Gaduh Hartawan
commited on
Commit
•
d1dfd80
1
Parent(s):
ed1e4ef
initial commit
Browse files- config.json +68 -0
- generation_config.json +16 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- tokenizer.json +0 -0
- trainer_state.json +721 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/bart-large-cnn",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0,
|
5 |
+
"activation_function": "gelu",
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": ["BartForConditionalGeneration"],
|
8 |
+
"attention_dropout": 0,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"classif_dropout": 0,
|
11 |
+
"classifier_dropout": 0,
|
12 |
+
"d_model": 1024,
|
13 |
+
"decoder_attention_heads": 16,
|
14 |
+
"decoder_ffn_dim": 4096,
|
15 |
+
"decoder_layerdrop": 0,
|
16 |
+
"decoder_layers": 12,
|
17 |
+
"decoder_start_token_id": 2,
|
18 |
+
"dropout": 0.1,
|
19 |
+
"early_stopping": true,
|
20 |
+
"encoder_attention_heads": 16,
|
21 |
+
"encoder_ffn_dim": 4096,
|
22 |
+
"encoder_layerdrop": 0,
|
23 |
+
"encoder_layers": 12,
|
24 |
+
"eos_token_id": 2,
|
25 |
+
"force_bos_token_to_be_generated": true,
|
26 |
+
"forced_bos_token_id": 0,
|
27 |
+
"forced_eos_token_id": 2,
|
28 |
+
"gradient_checkpointing": false,
|
29 |
+
"id2label": {
|
30 |
+
"0": "LABEL_0",
|
31 |
+
"1": "LABEL_1",
|
32 |
+
"2": "LABEL_2"
|
33 |
+
},
|
34 |
+
"init_std": 0.02,
|
35 |
+
"is_encoder_decoder": true,
|
36 |
+
"label2id": {
|
37 |
+
"LABEL_0": 0,
|
38 |
+
"LABEL_1": 1,
|
39 |
+
"LABEL_2": 2
|
40 |
+
},
|
41 |
+
"length_penalty": 2,
|
42 |
+
"max_length": 142,
|
43 |
+
"max_position_embeddings": 1024,
|
44 |
+
"min_length": 56,
|
45 |
+
"model_type": "bart",
|
46 |
+
"no_repeat_ngram_size": 3,
|
47 |
+
"normalize_before": false,
|
48 |
+
"num_beams": 4,
|
49 |
+
"num_hidden_layers": 12,
|
50 |
+
"output_past": true,
|
51 |
+
"pad_token_id": 1,
|
52 |
+
"prefix": " ",
|
53 |
+
"scale_embedding": false,
|
54 |
+
"task_specific_params": {
|
55 |
+
"summarization": {
|
56 |
+
"early_stopping": true,
|
57 |
+
"length_penalty": 2,
|
58 |
+
"max_length": 142,
|
59 |
+
"min_length": 56,
|
60 |
+
"no_repeat_ngram_size": 3,
|
61 |
+
"num_beams": 4
|
62 |
+
}
|
63 |
+
},
|
64 |
+
"torch_dtype": "float32",
|
65 |
+
"transformers_version": "4.39.3",
|
66 |
+
"use_cache": true,
|
67 |
+
"vocab_size": 50264
|
68 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"early_stopping": true,
|
6 |
+
"eos_token_id": 2,
|
7 |
+
"forced_bos_token_id": 0,
|
8 |
+
"forced_eos_token_id": 2,
|
9 |
+
"length_penalty": 2,
|
10 |
+
"max_length": 142,
|
11 |
+
"min_length": 56,
|
12 |
+
"no_repeat_ngram_size": 3,
|
13 |
+
"num_beams": 4,
|
14 |
+
"pad_token_id": 1,
|
15 |
+
"transformers_version": "4.39.3"
|
16 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94d77b88b53e60486fa354f908682cf96464aa7814c73cad0e32efb5fb61bdde
|
3 |
+
size 1625422896
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1001cadba2b41579a11e9ce748bb21699806d1d062b4ec3536f7355be8e482e
|
3 |
+
size 3250751759
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57d9e6df68fcc2e87120d40a7ad60c5805fe1f7dc666dc615c364a9806c90d48
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04c72869181363c7c0dcffb7a71857fd6a7c81a93e70aff2985fc26363295969
|
3 |
+
size 1064
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
trainer_state.json
ADDED
@@ -0,0 +1,721 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.20630892698727074,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 10000,
