Training in progress, epoch 8, checkpoint
Browse files- checkpoint-29944/config.json +59 -0
- checkpoint-29944/generation_config.json +12 -0
- checkpoint-29944/model.safetensors +3 -0
- checkpoint-29944/optimizer.pt +3 -0
- checkpoint-29944/rng_state.pth +3 -0
- checkpoint-29944/scheduler.pt +3 -0
- checkpoint-29944/sentencepiece.bpe.model +3 -0
- checkpoint-29944/special_tokens_map.json +15 -0
- checkpoint-29944/tokenizer.json +0 -0
- checkpoint-29944/tokenizer_config.json +55 -0
- checkpoint-29944/trainer_state.json +600 -0
- checkpoint-29944/training_args.bin +3 -0
checkpoint-29944/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-29944/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-29944/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06fd7924e8484d28248501e04d52d75a9ca01314a3bfa3a9cb694fcf4c0c5570
|
3 |
+
size 557116312
|
checkpoint-29944/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d48b866820a13939d7bcede8741fd8049d9d3d2a4f3a176fe71d1c83683e866
|
3 |
+
size 1113991930
|
checkpoint-29944/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b689ed000e6769a689a2f55a26b0534a56b3743205d5316ab38d1f99759a2e4
|
3 |
+
size 14244
|
checkpoint-29944/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55b359a2ddbd119e4a85f4859ff895ea5a6776262560ff703b0b21835295dc92
|
3 |
+
size 1064
|
checkpoint-29944/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-29944/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-29944/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-29944/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-29944/trainer_state.json
ADDED
@@ -0,0 +1,600 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 27.7286,
|
3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/ArabartModel/checkpoint-26201",
|
4 |
+
"epoch": 8.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 29944,
|
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 |
+
"epoch": 5.2356020942408374,
|
173 |
+
"grad_norm": 4.417330741882324,
|
174 |
+
"learning_rate": 2.382198952879581e-05,
|
175 |
+
"loss": 0.9343,
|
176 |
+
"step": 8000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 5.56282722513089,
|
180 |
+
"grad_norm": 5.149570465087891,
|
181 |
+
"learning_rate": 2.218586387434555e-05,
|
182 |
+
"loss": 0.9473,
|
183 |
+
"step": 8500
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 5.890052356020942,
|
187 |
+
"grad_norm": 5.305272102355957,
|
188 |
+
"learning_rate": 2.054973821989529e-05,
|
189 |
+
"loss": 0.9589,
|
190 |
+
"step": 9000
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 6.0,
|
194 |
+
"eval_loss": 3.433619737625122,
|
195 |
+
"eval_rouge1": 26.3479,
|
196 |
+
"eval_rouge2": 10.8544,
|
197 |
+
"eval_rougeL": 23.0206,
|
198 |
+
"eval_runtime": 385.2891,
|
199 |
+
"eval_samples_per_second": 5.697,
|
200 |
+
"eval_steps_per_second": 0.571,
|
201 |
+
"step": 9168
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 6.217277486910994,
|
205 |
+
"grad_norm": 5.96689510345459,
|
206 |
+
"learning_rate": 1.8913612565445027e-05,
|
207 |
+
"loss": 0.8437,
|
208 |
+
"step": 9500
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 6.544502617801047,
|
212 |
+
"grad_norm": 5.179261207580566,
|
213 |
+
"learning_rate": 1.7277486910994763e-05,
|
214 |
+
"loss": 0.8582,
|
215 |
+
"step": 10000
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 6.871727748691099,
|
219 |
+
"grad_norm": 4.92213773727417,
|
220 |
+
"learning_rate": 1.5641361256544503e-05,
|
221 |
+
"loss": 0.8669,
|
222 |
+
"step": 10500
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 7.0,
|
226 |
+
"eval_loss": 3.551990032196045,
|
227 |
+
"eval_rouge1": 26.0878,
|
228 |
+
"eval_rouge2": 10.6444,
|
229 |
+
"eval_rougeL": 22.7671,
|
230 |
+
"eval_runtime": 413.1448,
|
231 |
+
"eval_samples_per_second": 5.313,
|
232 |
+
"eval_steps_per_second": 0.533,
