Training in progress, step 2500, checkpoint
Browse files- checkpoint-2500/config.json +30 -0
- checkpoint-2500/generation_config.json +6 -0
- checkpoint-2500/model.safetensors +3 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/rng_state.pth +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/special_tokens_map.json +24 -0
- checkpoint-2500/tokenizer.json +96 -0
- checkpoint-2500/tokenizer_config.json +38 -0
- checkpoint-2500/trainer_state.json +208 -0
- checkpoint-2500/training_args.bin +3 -0
checkpoint-2500/config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "EleutherAI/pythia-160m",
|
3 |
+
"architectures": [
|
4 |
+
"GPTNeoXForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": true,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": 0.1,
|
10 |
+
"eos_token_id": 0,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout": 0.0,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 2048,
|
18 |
+
"model_type": "gpt_neox",
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_layers": 12,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rotary_emb_base": 10000,
|
23 |
+
"rotary_pct": 0.25,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.42.3",
|
27 |
+
"use_cache": true,
|
28 |
+
"use_parallel_residual": true,
|
29 |
+
"vocab_size": 8
|
30 |
+
}
|
checkpoint-2500/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.42.3"
|
6 |
+
}
|
checkpoint-2500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b94258c447e746acbb0c6a09966ea472ec49ea7325f437afd98f3f012c7477c2
|
3 |
+
size 340289960
|
checkpoint-2500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad1b9a61cebfb5229ffcf52f6f0f4b0c6dd22d06a5526be7394b27100bca05e9
|
3 |
+
size 680670138
|
checkpoint-2500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:835f869ea325fd6edf27b48b589309fb66641cb92b45f2fc13d1bb6e8814106c
|
3 |
+
size 14244
|
checkpoint-2500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4060b1c2ecc534ce7f5b6b3c2e8af6e90775b896d53d22b35807710eb2021f60
|
3 |
+
size 1064
|
checkpoint-2500/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|beginoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|unknown|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-2500/tokenizer.json
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "<|beginoftext|>",
|
9 |
+
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"special": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 1,
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"special": true
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"id": 2,
|
26 |
+
"content": "<|unknown|>",
|
27 |
+
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"special": true
|
32 |
+
}
|
33 |
+
],
|
34 |
+
"normalizer": {
|
35 |
+
"type": "NFC"
|
36 |
+
},
|
37 |
+
"pre_tokenizer": {
|
38 |
+
"type": "ByteLevel",
|
39 |
+
"add_prefix_space": false,
|
40 |
+
"trim_offsets": true,
|
41 |
+
"use_regex": true
|
42 |
+
},
|
43 |
+
"post_processor": {
|
44 |
+
"type": "TemplateProcessing",
|
45 |
+
"single": [
|
46 |
+
{
|
47 |
+
"Sequence": {
|
48 |
+
"id": "A",
|
49 |
+
"type_id": 0
|
50 |
+
}
|
51 |
+
}
|
52 |
+
],
|
53 |
+
"pair": [
|
54 |
+
{
|
55 |
+
"Sequence": {
|
56 |
+
"id": "A",
|
57 |
+
"type_id": 0
|
58 |
+
}
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"Sequence": {
|
62 |
+
"id": "B",
|
63 |
+
"type_id": 1
|
64 |
+
}
|
65 |
+
}
|
66 |
+
],
|
67 |
+
"special_tokens": {}
|
68 |
+
},
|
69 |
+
"decoder": {
|
70 |
+
"type": "ByteLevel",
|
71 |
+
"add_prefix_space": false,
|
72 |
+
"trim_offsets": true,
|
73 |
+
"use_regex": true
|
74 |
+
},
|
75 |
+
"model": {
|
76 |
+
"type": "BPE",
|
77 |
+
"dropout": null,
|
78 |
+