|
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,
|
13 |
+
"grad_norm": 12.003094673156738,
|
14 |
+
"learning_rate": 0.00001,
|
15 |
+
"loss": 2.4799,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0,
|
20 |
+
"grad_norm": 2.0890064239501953,
|
21 |
+
"learning_rate": 0.00002,
|
22 |
+
"loss": 0.6329,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.01,
|
27 |
+
"grad_norm": 2.033069133758545,
|
28 |
+
"learning_rate": 0.00003,
|
29 |
+
"loss": 0.5035,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.01,
|
34 |
+
"grad_norm": 2.252149820327759,
|
35 |
+
"learning_rate": 0.00004,
|
36 |
+
"loss": 0.4943,
|
37 |
+
"step": 400
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.01,
|
41 |
+
"grad_norm": 2.118387460708618,
|
42 |
+
"learning_rate": 0.00005,
|
43 |
+
"loss": 0.5105,
|
44 |
+
"step": 500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.01,
|
48 |
+
"grad_norm": 1.954121708869934,
|
49 |
+
"learning_rate": 0.000049473684210526315,
|
50 |
+
"loss": 0.5008,
|
51 |
+
"step": 600
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.01,
|
55 |
+
"grad_norm": 2.036804676055908,
|
56 |
+
"learning_rate": 0.000048947368421052635,
|
57 |
+
"loss": 0.4793,
|
58 |
+
"step": 700
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.02,
|
62 |
+
"grad_norm": 1.824407696723938,
|
63 |
+
"learning_rate": 0.00004842105263157895,
|
64 |
+
"loss": 0.469,
|
65 |
+
"step": 800
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.02,
|
69 |
+
"grad_norm": 1.724145531654358,
|
70 |
+
"learning_rate": 0.00004789473684210526,
|
71 |
+
"loss": 0.4633,
|
72 |
+
"step": 900
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.02,
|
76 |
+
"grad_norm": 1.3427892923355103,
|
77 |
+
"learning_rate": 0.00004736842105263158,
|
78 |
+
"loss": 0.4614,
|
79 |
+
"step": 1000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.02,
|
83 |
+
"grad_norm": 1.0959577560424805,
|
84 |
+
"learning_rate": 0.0000468421052631579,
|
85 |
+
"loss": 0.4605,
|
86 |
+
"step": 1100
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.02,
|
90 |
+
"grad_norm": 1.5479639768600464,
|
91 |
+
"learning_rate": 0.000046315789473684214,
|
92 |
+
"loss": 0.46,
|
93 |
+
"step": 1200
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.03,
|
97 |
+
"grad_norm": 1.535975456237793,
|
98 |
+
"learning_rate": 0.000045789473684210527,
|
99 |
+
"loss": 0.4252,
|
100 |
+
"step": 1300
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.03,
|
104 |
+
"grad_norm": 1.5321663618087769,
|
105 |
+
"learning_rate": 0.000045263157894736846,
|
106 |
+
"loss": 0.4369,
|
107 |
+
"step": 1400
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.03,
|
111 |
+
"grad_norm": 1.5459933280944824,
|
112 |
+
"learning_rate": 0.00004473684210526316,
|
113 |
+
"loss": 0.4276,
|
114 |
+
"step": 1500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.03,
|
118 |
+
"grad_norm": 1.7711249589920044,
|
119 |
+
"learning_rate": 0.00004421052631578947,
|
120 |
+
"loss": 0.4474,
|
121 |
+
"step": 1600
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.04,
|
125 |
+
"grad_norm": 1.376570701599121,
|
126 |
+
"learning_rate": 0.00004368421052631579,
|
127 |
+
"loss": 0.4064,
|
128 |
+
"step": 1700
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.04,
|
132 |
+
"grad_norm": 1.74457585811615,
|
133 |
+
"learning_rate": 0.000043157894736842105,
