Training in progress, step 1000, checkpoint
Browse files- checkpoint-1000/config.json +32 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/pytorch_model.bin +3 -0
- checkpoint-1000/rng_state_0.pth +3 -0
- checkpoint-1000/rng_state_1.pth +3 -0
- checkpoint-1000/rng_state_2.pth +3 -0
- checkpoint-1000/rng_state_3.pth +3 -0
- checkpoint-1000/rng_state_4.pth +3 -0
- checkpoint-1000/rng_state_5.pth +3 -0
- checkpoint-1000/rng_state_6.pth +3 -0
- checkpoint-1000/rng_state_7.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +37 -0
- checkpoint-1000/tokenizer.json +0 -0
- checkpoint-1000/tokenizer_config.json +60 -0
- checkpoint-1000/trainer_state.json +35 -0
- checkpoint-1000/training_args.bin +3 -0
checkpoint-1000/config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"LongelmForMaskedLMWithEdgePrediction"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"block_size": 8,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"ep_add_linear_projection": true,
|
11 |
+
"global_memory_size": 1,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"layer_norm_eps": 1e-12,
|
18 |
+
"max_blocks": 200,
|
19 |
+
"max_position_embeddings": 1801,
|
20 |
+
"max_relative_position_embeddings": 8,
|
21 |
+
"model_type": "longelm",
|
22 |
+
"node_size": 1,
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_layers": 12,
|
25 |
+
"pad_token_id": 3,
|
26 |
+
"position_embedding_type": "mixed",
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.34.1",
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 50265
|
32 |
+
}
|
checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20d7fa52c7c128f99987417c0874a0b4ed842d0adf710b8bedc516658aaac293
|
3 |
+
size 1010407418
|
checkpoint-1000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa88ed43c6b4fd4f23e04c5fe254b66b1dc5e83ea5e80ca243566a811d7b5a2d
|
3 |
+
size 505188394
|
checkpoint-1000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f55c758f67d36ce682d64451b06ad069185cca502827955d29caebbdad0664fd
|
3 |
+
size 15984
|
checkpoint-1000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:736f50a967aae5f84ed9907a15e0edc9218cc88f722acb3b68f5d08a91f442aa
|
3 |
+
size 15984
|
checkpoint-1000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:586b4ad458b891147941df884e07d3fe37b9c1ee793f5c3190fb429acbc8065a
|
3 |
+
size 15984
|
checkpoint-1000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d62ff95dc6bc6dd01a3bee4d7b8f7e300d7f81298d9e82920e7f8cd60b1732ad
|
3 |
+
size 15984
|
checkpoint-1000/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3a57642c60e8509d71d20db84c6566ff45f8c326e3647c9be08e6b8a325998c
|
3 |
+
size 15984
|
checkpoint-1000/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3f1fa65a47fc2cd4a459a6d5e659574103f62ce1eb4cd9bcb43f1a95a373d33
|
3 |
+
size 15984
|
checkpoint-1000/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e85a8ab59c1aeb78fec644884e4146507d2b305a8c6ca280efb340d2b98ccab8
|
3 |
+
size 15984
|
checkpoint-1000/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07414a8b2550bf54ac5fc8b6257747b590a7c459fe42aa5e88cd82b881d5bf63
|
3 |
+
size 15984
|
checkpoint-1000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a56b2c9c1f74435100f93711ec1a4f79bb33df727044c2609fab9ac502f2d6ec
|
3 |
+
size 1064
|
checkpoint-1000/special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
checkpoint-1000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1000/tokenizer_config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[CLS]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[SEP]",
|
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 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"30522": {
|
44 |
+
"content": "<INST>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
+
}
|
51 |
+
},
|
52 |
+
"clean_up_tokenization_spaces": true,
|
53 |
+
"cls_token": "[CLS]",
|
54 |
+
"mask_token": "[MASK]",
|
55 |
+
"model_max_length": 512,
|
56 |
+
"pad_token": "[PAD]",
|
57 |
+
"sep_token": "[SEP]",
|
58 |
+
"tokenizer_class": "LongelmTokenizer",
|
59 |
+
"unk_token": "[UNK]"
|
60 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.07688241795204459,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"ep_loss": 4.7343,
|
13 |
+
"epoch": 0.04,
|
14 |
+
"learning_rate": 2.5e-05,
|
15 |
+
"loss": 11.6218,
|
16 |
+
"mlm_loss": 6.8875,
|
17 |
+
"step": 500
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"ep_loss": 0.4315,
|
21 |
+
"epoch": 0.08,
|
22 |
+
"learning_rate": 5e-05,
|
23 |
+
"loss": 3.0285,
|
24 |
+
"mlm_loss": 2.5969,
|
25 |
+
"step": 1000
|
26 |
+
}
|
27 |
+
],
|
28 |
+
"logging_steps": 500,
|
29 |
+
"max_steps": 520240,
|
30 |
+
"num_train_epochs": 40,
|
31 |
+
"save_steps": 500,
|
32 |
+
"total_flos": 9.548172719502131e+17,
|
33 |
+
"trial_name": null,
|
34 |
+
"trial_params": null
|
35 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cee56d4f38339eac5ecf098381d5222b3783455863547a17ac0df67c8caa7d15
|
3 |
+
size 4664
|