": 3.927168369293213,
|
99 |
+
"eval_rouge1": 25.5914,
|
100 |
+
"eval_rouge2": 10.2904,
|
101 |
+
"eval_rougeL": 22.3089,
|
102 |
+
"eval_runtime": 412.3529,
|
103 |
+
"eval_samples_per_second": 5.323,
|
104 |
+
"eval_steps_per_second": 0.534,
|
105 |
+
"step": 4584
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 3.2722513089005236,
|
109 |
+
"grad_norm": 5.320337772369385,
|
110 |
+
"learning_rate": 3.3638743455497386e-05,
|
111 |
+
"loss": 0.7617,
|
112 |
+
"step": 5000
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 3.599476439790576,
|
116 |
+
"grad_norm": 5.708410739898682,
|
117 |
+
"learning_rate": 3.2002617801047126e-05,
|
118 |
+
"loss": 0.9186,
|
119 |
+
"step": 5500
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 3.9267015706806285,
|
123 |
+
"grad_norm": 6.043923377990723,
|
124 |
+
"learning_rate": 3.036649214659686e-05,
|
125 |
+
"loss": 1.112,
|
126 |
+
"step": 6000
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 4.0,
|
130 |
+
"eval_loss": 3.2077620029449463,
|
131 |
+
"eval_rouge1": 26.5258,
|
132 |
+
"eval_rouge2": 11.116,
|
133 |
+
"eval_rougeL": 23.3381,
|
134 |
+
"eval_runtime": 397.8337,
|
135 |
+
"eval_samples_per_second": 5.517,
|
136 |
+
"eval_steps_per_second": 0.553,
|
137 |
+
"step": 6112
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 4.2539267015706805,
|
141 |
+
"grad_norm": 5.179211139678955,
|
142 |
+
"learning_rate": 2.87303664921466e-05,
|
143 |
+
"loss": 1.0997,
|
144 |
+
"step": 6500
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 4.581151832460733,
|
148 |
+
"grad_norm": 4.997713565826416,
|
149 |
+
"learning_rate": 2.709424083769634e-05,
|
150 |
+
"loss": 1.0736,
|
151 |
+
"step": 7000
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 4.908376963350785,
|
155 |
+
"grad_norm": 5.441833972930908,
|
156 |
+
"learning_rate": 2.545811518324607e-05,
|
157 |
+
"loss": 1.0866,
|
158 |
+
"step": 7500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 5.0,
|
162 |
+
"eval_loss": 3.3156800270080566,
|
163 |
+
"eval_rouge1": 26.4275,
|
164 |
+
"eval_rouge2": 10.8484,
|
165 |
+
"eval_rougeL": 23.0503,
|
166 |
+
"eval_runtime": 402.2407,
|
167 |
+
"eval_samples_per_second": 5.457,
|
168 |
+
"eval_steps_per_second": 0.547,
|
169 |
+
"step": 7640
|
170 |
+
}
|
171 |
+
],
|
172 |
+
"logging_steps": 500,
|
173 |
+
"max_steps": 15280,
|
174 |
+
"num_input_tokens_seen": 0,
|
175 |
+
"num_train_epochs": 10,
|
176 |
+
"save_steps": 500,
|
177 |
+
"stateful_callbacks": {
|
178 |
+
"TrainerControl": {
|
179 |
+
"args": {
|
180 |
+
"should_epoch_stop": false,
|
181 |
+
"should_evaluate": false,
|
182 |
+
"should_log": false,
|
183 |
+
"should_save": true,
|
184 |
+
"should_training_stop": false
|
185 |
+
},
|
186 |
+
"attributes": {}
|
187 |
+
}
|
188 |
+
},
|
189 |
+
"total_flos": 3.665409368879923e+16,
|
190 |
+
"train_batch_size": 10,
|
191 |
+
"trial_name": null,
|
192 |
+
"trial_params": null
|
193 |
+
}
|
checkpoint-7640/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a35dd57590090f24ebba9a087e2c3d94297cd357e1c5960144536e9514488b6a
|
3 |
+
size 6904
|