|
134 |
+
"loss": 0.4093,
|
135 |
+
"step": 1800
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.04,
|
139 |
+
"grad_norm": 1.4628654718399048,
|
140 |
+
"learning_rate": 0.000042631578947368425,
|
141 |
+
"loss": 0.4236,
|
142 |
+
"step": 1900
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.04,
|
146 |
+
"grad_norm": 1.0637551546096802,
|
147 |
+
"learning_rate": 0.00004210526315789474,
|
148 |
+
"loss": 0.4137,
|
149 |
+
"step": 2000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.04,
|
153 |
+
"grad_norm": 1.385728359222412,
|
154 |
+
"learning_rate": 0.00004157894736842106,
|
155 |
+
"loss": 0.4071,
|
156 |
+
"step": 2100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.05,
|
160 |
+
"grad_norm": 1.3536651134490967,
|
161 |
+
"learning_rate": 0.00004105263157894737,
|
162 |
+
"loss": 0.4215,
|
163 |
+
"step": 2200
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.05,
|
167 |
+
"grad_norm": 1.5586481094360352,
|
168 |
+
"learning_rate": 0.000040526315789473684,
|
169 |
+
"loss": 0.4041,
|
170 |
+
"step": 2300
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.05,
|
174 |
+
"grad_norm": 1.0527902841567993,
|
175 |
+
"learning_rate": 0.00004,
|
176 |
+
"loss": 0.3984,
|
177 |
+
"step": 2400
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.05,
|
181 |
+
"grad_norm": 1.5508724451065063,
|
182 |
+
"learning_rate": 0.000039473684210526316,
|
183 |
+
"loss": 0.406,
|
184 |
+
"step": 2500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.05,
|
188 |
+
"grad_norm": 1.7268626689910889,
|
189 |
+
"learning_rate": 0.00003894736842105263,
|
190 |
+
"loss": 0.3978,
|
191 |
+
"step": 2600
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.06,
|
195 |
+
"grad_norm": 1.259959101676941,
|
196 |
+
"learning_rate": 0.00003842105263157895,
|
197 |
+
"loss": 0.4111,
|
198 |
+
"step": 2700
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.06,
|
202 |
+
"grad_norm": 1.5187910795211792,
|
203 |
+
"learning_rate": 0.00003789473684210527,
|
204 |
+
"loss": 0.3862,
|
205 |
+
"step": 2800
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.06,
|
209 |
+
"grad_norm": 1.4480005502700806,
|
210 |
+
"learning_rate": 0.00003736842105263158,
|
211 |
+
"loss": 0.4021,
|
212 |
+
"step": 2900
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.06,
|
216 |
+
"grad_norm": 1.2096664905548096,
|
217 |
+
"learning_rate": 0.000036842105263157895,
|
218 |
+
"loss": 0.4092,
|
219 |
+
"step": 3000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.06,
|
223 |
+
"grad_norm": 1.0258468389511108,
|
224 |
+
"learning_rate": 0.000036315789473684214,
|
225 |
+
"loss": 0.3829,
|
226 |
+
"step": 3100
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.07,
|
230 |
+
"grad_norm": 1.336549162864685,
|
231 |
+
"learning_rate": 0.00003578947368421053,
|
232 |
+
"loss": 0.4082,
|
233 |
+
"step": 3200
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.07,
|
237 |
+
"grad_norm": 1.1610171794891357,
|
238 |
+
"learning_rate": 0.00003526315789473684,
|
239 |
+
"loss": 0.4216,
|
240 |
+
"step": 3300
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.07,
|
244 |
+
"grad_norm": 1.1225395202636719,
|
245 |
+
"learning_rate": 0.00003473684210526316,
|
246 |
+
"loss": 0.3866,
|
247 |
+
"step": 3400
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.07,
|
251 |
+
"grad_norm": 1.2079445123672485,
|
252 |
+
"learning_rate": 0.00003421052631578947,
