Upload 18 files
Browse files- config.json +32 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +44 -0
- trainer_state.json +383 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2LMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"pad_token_id": 3,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_embd": 384,
|
15 |
+
"n_head": 12,
|
16 |
+
"n_inner": null,
|
17 |
+
"n_layer": 12,
|
18 |
+
"n_positions": 256,
|
19 |
+
"reorder_and_upcast_attn": false,
|
20 |
+
"resid_pdrop": 0.1,
|
21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
22 |
+
"scale_attn_weights": true,
|
23 |
+
"summary_activation": null,
|
24 |
+
"summary_first_dropout": 0.1,
|
25 |
+
"summary_proj_to_labels": true,
|
26 |
+
"summary_type": "cls_index",
|
27 |
+
"summary_use_proj": true,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.43.4",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 12000
|
32 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"eos_token_id": 3,
|
5 |
+
"transformers_version": "4.43.4"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6eb9211d1528533067c2d7597847c0788e5578e0bf49828c0d794631825749c
|
3 |
+
size 104017304
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:851adf4eaca9b5c08a3bbb12ccdcee2cc7d85a060e81d8e6ea761061a392706e
|
3 |
+
size 208128954
|
rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81200223bf2c0d600698970a7c2ba66b5b0790b87726e5859fceea4f062c23f0
|
3 |
+
size 15984
|
rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43a94eca64adf682e6c4afdff5a761218f2ad867734f252ae336a3322875bf3a
|
3 |
+
size 15984
|
rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8baf5eb40487de162d10fc74bfdac50b5d4102978b796d3cbdaf051869514398
|
3 |
+
size 15984
|
rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75707fde14da5c30bdf811143e8c5947e66120b7bfb5905ca97ae767c0edea1a
|
3 |
+
size 15984
|
rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:194c2c331d205afd9dd93d5ae00960df17a31763d26e08bad72c6c0628c815da
|
3 |
+
size 15984
|
rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0354cf0563ccef647bf17d17da90532c48be4003332acea51bf66ac168630c8
|
3 |
+
size 15984
|
rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6831753ddb3c34fda85ead6b6ffa64bcbce1aa2bb0154b33350d078b298b59f2
|
3 |
+
size 15984
|
rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47d2bcbd3fa196b84438a458da4848bbe2b3085a365e7e96466ddce11dcc6378
|
3 |
+
size 15984
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9decee5f0aebd2c42dfa45be0e9fcf5bbb3d4065d64200fdf0874156e057a2dd
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|bos|>",
|
3 |
+
"eos_token": "<|eos|>",
|
4 |
+
"mask_token": "<|mask|>",
|
5 |
+
"pad_token": "<|pad|>"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<|mask|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<|bos|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "<|eos|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<|pad|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"bos_token": "<|bos|>",
|
37 |
+
"clean_up_tokenization_spaces": true,
|
38 |
+
"eos_token": "<|eos|>",
|
39 |
+
"mask_token": "<|mask|>",
|
40 |
+
"model_max_length": 256,
|
41 |
+
"pad_token": "<|pad|>",
|
42 |
+
"return_tensors": "pt",
|
43 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
44 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,383 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.602890571231933,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 25000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.1720578114246387,
|
13 |
+
"grad_norm": 2.9087114334106445,
|
14 |
+
"learning_rate": 2.867630190410645e-06,
|
15 |
+