|
233 |
+
"step": 10696
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 7.198952879581152,
|
237 |
+
"grad_norm": 4.538914203643799,
|
238 |
+
"learning_rate": 1.4005235602094241e-05,
|
239 |
+
"loss": 0.7803,
|
240 |
+
"step": 11000
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 7.526178010471204,
|
244 |
+
"grad_norm": 5.420250415802002,
|
245 |
+
"learning_rate": 1.236910994764398e-05,
|
246 |
+
"loss": 0.7777,
|
247 |
+
"step": 11500
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 7.853403141361256,
|
251 |
+
"grad_norm": 4.503458023071289,
|
252 |
+
"learning_rate": 1.0732984293193717e-05,
|
253 |
+
"loss": 0.7894,
|
254 |
+
"step": 12000
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 8.0,
|
258 |
+
"eval_loss": 3.652216672897339,
|
259 |
+
"eval_rouge1": 26.1239,
|
260 |
+
"eval_rouge2": 10.689,
|
261 |
+
"eval_rougeL": 22.8303,
|
262 |
+
"eval_runtime": 389.5703,
|
263 |
+
"eval_samples_per_second": 5.634,
|
264 |
+
"eval_steps_per_second": 0.565,
|
265 |
+
"step": 12224
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 8.180628272251308,
|
269 |
+
"grad_norm": 4.9211812019348145,
|
270 |
+
"learning_rate": 9.096858638743457e-06,
|
271 |
+
"loss": 0.7505,
|
272 |
+
"step": 12500
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 8.507853403141361,
|
276 |
+
"grad_norm": 4.948258876800537,
|
277 |
+
"learning_rate": 7.4607329842931935e-06,
|
278 |
+
"loss": 0.731,
|
279 |
+
"step": 13000
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 8.835078534031414,
|
283 |
+
"grad_norm": 4.717357158660889,
|
284 |
+
"learning_rate": 5.824607329842932e-06,
|
285 |
+
"loss": 0.7331,
|
286 |
+
"step": 13500
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 9.0,
|
290 |
+
"eval_loss": 3.7317800521850586,
|
291 |
+
"eval_rouge1": 26.2374,
|
292 |
+
"eval_rouge2": 10.7166,
|
293 |
+
"eval_rougeL": 22.9298,
|
294 |
+
"eval_runtime": 385.8895,
|
295 |
+
"eval_samples_per_second": 5.688,
|
296 |
+
"eval_steps_per_second": 0.57,
|
297 |
+
"step": 13752
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 9.162303664921467,
|
301 |
+
"grad_norm": 4.790928363800049,
|
302 |
+
"learning_rate": 4.18848167539267e-06,
|
303 |
+
"loss": 0.7187,
|
304 |
+
"step": 14000
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 9.489528795811518,
|
308 |
+
"grad_norm": 4.424731254577637,
|
309 |
+
"learning_rate": 2.5523560209424085e-06,
|
310 |
+
"loss": 0.6988,
|
311 |
+
"step": 14500
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 9.81675392670157,
|
315 |
+
"grad_norm": 4.868335723876953,
|
316 |
+
"learning_rate": 9.162303664921465e-07,
|
317 |
+
"loss": 0.7027,
|
318 |
+
"step": 15000
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 10.0,
|
322 |
+
"eval_loss": 3.772279739379883,
|
323 |
+
"eval_rouge1": 26.1242,
|
324 |
+
"eval_rouge2": 10.7689,
|
325 |
+
"eval_rougeL": 22.8692,
|
326 |
+
"eval_runtime": 387.9211,
|
327 |
+
"eval_samples_per_second": 5.658,
|
328 |
+
"eval_steps_per_second": 0.567,
|
329 |
+
"step": 15280
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 4.141063318193962,
|
333 |
+
"grad_norm": 4.127313613891602,
|
334 |
+
"learning_rate": 3.619645560602013e-05,
|
335 |
+
"loss": 2.3856,
|
336 |
+
"step": 15500
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 4.2746460058776385,
|
340 |
+
"grad_norm": 3.7080917358398438,
|
341 |
+
"learning_rate": 3.575117998040787e-05,
|
342 |
+
"loss": 2.2343,
|
343 |
+
"step": 16000
|
344 |
+
},
|
345 |
+
{
|
346 |
+
"epoch": 4.408228693561314,
|
347 |
+
"grad_norm": 3.771442413330078,
|
348 |
+
"learning_rate": 3.530590435479562e-05,
|
349 |
+
"loss": 2.2498,
|
350 |
+
"step": 16500
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 4.54181138124499,
|
354 |
+
"grad_norm": 3.3883867263793945,
|
355 |
+
"learning_rate": 3.486062872918336e-05,
|
356 |