|
253 |
+
"loss": 0.3827,
|
254 |
+
"step": 3500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.07,
|
258 |
+
"grad_norm": 0.8150144815444946,
|
259 |
+
"learning_rate": 0.00003368421052631579,
|
260 |
+
"loss": 0.3833,
|
261 |
+
"step": 3600
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.08,
|
265 |
+
"grad_norm": 1.1681067943572998,
|
266 |
+
"learning_rate": 0.000033157894736842106,
|
267 |
+
"loss": 0.3953,
|
268 |
+
"step": 3700
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.08,
|
272 |
+
"grad_norm": 1.1494988203048706,
|
273 |
+
"learning_rate": 0.000032631578947368426,
|
274 |
+
"loss": 0.3785,
|
275 |
+
"step": 3800
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.08,
|
279 |
+
"grad_norm": 0.8699579238891602,
|
280 |
+
"learning_rate": 0.00003210526315789474,
|
281 |
+
"loss": 0.3802,
|
282 |
+
"step": 3900
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.08,
|
286 |
+
"grad_norm": 1.560229778289795,
|
287 |
+
"learning_rate": 0.00003157894736842105,
|
288 |
+
"loss": 0.3837,
|
289 |
+
"step": 4000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.08,
|
293 |
+
"grad_norm": 1.1917518377304077,
|
294 |
+
"learning_rate": 0.00003105263157894737,
|
295 |
+
"loss": 0.3775,
|
296 |
+
"step": 4100
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.09,
|
300 |
+
"grad_norm": 1.050404667854309,
|
301 |
+
"learning_rate": 0.000030526315789473684,
|
302 |
+
"loss": 0.3781,
|
303 |
+
"step": 4200
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.09,
|
307 |
+
"grad_norm": 0.8547882437705994,
|
308 |
+
"learning_rate": 0.00003,
|
309 |
+
"loss": 0.3629,
|
310 |
+
"step": 4300
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.09,
|
314 |
+
"grad_norm": 1.0195717811584473,
|
315 |
+
"learning_rate": 0.000029473684210526314,
|
316 |
+
"loss": 0.3644,
|
317 |
+
"step": 4400
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.09,
|
321 |
+
"grad_norm": 1.0551220178604126,
|
322 |
+
"learning_rate": 0.000028947368421052634,
|
323 |
+
"loss": 0.3774,
|
324 |
+
"step": 4500
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.09,
|
328 |
+
"grad_norm": 0.9689894318580627,
|
329 |
+
"learning_rate": 0.00002842105263157895,
|
330 |
+
"loss": 0.3384,
|
331 |
+
"step": 4600
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.1,
|
335 |
+
"grad_norm": 1.3785911798477173,
|
336 |
+
"learning_rate": 0.000027894736842105263,
|
337 |
+
"loss": 0.3725,
|
338 |
+
"step": 4700
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.1,
|
342 |
+
"grad_norm": 1.1647924184799194,
|
343 |
+
"learning_rate": 0.000027368421052631583,
|
344 |
+
"loss": 0.3716,
|
345 |
+
"step": 4800
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.1,
|
349 |
+
"grad_norm": 1.0317350625991821,
|
350 |
+
"learning_rate": 0.000026842105263157896,
|
351 |
+
"loss": 0.3454,
|
352 |
+
"step": 4900
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.1,
|
356 |
+
"grad_norm": 1.2156306505203247,
|
357 |
+
"learning_rate": 0.000026315789473684212,
|
358 |
+
"loss": 0.3414,
|
359 |
+
"step": 5000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.11,
|
363 |
+
"grad_norm": 1.0330926179885864,
|
364 |
+
"learning_rate": 0.00002578947368421053,
|
365 |
+
"loss": 0.3658,
|
366 |
+
"step": 5100
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.11,
|
370 |
+
"grad_norm": 1.1999331712722778,
|
371 |
+
"learning_rate": 0.000025263157894736845,