"loss": 8.3862,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.3441156228492774,
|
20 |
+
"grad_norm": 2.4263219833374023,
|
21 |
+
"learning_rate": 5.73526038082129e-06,
|
22 |
+
"loss": 6.9689,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.516173434273916,
|
27 |
+
"grad_norm": 4.725559234619141,
|
28 |
+
"learning_rate": 8.602890571231935e-06,
|
29 |
+
"loss": 5.7891,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.6882312456985548,
|
34 |
+
"grad_norm": 3.8100438117980957,
|
35 |
+
"learning_rate": 1.147052076164258e-05,
|
36 |
+
"loss": 4.8611,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.8602890571231934,
|
41 |
+
"grad_norm": 2.8300278186798096,
|
42 |
+
"learning_rate": 1.4338150952053223e-05,
|
43 |
+
"loss": 4.2645,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.032346868547832,
|
48 |
+
"grad_norm": 3.759568929672241,
|
49 |
+
"learning_rate": 1.720578114246387e-05,
|
50 |
+
"loss": 3.8533,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.2044046799724708,
|
55 |
+
"grad_norm": 3.1716251373291016,
|
56 |
+
"learning_rate": 2.0073411332874516e-05,
|
57 |
+
"loss": 3.5417,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.3764624913971093,
|
62 |
+
"grad_norm": 3.578864812850952,
|
63 |
+
"learning_rate": 2.294104152328516e-05,
|
64 |
+
"loss": 3.2905,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.548520302821748,
|
69 |
+
"grad_norm": 2.953669309616089,
|
70 |
+
"learning_rate": 2.5808671713695802e-05,
|
71 |
+
"loss": 3.0965,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.7205781142463867,
|
76 |
+
"grad_norm": 3.457939863204956,
|
77 |
+
"learning_rate": 2.8676301904106445e-05,
|
78 |
+
"loss": 2.9353,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.8926359256710255,
|
83 |
+
"grad_norm": 2.893206834793091,
|
84 |
+
"learning_rate": 3.1543932094517095e-05,
|
85 |
+
"loss": 2.8001,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.064693737095664,
|
90 |
+
"grad_norm": 2.9178900718688965,
|
91 |
+
"learning_rate": 3.441156228492774e-05,
|
92 |
+
"loss": 2.6832,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.236751548520303,
|
97 |
+
"grad_norm": 2.7625951766967773,
|
98 |
+
"learning_rate": 3.7273457214957565e-05,
|
99 |
+
"loss": 2.5764,
|
100 |
+
"step": 6500
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 2.4088093599449416,
|
104 |
+
"grad_norm": 2.936638116836548,
|
105 |
+
"learning_rate": 4.01410874053682e-05,
|
106 |
+
"loss": 2.4878,
|
107 |
+
"step": 7000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 2.5808671713695803,
|
111 |
+
"grad_norm": 2.8190789222717285,
|
112 |
+
"learning_rate": 4.300871759577885e-05,
|
113 |
+
"loss": 2.4027,
|
114 |
+
"step": 7500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 2.7529249827942186,
|
118 |
+
"grad_norm": 2.407775402069092,
|
119 |
+
"learning_rate": 4.5876347786189495e-05,
|
120 |
+
"loss": 2.3358,
|
121 |
+
"step": 8000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 2.9249827942188578,
|
125 |
+
"grad_norm": 2.336435317993164,
|
126 |
+
"learning_rate": 4.8738242716219315e-05,
|
127 |
+
"loss": 2.2753,
|
128 |
+
"step": 8500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 3.097040605643496,
|
132 |
+
"grad_norm": 2.211622953414917,
|
133 |
+
"learning_rate": 5.160587290662996e-05,
|
134 |
+
"loss": 2.2115,
|
135 |
+
"step": 9000
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 3.2690984170681348,
|
139 |
+
"grad_norm": 2.3094568252563477,
|
140 |
+
"learning_rate": 5.4473503097040615e-05,
|
141 |
+
"loss": 2.1567,
|
142 |
+
"step": 9500
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 3.4411562284927735,
|
146 |
+
"grad_norm": 2.2486841678619385,
|
147 |
+