+
"loss": 2.2734,
|
357 |
+
"step": 17000
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 4.675394068928667,
|
361 |
+
"grad_norm": 3.82869029045105,
|
362 |
+
"learning_rate": 3.441535310357111e-05,
|
363 |
+
"loss": 2.2957,
|
364 |
+
"step": 17500
|
365 |
+
},
|
366 |
+
{
|
367 |
+
"epoch": 4.808976756612343,
|
368 |
+
"grad_norm": 3.480701208114624,
|
369 |
+
"learning_rate": 3.397007747795886e-05,
|
370 |
+
"loss": 2.255,
|
371 |
+
"step": 18000
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 4.94255944429602,
|
375 |
+
"grad_norm": 3.433276891708374,
|
376 |
+
"learning_rate": 3.3524801852346606e-05,
|
377 |
+
"loss": 2.2527,
|
378 |
+
"step": 18500
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 5.0,
|
382 |
+
"eval_loss": 2.624432325363159,
|
383 |
+
"eval_rouge1": 27.5622,
|
384 |
+
"eval_rouge2": 11.8188,
|
385 |
+
"eval_rougeL": 24.2339,
|
386 |
+
"eval_runtime": 862.1361,
|
387 |
+
"eval_samples_per_second": 5.439,
|
388 |
+
"eval_steps_per_second": 0.544,
|
389 |
+
"step": 18715
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 5.0761421319796955,
|
393 |
+
"grad_norm": 3.8290796279907227,
|
394 |
+
"learning_rate": 3.307952622673435e-05,
|
395 |
+
"loss": 2.1614,
|
396 |
+
"step": 19000
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 5.209724819663371,
|
400 |
+
"grad_norm": 4.148732662200928,
|
401 |
+
"learning_rate": 3.2634250601122095e-05,
|
402 |
+
"loss": 2.028,
|
403 |
+
"step": 19500
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 5.343307507347048,
|
407 |
+
"grad_norm": 3.9491941928863525,
|
408 |
+
"learning_rate": 3.218897497550984e-05,
|
409 |
+
"loss": 2.0413,
|
410 |
+
"step": 20000
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 5.476890195030724,
|
414 |
+
"grad_norm": 4.000278472900391,
|
415 |
+
"learning_rate": 3.174369934989759e-05,
|
416 |
+
"loss": 2.1058,
|
417 |
+
"step": 20500
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 5.6104728827144,
|
421 |
+
"grad_norm": 4.109215259552002,
|
422 |
+
"learning_rate": 3.129842372428534e-05,
|
423 |
+
"loss": 2.0563,
|
424 |
+
"step": 21000
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 5.744055570398077,
|
428 |
+
"grad_norm": 3.3794937133789062,
|
429 |
+
"learning_rate": 3.085314809867308e-05,
|
430 |
+
"loss": 2.0737,
|
431 |
+
"step": 21500
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 5.8776382580817526,
|
435 |
+
"grad_norm": 3.326864719390869,
|
436 |
+
"learning_rate": 3.0407872473060827e-05,
|
437 |
+
"loss": 2.085,
|
438 |
+
"step": 22000
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 6.0,
|
442 |
+
"eval_loss": 2.6439783573150635,
|
443 |
+
"eval_rouge1": 27.1127,
|
444 |
+
"eval_rouge2": 11.6364,
|
445 |
+
"eval_rougeL": 23.8039,
|
446 |
+
"eval_runtime": 879.7933,
|
447 |
+
"eval_samples_per_second": 5.33,
|
448 |
+
"eval_steps_per_second": 0.533,
|
449 |
+
"step": 22458
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 6.011220945765428,
|
453 |
+
"grad_norm": 3.5264782905578613,
|
454 |
+
"learning_rate": 2.9962596847448572e-05,
|
455 |
+
"loss": 1.8559,
|
456 |
+
"step": 22500
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 6.144803633449105,
|
460 |
+
"grad_norm": 3.7577388286590576,
|
461 |
+
"learning_rate": 2.951732122183632e-05,
|
462 |
+
"loss": 1.8982,
|
463 |
+
"step": 23000
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"epoch": 6.278386321132781,
|
467 |
+
"grad_norm": 3.2084107398986816,
|
468 |
+
"learning_rate": 2.907204559622406e-05,
|
469 |
+
"loss": 1.8801,
|
470 |
+
"step": 23500
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 6.411969008816458,
|
474 |
+
"grad_norm": 4.275125503540039,
|
475 |
+
"learning_rate": 2.8626769970611812e-05,
|
476 |
+
"loss": 1.9144,
|
477 |
+
"step": 24000
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 6.545551696500134,