"unk_token": "<|unknown|>",
|
79 |
+
"continuing_subword_prefix": null,
|
80 |
+
"end_of_word_suffix": null,
|
81 |
+
"fuse_unk": false,
|
82 |
+
"byte_fallback": false,
|
83 |
+
"ignore_merges": false,
|
84 |
+
"vocab": {
|
85 |
+
"<|beginoftext|>": 0,
|
86 |
+
"<|padding|>": 1,
|
87 |
+
"<|unknown|>": 2,
|
88 |
+
"a": 3,
|
89 |
+
"c": 4,
|
90 |
+
"g": 5,
|
91 |
+
"t": 6,
|
92 |
+
"n": 7
|
93 |
+
},
|
94 |
+
"merges": []
|
95 |
+
}
|
96 |
+
}
|
checkpoint-2500/tokenizer_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": false,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<|beginoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<|endoftext|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "<|unknown|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"bos_token": "<|beginoftext|>",
|
32 |
+
"clean_up_tokenization_spaces": true,
|
33 |
+
"eos_token": "<|endoftext|>",
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_token": "<|endoftext|>",
|
36 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
37 |
+
"unk_token": "<|unknown|>"
|
38 |
+
}
|
checkpoint-2500/trainer_state.json
ADDED
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.024429569550984513,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0009771827820393806,
|
13 |
+
"grad_norm": 0.5417118072509766,
|
14 |
+
"learning_rate": 4.995602247740044e-05,
|
15 |
+
"loss": 1.378,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.001954365564078761,
|
20 |
+
"grad_norm": 0.6493918895721436,
|
21 |
+
"learning_rate": 4.990715856340093e-05,
|
22 |
+
"loss": 1.3304,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0029315483461181415,
|
27 |
+
"grad_norm": 0.9062462449073792,
|
28 |
+
"learning_rate": 4.9858294649401425e-05,
|
29 |
+
"loss": 1.3284,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.003908731128157522,
|
34 |
+
"grad_norm": 0.750052273273468,
|
35 |
+
"learning_rate": 4.9809430735401906e-05,
|
36 |
+
"loss": 1.3166,
|
37 |
+
"step": 400
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.004885913910196903,
|
41 |
+
"grad_norm": 0.6602022051811218,
|
42 |
+
"learning_rate": 4.97605668214024e-05,
|
43 |
+
"loss": 1.3166,
|
44 |
+
"step": 500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.005863096692236283,
|
48 |
+
"grad_norm": 0.4193927049636841,
|
49 |
+
"learning_rate": 4.971170290740288e-05,
|
50 |
+
"loss": 1.3098,
|
51 |
+
"step": 600
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.006840279474275663,
|
55 |
+
"grad_norm": 0.6095415949821472,
|
56 |
+
"learning_rate": 4.966283899340338e-05,
|
57 |
+
"loss": 1.3103,
|
58 |
+
"step": 700
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.007817462256315045,
|
62 |
+
"grad_norm": 0.9943467378616333,
|
63 |
+
"learning_rate": 4.9613975079403865e-05,
|
64 |
+
"loss": 1.3096,
|
65 |
+
"step": 800
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.008794645038354424,
|
69 |
+
"grad_norm": 1.2263585329055786,
|
70 |
+
"learning_rate": 4.9565111165404346e-05,
|
71 |
+
"loss": 1.3067,
|
72 |
+
"step": 900
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.009771827820393805,
|
76 |
+
"grad_norm": 0.7198677659034729,
|
77 |
+
"learning_rate": 4.951624725140484e-05,
|
78 |
+
"loss": 1.3041,
|
79 |
+
"step": 1000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.010749010602433185,
|
83 |
+
"grad_norm": 0.7370775938034058,
|
84 |
+
"learning_rate": 4.946738333740533e-05,
|
85 |
+
"loss": 1.302,
|
86 |
+
"step": 1100
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.011726193384472566,
|
90 |
+
"grad_norm": 0.5109437704086304,
|
91 |
+
"learning_rate": 4.941851942340582e-05,
|
92 |
+
"loss": 1.3089,