"learning_rate": 5.734113328745125e-05,
|
148 |
+
"loss": 2.1201,
|
149 |
+
"step": 10000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 3.613214039917412,
|
153 |
+
"grad_norm": 2.023249864578247,
|
154 |
+
"learning_rate": 6.020302821748107e-05,
|
155 |
+
"loss": 2.0788,
|
156 |
+
"step": 10500
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 3.785271851342051,
|
160 |
+
"grad_norm": 2.1235194206237793,
|
161 |
+
"learning_rate": 6.307065840789173e-05,
|
162 |
+
"loss": 2.0441,
|
163 |
+
"step": 11000
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 3.9573296627666896,
|
167 |
+
"grad_norm": 2.0521788597106934,
|
168 |
+
"learning_rate": 6.593828859830237e-05,
|
169 |
+
"loss": 2.0071,
|
170 |
+
"step": 11500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 4.129387474191328,
|
174 |
+
"grad_norm": 2.0152077674865723,
|
175 |
+
"learning_rate": 6.880591878871302e-05,
|
176 |
+
"loss": 1.9692,
|
177 |
+
"step": 12000
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 4.301445285615967,
|
181 |
+
"grad_norm": 1.9169940948486328,
|
182 |
+
"learning_rate": 7.167354897912365e-05,
|
183 |
+
"loss": 1.9382,
|
184 |
+
"step": 12500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 4.473503097040606,
|
188 |
+
"grad_norm": 1.7628319263458252,
|
189 |
+
"learning_rate": 7.45411791695343e-05,
|
190 |
+
"loss": 1.9156,
|
191 |
+
"step": 13000
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 4.645560908465244,
|
195 |
+
"grad_norm": 1.7819803953170776,
|
196 |
+
"learning_rate": 7.740880935994495e-05,
|
197 |
+
"loss": 1.8907,
|
198 |
+
"step": 13500
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 4.817618719889883,
|
202 |
+
"grad_norm": 1.6823229789733887,
|
203 |
+
"learning_rate": 8.027643955035559e-05,
|
204 |
+
"loss": 1.8663,
|
205 |
+
"step": 14000
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 4.9896765313145215,
|
209 |
+
"grad_norm": 1.6162245273590088,
|
210 |
+
"learning_rate": 8.313833448038542e-05,
|
211 |
+
"loss": 1.8432,
|
212 |
+
"step": 14500
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 5.161734342739161,
|
216 |
+
"grad_norm": 1.6801457405090332,
|
217 |
+
"learning_rate": 8.600596467079606e-05,
|
218 |
+
"loss": 1.8093,
|
219 |
+
"step": 15000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 5.333792154163799,
|
223 |
+
"grad_norm": 1.5677675008773804,
|
224 |
+
"learning_rate": 8.88735948612067e-05,
|
225 |
+
"loss": 1.7915,
|
226 |
+
"step": 15500
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 5.505849965588438,
|
230 |
+
"grad_norm": 1.5037736892700195,
|
231 |
+
"learning_rate": 9.174122505161736e-05,
|
232 |
+
"loss": 1.7751,
|
233 |
+
"step": 16000
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 5.677907777013076,
|
237 |
+
"grad_norm": 1.515109658241272,
|
238 |
+
"learning_rate": 9.460311998164716e-05,
|
239 |
+
"loss": 1.7607,
|
240 |
+
"step": 16500
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 5.8499655884377155,
|
244 |
+
"grad_norm": 1.44197678565979,
|
245 |
+
"learning_rate": 9.747075017205781e-05,
|
246 |
+
"loss": 1.7413,
|
247 |
+
"step": 17000
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 6.022023399862354,
|
251 |
+
"grad_norm": 1.3949217796325684,
|
252 |
+
"learning_rate": 9.99994810855854e-05,
|
253 |
+
"loss": 1.7247,
|
254 |
+
"step": 17500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 6.194081211286992,
|
258 |
+
"grad_norm": 1.3660074472427368,
|
259 |
+
"learning_rate": 9.995342545257314e-05,
|
260 |
+
"loss": 1.6924,
|
261 |
+
"step": 18000
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 6.366139022711631,
|
265 |
+
"grad_norm": 1.3406497240066528,
|
266 |
+