|
372 |
+
"loss": 0.3659,
|
373 |
+
"step": 5200
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.11,
|
377 |
+
"grad_norm": 0.8645588159561157,
|
378 |
+
"learning_rate": 0.000024736842105263158,
|
379 |
+
"loss": 0.3567,
|
380 |
+
"step": 5300
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.11,
|
384 |
+
"grad_norm": 1.3966509103775024,
|
385 |
+
"learning_rate": 0.000024210526315789474,
|
386 |
+
"loss": 0.3593,
|
387 |
+
"step": 5400
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.11,
|
391 |
+
"grad_norm": 0.9758176207542419,
|
392 |
+
"learning_rate": 0.00002368421052631579,
|
393 |
+
"loss": 0.3491,
|
394 |
+
"step": 5500
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.12,
|
398 |
+
"grad_norm": 1.0079020261764526,
|
399 |
+
"learning_rate": 0.000023157894736842107,
|
400 |
+
"loss": 0.3403,
|
401 |
+
"step": 5600
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.12,
|
405 |
+
"grad_norm": 1.0078275203704834,
|
406 |
+
"learning_rate": 0.000022631578947368423,
|
407 |
+
"loss": 0.3396,
|
408 |
+
"step": 5700
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.12,
|
412 |
+
"grad_norm": 1.2329459190368652,
|
413 |
+
"learning_rate": 0.000022105263157894736,
|
414 |
+
"loss": 0.3323,
|
415 |
+
"step": 5800
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.12,
|
419 |
+
"grad_norm": 1.5663444995880127,
|
420 |
+
"learning_rate": 0.000021578947368421053,
|
421 |
+
"loss": 0.332,
|
422 |
+
"step": 5900
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.12,
|
426 |
+
"grad_norm": 1.104218602180481,
|
427 |
+
"learning_rate": 0.00002105263157894737,
|
428 |
+
"loss": 0.346,
|
429 |
+
"step": 6000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.13,
|
433 |
+
"grad_norm": 1.1730228662490845,
|
434 |
+
"learning_rate": 0.000020526315789473685,
|
435 |
+
"loss": 0.3485,
|
436 |
+
"step": 6100
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.13,
|
440 |
+
"grad_norm": 1.2409980297088623,
|
441 |
+
"learning_rate": 0.00002,
|
442 |
+
"loss": 0.3539,
|
443 |
+
"step": 6200
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.13,
|
447 |
+
"grad_norm": 0.933708906173706,
|
448 |
+
"learning_rate": 0.000019473684210526315,
|
449 |
+
"loss": 0.3177,
|
450 |
+
"step": 6300
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.13,
|
454 |
+
"grad_norm": 1.0058486461639404,
|
455 |
+
"learning_rate": 0.000018947368421052634,
|
456 |
+
"loss": 0.3394,
|
457 |
+
"step": 6400
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.13,
|
461 |
+
"grad_norm": 1.2994540929794312,
|
462 |
+
"learning_rate": 0.000018421052631578947,
|
463 |
+
"loss": 0.3447,
|
464 |
+
"step": 6500
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.14,
|
468 |
+
"grad_norm": 1.1113885641098022,
|
469 |
+
"learning_rate": 0.000017894736842105264,
|
470 |
+
"loss": 0.3572,
|
471 |
+
"step": 6600
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.14,
|
475 |
+
"grad_norm": 1.1501245498657227,
|
476 |
+
"learning_rate": 0.00001736842105263158,
|
477 |
+
"loss": 0.3468,
|
478 |
+
"step": 6700
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.14,
|
482 |
+
"grad_norm": 1.5754578113555908,
|
483 |
+
"learning_rate": 0.000016842105263157896,
|
484 |
+
"loss": 0.3461,
|
485 |
+
"step": 6800
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.14,
|
489 |
+
"grad_norm": 1.214449167251587,
|
490 |
+
