Training in progress, step 3500, checkpoint
Browse files- checkpoint-3500/config.json +32 -0
- checkpoint-3500/optimizer.pt +3 -0
- checkpoint-3500/pytorch_model.bin +3 -0
- checkpoint-3500/rng_state_0.pth +3 -0
- checkpoint-3500/rng_state_1.pth +3 -0
- checkpoint-3500/rng_state_2.pth +3 -0
- checkpoint-3500/rng_state_3.pth +3 -0
- checkpoint-3500/rng_state_4.pth +3 -0
- checkpoint-3500/rng_state_5.pth +3 -0
- checkpoint-3500/rng_state_6.pth +3 -0
- checkpoint-3500/rng_state_7.pth +3 -0
- checkpoint-3500/scheduler.pt +3 -0
- checkpoint-3500/special_tokens_map.json +37 -0
- checkpoint-3500/tokenizer.json +0 -0
- checkpoint-3500/tokenizer_config.json +60 -0
- checkpoint-3500/trainer_state.json +75 -0
- checkpoint-3500/training_args.bin +3 -0
checkpoint-3500/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-3500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a960886a4c9d87b6eb7f9065535fef1c4cb638be98fe7dec7dea5d3acf52f531
|
3 |
+
size 1010407418
|
checkpoint-3500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46a2d7451d4ac97e24a528226da11541afc6ec75b64054f79a5ba92b423229a7
|
3 |
+
size 505188394
|
checkpoint-3500/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f3205d0c956e5d6911dfc414a2bd0d2e7fa4c3c3d8a6ae6113ffb729705e211
|
3 |
+
size 15984
|
checkpoint-3500/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2775f561c29fcccf685135119ad8c1d3d11d86794264092c247a08adf74763d
|
3 |
+
size 15984
|
checkpoint-3500/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4ed1d602acba70a0ec1494705e623d852b5935cc6058a6c4c3577d767ec7c8d
|
3 |
+
size 15984
|
checkpoint-3500/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83b0306903eabcc985f74ea10caf58e3798c2fb748a3a5060ddc97049acb9da6
|
3 |
+
size 15984
|
checkpoint-3500/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5899bc1361d21cbdb94d4e62f5bdedf4b9e9fb03ebf3c5e1517286bd5687d73
|
3 |
+
size 15984
|
checkpoint-3500/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cd624d65e2da862a58e5ccb2d994f79ebf3fd2e5594e046e974ff91b4fa5d23
|
3 |
+
size 15984
|
checkpoint-3500/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33ef70c9df467f02d651d5ff00cc27d5322308c923b474f650109a831d0022f7
|
3 |
+
size 15984
|
checkpoint-3500/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e941c3d9c91923a95df93b0817c54d3b30eb148f3d4c542445388d02715838e1
|
3 |
+
size 15984
|
checkpoint-3500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:deeb69aa98ee23361f5d844d69be12f04fe15fda35332cd805bb3ed5e5fd6128
|
3 |
+
size 1064
|
checkpoint-3500/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-3500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3500/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-3500/trainer_state.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2690884628321561,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 3500,
|
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 |
+
"ep_loss": 0.3811,
|
29 |
+
"epoch": 0.12,
|
30 |
+
"learning_rate": 7.5e-05,
|
31 |
+
"loss": 2.2571,
|
32 |
+
"mlm_loss": 1.8761,
|
33 |
+
"step": 1500
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"ep_loss": 0.37,
|
37 |
+
"epoch": 0.15,
|
38 |
+
"learning_rate": 0.0001,
|
39 |
+
"loss": 1.9695,
|
40 |
+
"mlm_loss": 1.5994,
|
41 |
+
"step": 2000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"ep_loss": 0.3813,
|
45 |
+
"epoch": 0.19,
|
46 |
+
"learning_rate": 0.00012495,
|
47 |
+
"loss": 1.5597,
|
48 |
+
"mlm_loss": 1.1785,
|
49 |
+
"step": 2500
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"ep_loss": 0.3624,
|
53 |
+
"epoch": 0.23,
|
54 |
+
"learning_rate": 0.00014995,
|
55 |
+
"loss": 1.4228,
|
56 |
+
"mlm_loss": 1.0604,
|
57 |
+
"step": 3000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"ep_loss": 0.338,
|
61 |
+
"epoch": 0.27,
|
62 |
+
"learning_rate": 0.00017495,
|
63 |
+
"loss": 1.3108,
|
64 |
+
"mlm_loss": 0.9729,
|
65 |
+
"step": 3500
|
66 |
+
}
|
67 |
+
],
|
68 |
+
"logging_steps": 500,
|
69 |
+
"max_steps": 520240,
|
70 |
+
"num_train_epochs": 40,
|
71 |
+
"save_steps": 500,
|
72 |
+
"total_flos": 3.341860451825746e+18,
|
73 |
+
"trial_name": null,
|
74 |
+
"trial_params": null
|
75 |
+
}
|
checkpoint-3500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cee56d4f38339eac5ecf098381d5222b3783455863547a17ac0df67c8caa7d15
|
3 |
+
size 4664
|