"learning_rate": 9.983322835071715e-05,
|
267 |
+
"loss": 1.6832,
|
268 |
+
"step": 18500
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 6.5381968341362695,
|
272 |
+
"grad_norm": 1.3978294134140015,
|
273 |
+
"learning_rate": 9.963858724454791e-05,
|
274 |
+
"loss": 1.667,
|
275 |
+
"step": 19000
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 6.710254645560909,
|
279 |
+
"grad_norm": 1.2904192209243774,
|
280 |
+
"learning_rate": 9.936995871142264e-05,
|
281 |
+
"loss": 1.6525,
|
282 |
+
"step": 19500
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 6.882312456985547,
|
286 |
+
"grad_norm": 1.2701600790023804,
|
287 |
+
"learning_rate": 9.90277431481914e-05,
|
288 |
+
"loss": 1.6389,
|
289 |
+
"step": 20000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 7.054370268410186,
|
293 |
+
"grad_norm": 1.305159568786621,
|
294 |
+
"learning_rate": 9.861245063482206e-05,
|
295 |
+
"loss": 1.6201,
|
296 |
+
"step": 20500
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 7.226428079834824,
|
300 |
+
"grad_norm": 1.2807930707931519,
|
301 |
+
"learning_rate": 9.812574752273107e-05,
|
302 |
+
"loss": 1.5973,
|
303 |
+
"step": 21000
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 7.3984858912594635,
|
307 |
+
"grad_norm": 1.1819531917572021,
|
308 |
+
"learning_rate": 9.756640878275985e-05,
|
309 |
+
"loss": 1.589,
|
310 |
+
"step": 21500
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 7.570543702684102,
|
314 |
+
"grad_norm": 1.2513145208358765,
|
315 |
+
"learning_rate": 9.693617124427856e-05,
|
316 |
+
"loss": 1.574,
|
317 |
+
"step": 22000
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 7.74260151410874,
|
321 |
+
"grad_norm": 1.2013038396835327,
|
322 |
+
"learning_rate": 9.623597429046535e-05,
|
323 |
+
"loss": 1.5713,
|
324 |
+
"step": 22500
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 7.914659325533379,
|
328 |
+
"grad_norm": 1.1914407014846802,
|
329 |
+
"learning_rate": 9.546846783889485e-05,
|
330 |
+
"loss": 1.5583,
|
331 |
+
"step": 23000
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 8.086717136958018,
|
335 |
+
"grad_norm": 1.1989445686340332,
|
336 |
+
"learning_rate": 9.463172007988832e-05,
|
337 |
+
"loss": 1.5376,
|
338 |
+
"step": 23500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 8.258774948382657,
|
342 |
+
"grad_norm": 1.1866331100463867,
|
343 |
+
"learning_rate": 9.372844774166556e-05,
|
344 |
+
"loss": 1.5211,
|
345 |
+
"step": 24000
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 8.430832759807295,
|
349 |
+
"grad_norm": 1.1914212703704834,
|
350 |
+
"learning_rate": 9.275999717189387e-05,
|
351 |
+
"loss": 1.5163,
|
352 |
+
"step": 24500
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 8.602890571231933,
|
356 |
+
"grad_norm": 1.153332233428955,
|
357 |
+
"learning_rate": 9.172993883873278e-05,
|
358 |
+
"loss": 1.5072,
|
359 |
+
"step": 25000
|
360 |
+
}
|
361 |
+
],
|
362 |
+
"logging_steps": 500,
|
363 |
+
"max_steps": 58120,
|
364 |
+
"num_input_tokens_seen": 0,
|
365 |
+
"num_train_epochs": 20,
|
366 |
+
"save_steps": 1000,
|
367 |
+
"stateful_callbacks": {
|
368 |
+
"TrainerControl": {
|
369 |
+
"args": {
|
370 |
+
"should_epoch_stop": false,
|
371 |
+
"should_evaluate": false,
|
372 |
+
"should_log": false,
|
373 |
+
"should_save": true,
|
374 |
+
"should_training_stop": false
|
375 |
+
},
|
376 |
+
"attributes": {}
|
377 |
+
}
|
378 |
+
},
|
379 |
+
"total_flos": 1.046659236626432e+17,
|
380 |
+
"train_batch_size": 16,
|
381 |
+
"trial_name": null,
|
382 |
+
"trial_params": null
|
383 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0beaf9396837dd4e0bf474e57cae915ffc0cb5b808db764847cea7f33717b444
|
3 |
+
size 5304
|