"learning_rate": 0.000016315789473684213,
|
491 |
+
"loss": 0.3463,
|
492 |
+
"step": 6900
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.14,
|
496 |
+
"grad_norm": 1.38958740234375,
|
497 |
+
"learning_rate": 0.000015789473684210526,
|
498 |
+
"loss": 0.3432,
|
499 |
+
"step": 7000
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.15,
|
503 |
+
"grad_norm": 1.1833761930465698,
|
504 |
+
"learning_rate": 0.000015263157894736842,
|
505 |
+
"loss": 0.336,
|
506 |
+
"step": 7100
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.15,
|
510 |
+
"grad_norm": 1.2316564321517944,
|
511 |
+
"learning_rate": 0.000014736842105263157,
|
512 |
+
"loss": 0.3266,
|
513 |
+
"step": 7200
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.15,
|
517 |
+
"grad_norm": 1.5909250974655151,
|
518 |
+
"learning_rate": 0.000014210526315789475,
|
519 |
+
"loss": 0.3354,
|
520 |
+
"step": 7300
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.15,
|
524 |
+
"grad_norm": 1.1195193529129028,
|
525 |
+
"learning_rate": 0.000013684210526315791,
|
526 |
+
"loss": 0.3388,
|
527 |
+
"step": 7400
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.15,
|
531 |
+
"grad_norm": 1.1586064100265503,
|
532 |
+
"learning_rate": 0.000013157894736842106,
|
533 |
+
"loss": 0.3413,
|
534 |
+
"step": 7500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.16,
|
538 |
+
"grad_norm": 0.935364305973053,
|
539 |
+
"learning_rate": 0.000012631578947368422,
|
540 |
+
"loss": 0.3359,
|
541 |
+
"step": 7600
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.16,
|
545 |
+
"grad_norm": 1.3456859588623047,
|
546 |
+
"learning_rate": 0.000012105263157894737,
|
547 |
+
"loss": 0.3328,
|
548 |
+
"step": 7700
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.16,
|
552 |
+
"grad_norm": 1.5139777660369873,
|
553 |
+
"learning_rate": 0.000011578947368421053,
|
554 |
+
"loss": 0.3499,
|
555 |
+
"step": 7800
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.16,
|
559 |
+
"grad_norm": 1.0874484777450562,
|
560 |
+
"learning_rate": 0.000011052631578947368,
|
561 |
+
"loss": 0.3123,
|
562 |
+
"step": 7900
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.17,
|
566 |
+
"grad_norm": 0.9059338569641113,
|
567 |
+
"learning_rate": 0.000010526315789473684,
|
568 |
+
"loss": 0.3305,
|
569 |
+
"step": 8000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.17,
|
573 |
+
"grad_norm": 1.1520755290985107,
|
574 |
+
"learning_rate": 0.00001,
|
575 |
+
"loss": 0.3235,
|
576 |
+
"step": 8100
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.17,
|
580 |
+
"grad_norm": 1.2957168817520142,
|
581 |
+
"learning_rate": 0.000009473684210526317,
|
582 |
+
"loss": 0.3204,
|
583 |
+
"step": 8200
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.17,
|
587 |
+
"grad_norm": 1.0766379833221436,
|
588 |
+
"learning_rate": 0.000008947368421052632,
|
589 |
+
"loss": 0.3239,
|
590 |
+
"step": 8300
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.17,
|
594 |
+
"grad_norm": 1.1667858362197876,
|
595 |
+
"learning_rate": 0.000008421052631578948,
|
596 |
+
"loss": 0.3183,
|
597 |
+
"step": 8400
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.18,
|
601 |
+
"grad_norm": 1.364989161491394,
|
602 |
+
"learning_rate": 0.000007894736842105263,
|
603 |
+
"loss": 0.3326,
|
604 |
+
"step": 8500
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.18,
|
608 |
+
"grad_norm": 1.2203367948532104,
|
609 |
+