|
481 |
+
"grad_norm": 3.5503015518188477,
|
482 |
+
"learning_rate": 2.8181494344999553e-05,
|
483 |
+
"loss": 1.9229,
|
484 |
+
"step": 24500
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 6.67913438418381,
|
488 |
+
"grad_norm": 3.489950656890869,
|
489 |
+
"learning_rate": 2.77362187193873e-05,
|
490 |
+
"loss": 1.9033,
|
491 |
+
"step": 25000
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 6.812717071867486,
|
495 |
+
"grad_norm": 3.5493781566619873,
|
496 |
+
"learning_rate": 2.7290943093775046e-05,
|
497 |
+
"loss": 1.9058,
|
498 |
+
"step": 25500
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 6.946299759551162,
|
502 |
+
"grad_norm": 3.603605031967163,
|
503 |
+
"learning_rate": 2.6845667468162793e-05,
|
504 |
+
"loss": 1.8774,
|
505 |
+
"step": 26000
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 7.0,
|
509 |
+
"eval_loss": 2.670841693878174,
|
510 |
+
"eval_rouge1": 27.7286,
|
511 |
+
"eval_rouge2": 11.9572,
|
512 |
+
"eval_rougeL": 24.3316,
|
513 |
+
"eval_runtime": 903.5292,
|
514 |
+
"eval_samples_per_second": 5.19,
|
515 |
+
"eval_steps_per_second": 0.519,
|
516 |
+
"step": 26201
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 7.079882447234838,
|
520 |
+
"grad_norm": 3.9646942615509033,
|
521 |
+
"learning_rate": 2.640039184255054e-05,
|
522 |
+
"loss": 1.8442,
|
523 |
+
"step": 26500
|
524 |
+
},
|
525 |
+
{
|
526 |
+
"epoch": 7.213465134918515,
|
527 |
+
"grad_norm": 4.019280433654785,
|
528 |
+
"learning_rate": 2.5955116216938286e-05,
|
529 |
+
"loss": 1.729,
|
530 |
+
"step": 27000
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 7.347047822602191,
|
534 |
+
"grad_norm": 3.9131412506103516,
|
535 |
+
"learning_rate": 2.5509840591326034e-05,
|
536 |
+
"loss": 1.7656,
|
537 |
+
"step": 27500
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 7.480630510285867,
|
541 |
+
"grad_norm": 3.336970806121826,
|
542 |
+
"learning_rate": 2.5064564965713778e-05,
|
543 |
+
"loss": 1.7733,
|
544 |
+
"step": 28000
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 7.614213197969543,
|
548 |
+
"grad_norm": 3.7517452239990234,
|
549 |
+
"learning_rate": 2.4619289340101523e-05,
|
550 |
+
"loss": 1.7842,
|
551 |
+
"step": 28500
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 7.747795885653219,
|
555 |
+
"grad_norm": 3.8601882457733154,
|
556 |
+
"learning_rate": 2.4174013714489267e-05,
|
557 |
+
"loss": 1.7876,
|
558 |
+
"step": 29000
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 7.881378573336896,
|
562 |
+
"grad_norm": 3.928703784942627,
|
563 |
+
"learning_rate": 2.372873808887702e-05,
|
564 |
+
"loss": 1.7826,
|
565 |
+
"step": 29500
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"epoch": 8.0,
|
569 |
+
"eval_loss": 2.7165374755859375,
|
570 |
+
"eval_rouge1": 27.5923,
|
571 |
+
"eval_rouge2": 11.9,
|
572 |
+
"eval_rougeL": 24.2586,
|
573 |
+
"eval_runtime": 898.7001,
|
574 |
+
"eval_samples_per_second": 5.218,
|
575 |
+
"eval_steps_per_second": 0.522,
|
576 |
+
"step": 29944
|
577 |
+
}
|
578 |
+
],
|
579 |
+
"logging_steps": 500,
|
580 |
+
"max_steps": 56145,
|
581 |
+
"num_input_tokens_seen": 0,
|
582 |
+
"num_train_epochs": 15,
|
583 |
+
"save_steps": 500,
|
584 |
+
"stateful_callbacks": {
|
585 |
+
"TrainerControl": {
|
586 |
+
"args": {
|
587 |
+
"should_epoch_stop": false,
|
588 |
+
"should_evaluate": false,
|
589 |
+
"should_log": false,
|
590 |
+
"should_save": true,
|
591 |
+
"should_training_stop": false
|
592 |
+
},
|
593 |
+
"attributes": {}
|
594 |
+
}
|
595 |
+
},
|
596 |
+
"total_flos": 1.577814944897065e+17,
|
597 |
+
"train_batch_size": 10,
|
598 |
+
"trial_name": null,
|
599 |
+
"trial_params": null
|
600 |
+
}
|
checkpoint-29944/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b9414c9eeaaab303ed5167bf6ea848b944aeeea9d5c2edfef10ea3671a79573
|
3 |
+
size 6904
|