Training in progress, step 2500, checkpoint
Browse files- checkpoint-2500/adapter_config.json +4 -4
- checkpoint-2500/adapter_model.safetensors +1 -1
- checkpoint-2500/optimizer.pt +2 -2
- checkpoint-2500/rng_state.pth +1 -1
- checkpoint-2500/scheduler.pt +1 -1
- checkpoint-2500/special_tokens_map.json +0 -16
- checkpoint-2500/tokenizer.json +4 -4
- checkpoint-2500/tokenizer_config.json +8 -8
- checkpoint-2500/trainer_state.json +49 -49
- checkpoint-2500/training_args.bin +1 -1
checkpoint-2500/adapter_config.json
CHANGED
@@ -23,12 +23,12 @@
|
|
23 |
"revision": null,
|
24 |
"target_modules": [
|
25 |
"q_proj",
|
26 |
-
"v_proj",
|
27 |
-
"k_proj",
|
28 |
-
"up_proj",
|
29 |
"down_proj",
|
|
|
30 |
"o_proj",
|
31 |
-
"
|
|
|
|
|
32 |
],
|
33 |
"task_type": "CAUSAL_LM",
|
34 |
"use_dora": false,
|
|
|
23 |
"revision": null,
|
24 |
"target_modules": [
|
25 |
"q_proj",
|
|
|
|
|
|
|
26 |
"down_proj",
|
27 |
+
"k_proj",
|
28 |
"o_proj",
|
29 |
+
"v_proj",
|
30 |
+
"gate_proj",
|
31 |
+
"up_proj"
|
32 |
],
|
33 |
"task_type": "CAUSAL_LM",
|
34 |
"use_dora": false,
|
checkpoint-2500/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2460946960
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82971030ddbc8ed4dea42524dab0554d2893743b5a2990dd8a1fddf90f2fe309
|
3 |
size 2460946960
|
checkpoint-2500/optimizer.pt
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 sha256:81f45d14a05279c958d566d8b50abbacc972be214b58e8d697a5a110137eebf6
|
3 |
+
size 1831543994
|
checkpoint-2500/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14308
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd5bc3b5f58a5ab5b07a199a5cee4cb2ef460e0a2ac7342fe01496ddb803cd41
|
3 |
size 14308
|
checkpoint-2500/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13712619cb3399d895b0657a6d715ac5aaec0819cc89786eb755488b638f7dc0
|
3 |
size 1064
|
checkpoint-2500/special_tokens_map.json
CHANGED
@@ -1,20 +1,4 @@
|
|
1 |
{
|
2 |
-
"additional_special_tokens": [
|
3 |
-
{
|
4 |
-
"content": "[SQL]",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false
|
9 |
-
},
|
10 |
-
{
|
11 |
-
"content": "[/SQL]",
|
12 |
-
"lstrip": false,
|
13 |
-
"normalized": false,
|
14 |
-
"rstrip": false,
|
15 |
-
"single_word": false
|
16 |
-
}
|
17 |
-
],
|
18 |
"bos_token": {
|
19 |
"content": "<|endoftext|>",
|
20 |
"lstrip": false,
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<|endoftext|>",
|
4 |
"lstrip": false,
|
checkpoint-2500/tokenizer.json
CHANGED
@@ -437,8 +437,8 @@
|
|
437 |
"single_word": false,
|
438 |
"lstrip": false,
|
439 |
"rstrip": false,
|
440 |
-
"normalized":
|
441 |
-
"special":
|
442 |
},
|
443 |
{
|
444 |
"id": 50300,
|
@@ -446,8 +446,8 @@
|
|
446 |
"single_word": false,
|
447 |
"lstrip": false,
|
448 |
"rstrip": false,
|
449 |
-
"normalized":
|
450 |
-
"special":
|
451 |
}
|
452 |
],
|
453 |
"normalizer": {
|
|
|
437 |
"single_word": false,
|
438 |
"lstrip": false,
|
439 |
"rstrip": false,
|
440 |
+
"normalized": true,
|
441 |
+
"special": false
|
442 |
},
|
443 |
{
|
444 |
"id": 50300,
|
|
|
446 |
"single_word": false,
|
447 |
"lstrip": false,
|
448 |
"rstrip": false,
|
449 |
+
"normalized": true,
|
450 |
+
"special": false
|
451 |
}
|
452 |
],
|
453 |
"normalizer": {
|
checkpoint-2500/tokenizer_config.json