"learning_rate": 0.0000073684210526315784,
|
610 |
+
"loss": 0.3205,
|
611 |
+
"step": 8600
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.18,
|
615 |
+
"grad_norm": 1.254922866821289,
|
616 |
+
"learning_rate": 0.000006842105263157896,
|
617 |
+
"loss": 0.3448,
|
618 |
+
"step": 8700
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.18,
|
622 |
+
"grad_norm": 1.471166729927063,
|
623 |
+
"learning_rate": 0.000006315789473684211,
|
624 |
+
"loss": 0.3307,
|
625 |
+
"step": 8800
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.18,
|
629 |
+
"grad_norm": 1.1350233554840088,
|
630 |
+
"learning_rate": 0.000005789473684210527,
|
631 |
+
"loss": 0.3174,
|
632 |
+
"step": 8900
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.19,
|
636 |
+
"grad_norm": 0.953658401966095,
|
637 |
+
"learning_rate": 0.000005263157894736842,
|
638 |
+
"loss": 0.3327,
|
639 |
+
"step": 9000
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.19,
|
643 |
+
"grad_norm": 1.2155749797821045,
|
644 |
+
"learning_rate": 0.000004736842105263159,
|
645 |
+
"loss": 0.3251,
|
646 |
+
"step": 9100
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.19,
|
650 |
+
"grad_norm": 1.106632947921753,
|
651 |
+
"learning_rate": 0.000004210526315789474,
|
652 |
+
"loss": 0.3011,
|
653 |
+
"step": 9200
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.19,
|
657 |
+
"grad_norm": 1.2169803380966187,
|
658 |
+
"learning_rate": 0.0000036842105263157892,
|
659 |
+
"loss": 0.3331,
|
660 |
+
"step": 9300
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.19,
|
664 |
+
"grad_norm": 0.7549806237220764,
|
665 |
+
"learning_rate": 0.0000031578947368421056,
|
666 |
+
"loss": 0.319,
|
667 |
+
"step": 9400
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.2,
|
671 |
+
"grad_norm": 1.2598366737365723,
|
672 |
+
"learning_rate": 0.000002631578947368421,
|
673 |
+
"loss": 0.3201,
|
674 |
+
"step": 9500
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.2,
|
678 |
+
"grad_norm": 0.991303563117981,
|
679 |
+
"learning_rate": 0.000002105263157894737,
|
680 |
+
"loss": 0.3144,
|
681 |
+
"step": 9600
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.2,
|
685 |
+
"grad_norm": 1.120094656944275,
|
686 |
+
"learning_rate": 0.0000015789473684210528,
|
687 |
+
"loss": 0.2997,
|
688 |
+
"step": 9700
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.2,
|
692 |
+
"grad_norm": 0.9906071424484253,
|
693 |
+
"learning_rate": 0.0000010526315789473685,
|
694 |
+
"loss": 0.3244,
|
695 |
+
"step": 9800
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.2,
|
699 |
+
"grad_norm": 1.083082675933838,
|
700 |
+
"learning_rate": 5.263157894736843e-7,
|
701 |
+
"loss": 0.3382,
|
702 |
+
"step": 9900
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.21,
|
706 |
+
"grad_norm": 1.6393320560455322,
|
707 |
+
"learning_rate": 0,
|
708 |
+
"loss": 0.3064,
|
709 |
+
"step": 10000
|
710 |
+
}
|
711 |
+
],
|
712 |
+
"logging_steps": 100,
|
713 |
+
"max_steps": 10000,
|
714 |
+
"num_input_tokens_seen": 0,
|
715 |
+
"num_train_epochs": 1,
|
716 |
+
"save_steps": 5000,
|
717 |
+
"total_flos": 21671046021120000,
|
718 |
+
"train_batch_size": 4,
|
719 |
+
"trial_name": null,
|
720 |
+
"trial_params": null
|
721 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2cff83c64cd5abfb95d4aaafc2521a5b64e0dce5300f466e22dbf14f6ab5c25
|
3 |
+
size 4920
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|