Commit
•
9b42209
1
Parent(s):
cf193fb
Training in progress, step 1000
Browse files- model.safetensors +1 -1
- run-2/checkpoint-1000/model.safetensors +2 -2
- run-2/checkpoint-1000/optimizer.pt +3 -0
- run-2/checkpoint-1000/rng_state.pth +3 -0
- run-2/checkpoint-1000/scheduler.pt +3 -0
- run-2/checkpoint-1000/special_tokens_map.json +7 -0
- run-2/checkpoint-1000/tokenizer.json +0 -0
- run-2/checkpoint-1000/tokenizer_config.json +55 -0
- run-2/checkpoint-1000/trainer_state.json +63 -0
- run-2/checkpoint-1000/training_args.bin +3 -0
- run-2/checkpoint-1000/vocab.txt +0 -0
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 268290900
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdfacc0d200e99d738052580fb890ca33665de7eaa76e19e0033c66446adef98
|
3 |
size 268290900
|
run-2/checkpoint-1000/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdfacc0d200e99d738052580fb890ca33665de7eaa76e19e0033c66446adef98
|
3 |
+
size 268290900
|
run-2/checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e40ad42f5bc4a64b5b288a43e45dc19844fae9ef64a43d1e3ac242f8ff4f0ec9
|
3 |
+
size 536643898
|
run-2/checkpoint-1000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbeee5483b3473d40884032dbdc7615fd67ccf004ea5660dd5b8668c9c4e48a0
|
3 |
+
size 14244
|
run-2/checkpoint-1000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd6312bafb4f172d36cde8e97f0ddfa67db03a0e6d8fc98f230d4474ba8ee580
|
3 |
+
size 1064
|
run-2/checkpoint-1000/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-2/checkpoint-1000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-1000/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-2/checkpoint-1000/trainer_state.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.1446540880503147,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.2003006935119629,
|
14 |
+
"eval_runtime": 3.3177,
|
15 |
+
"eval_samples_per_second": 934.389,
|
16 |
+
"eval_steps_per_second": 19.592,
|
17 |
+
"step": 318
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 1.57,
|
21 |
+
"grad_norm": 0.5493956804275513,
|
22 |
+
"learning_rate": 1.371069182389937e-05,
|
23 |
+
"loss": 0.3146,
|
24 |
+
"step": 500
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.0,
|
28 |
+
"eval_loss": 0.10496184974908829,
|
29 |
+
"eval_runtime": 3.3448,
|
30 |
+
"eval_samples_per_second": 926.816,
|
31 |
+
"eval_steps_per_second": 19.433,
|
32 |
+
"step": 636
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 3.0,
|
36 |
+
"eval_loss": 0.07582292705774307,
|
37 |
+
"eval_runtime": 3.4125,
|
38 |
+
"eval_samples_per_second": 908.413,
|
39 |
+
"eval_steps_per_second": 19.047,
|
40 |
+
"step": 954
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 3.14,
|
44 |
+
"grad_norm": 0.5040295124053955,
|
45 |
+
"learning_rate": 7.421383647798742e-06,
|
46 |
+
"loss": 0.1211,
|
47 |
+
"step": 1000
|
48 |
+
}
|
49 |
+
],
|
50 |
+
"logging_steps": 500,
|
51 |
+
"max_steps": 1590,
|
52 |
+
"num_input_tokens_seen": 0,
|
53 |
+
"num_train_epochs": 5,
|
54 |
+
"save_steps": 500,
|
55 |
+
"total_flos": 260941334653608.0,
|
56 |
+
"train_batch_size": 48,
|
57 |
+
"trial_name": null,
|
58 |
+
"trial_params": {
|
59 |
+
"alpha": 0.80288090122901,
|
60 |
+
"num_train_epochs": 7,
|
61 |
+
"temperature": 17
|
62 |
+
}
|
63 |
+
}
|
run-2/checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4ef4d6f9f8144b6a0d57a691210e77bd9f5c55ff53f926c5e4cbe0cbfb35bbb
|
3 |
+
size 4984
|
run-2/checkpoint-1000/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|