|
93 |
+
"step": 1200
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.012703376166511945,
|
97 |
+
"grad_norm": 0.1879555583000183,
|
98 |
+
"learning_rate": 4.9369655509406305e-05,
|
99 |
+
"loss": 1.3043,
|
100 |
+
"step": 1300
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.013680558948551327,
|
104 |
+
"grad_norm": 0.951046884059906,
|
105 |
+
"learning_rate": 4.932079159540679e-05,
|
106 |
+
"loss": 1.3098,
|
107 |
+
"step": 1400
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.014657741730590706,
|
111 |
+
"grad_norm": 0.2478829026222229,
|
112 |
+
"learning_rate": 4.927192768140728e-05,
|
113 |
+
"loss": 1.3026,
|
114 |
+
"step": 1500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.01563492451263009,
|
118 |
+
"grad_norm": 0.5585843324661255,
|
119 |
+
"learning_rate": 4.9223063767407776e-05,
|
120 |
+
"loss": 1.3014,
|
121 |
+
"step": 1600
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.016612107294669467,
|
125 |
+
"grad_norm": 0.48532453179359436,
|
126 |
+
"learning_rate": 4.917419985340826e-05,
|
127 |
+
"loss": 1.2981,
|
128 |
+
"step": 1700
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.017589290076708848,
|
132 |
+
"grad_norm": 0.4233573079109192,
|
133 |
+
"learning_rate": 4.912533593940875e-05,
|
134 |
+
"loss": 1.2992,
|
135 |
+
"step": 1800
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.01856647285874823,
|
139 |
+
"grad_norm": 0.3272475600242615,
|
140 |
+
"learning_rate": 4.9076472025409234e-05,
|
141 |
+
"loss": 1.292,
|
142 |
+
"step": 1900
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.01954365564078761,
|
146 |
+
"grad_norm": 0.5299385786056519,
|
147 |
+
"learning_rate": 4.902760811140973e-05,
|
148 |
+
"loss": 1.2963,
|
149 |
+
"step": 2000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.02052083842282699,
|
153 |
+
"grad_norm": 0.1614024043083191,
|
154 |
+
"learning_rate": 4.8978744197410216e-05,
|
155 |
+
"loss": 1.2945,
|
156 |
+
"step": 2100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.02149802120486637,
|
160 |
+
"grad_norm": 0.6039963960647583,
|
161 |
+
"learning_rate": 4.8929880283410705e-05,
|
162 |
+
"loss": 1.2913,
|
163 |
+
"step": 2200
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.02247520398690575,
|
167 |
+
"grad_norm": 0.5772804021835327,
|
168 |
+
"learning_rate": 4.888101636941119e-05,
|
169 |
+
"loss": 1.2895,
|
170 |
+
"step": 2300
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.023452386768945132,
|
174 |
+
"grad_norm": 0.7489622235298157,
|
175 |
+
"learning_rate": 4.883215245541168e-05,
|
176 |
+
"loss": 1.2847,
|
177 |
+
"step": 2400
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.024429569550984513,
|
181 |
+
"grad_norm": 0.30208253860473633,
|
182 |
+
"learning_rate": 4.878328854141217e-05,
|
183 |
+
"loss": 1.2924,
|
184 |
+
"step": 2500
|
185 |
+
}
|
186 |
+
],
|
187 |
+
"logging_steps": 100,
|
188 |
+
"max_steps": 102335,
|
189 |
+
"num_input_tokens_seen": 0,
|
190 |
+
"num_train_epochs": 1,
|
191 |
+
"save_steps": 500,
|
192 |
+
"stateful_callbacks": {
|
193 |
+
"TrainerControl": {
|
194 |
+
"args": {
|
195 |
+
"should_epoch_stop": false,
|
196 |
+
"should_evaluate": false,
|
197 |
+
"should_log": false,
|
198 |
+
"should_save": true,
|
199 |
+
"should_training_stop": false
|
200 |
+
},
|
201 |
+
"attributes": {}
|
202 |
+
}
|
203 |
+
},
|
204 |
+
"total_flos": 3.13573079252992e+16,
|
205 |
+
"train_batch_size": 12,
|
206 |
+
"trial_name": null,
|
207 |
+
"trial_params": null
|
208 |
+
}
|
checkpoint-2500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:278b8ae4ca6b721ea0f2d20061c63ec30cd0ca06fdf7af3d153eaddb11a3fd6b
|
3 |
+
size 5176
|