CHANGED
@@ -382,30 +382,30 @@
|
|
382 |
"50299": {
|
383 |
"content": "[SQL]",
|
384 |
"lstrip": false,
|
385 |
-
"normalized":
|
386 |
"rstrip": false,
|
387 |
"single_word": false,
|
388 |
-
"special":
|
389 |
},
|
390 |
"50300": {
|
391 |
"content": "[/SQL]",
|
392 |
"lstrip": false,
|
393 |
-
"normalized":
|
394 |
"rstrip": false,
|
395 |
"single_word": false,
|
396 |
-
"special":
|
397 |
}
|
398 |
},
|
399 |
-
"additional_special_tokens": [
|
400 |
-
"[SQL]",
|
401 |
-
"[/SQL]"
|
402 |
-
],
|
403 |
"bos_token": "<|endoftext|>",
|
404 |
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
405 |
"clean_up_tokenization_spaces": true,
|
406 |
"eos_token": "<|endoftext|>",
|
|
|
407 |
"model_max_length": 4096,
|
408 |
"pad_token": "<|endoftext|>",
|
|
|
409 |
"tokenizer_class": "GPTNeoXTokenizer",
|
|
|
|
|
410 |
"unk_token": "<|endoftext|>"
|
411 |
}
|
|
|
382 |
"50299": {
|
383 |
"content": "[SQL]",
|
384 |
"lstrip": false,
|
385 |
+
"normalized": true,
|
386 |
"rstrip": false,
|
387 |
"single_word": false,
|
388 |
+
"special": false
|
389 |
},
|
390 |
"50300": {
|
391 |
"content": "[/SQL]",
|
392 |
"lstrip": false,
|
393 |
+
"normalized": true,
|
394 |
"rstrip": false,
|
395 |
"single_word": false,
|
396 |
+
"special": false
|
397 |
}
|
398 |
},
|
|
|
|
|
|
|
|
|
399 |
"bos_token": "<|endoftext|>",
|
400 |
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
401 |
"clean_up_tokenization_spaces": true,
|
402 |
"eos_token": "<|endoftext|>",
|
403 |
+
"max_length": 1024,
|
404 |
"model_max_length": 4096,
|
405 |
"pad_token": "<|endoftext|>",
|
406 |
+
"stride": 0,
|
407 |
"tokenizer_class": "GPTNeoXTokenizer",
|
408 |
+
"truncation_side": "right",
|
409 |
+
"truncation_strategy": "longest_first",
|
410 |
"unk_token": "<|endoftext|>"
|
411 |
}
|
checkpoint-2500/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 2500,
|
7 |
"is_hyper_param_search": false,
|
@@ -9,88 +9,88 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"grad_norm": 0.
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 0.
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"eval_loss": 0.
|
21 |
-
"eval_runtime":
|
22 |
-
"eval_samples_per_second":
|
23 |
-
"eval_steps_per_second":
|
24 |
"step": 500
|
25 |
},
|
26 |
{
|
27 |
-
"epoch": 0.
|
28 |
-
"grad_norm": 0.
|
29 |
-
"learning_rate":
|
30 |
-
"loss": 0.
|
31 |
"step": 1000
|
32 |
},
|
33 |
{
|
34 |
-
"epoch": 0.
|
35 |
-
"eval_loss": 0.
|
36 |
-
"eval_runtime":
|
37 |
-
"eval_samples_per_second":
|
38 |
-
"eval_steps_per_second":
|
39 |
"step": 1000
|
40 |
},
|
41 |
{
|
42 |
-
"epoch":
|
43 |
-
"grad_norm": 0.
|
44 |
-
"learning_rate":
|
45 |
-
"loss": 0.
|
46 |
"step": 1500
|
47 |
},
|
48 |
{
|
49 |
-
"epoch":
|
50 |
-
"eval_loss": 0.
|
51 |
-
"eval_runtime":
|
52 |
-
"eval_samples_per_second":
|
53 |
-
"eval_steps_per_second":
|
54 |
"step": 1500
|
55 |
},
|
56 |
{
|
57 |
-
"epoch":
|
58 |
-
"grad_norm": 0.
|
59 |
-
"learning_rate":
|
60 |
-
"loss": 0.
|
61 |
"step": 2000
|
62 |
},
|
63 |
{
|
64 |
-
"epoch":
|
65 |
-
"eval_loss": 0.
|
66 |
-
"eval_runtime":
|
67 |
-
"eval_samples_per_second": 1.
|
68 |
-
"eval_steps_per_second": 1.
|
69 |
"step": 2000
|
70 |
},
|
71 |
{
|
72 |
-
"epoch":
|
73 |
-
"grad_norm":
|
74 |
-
"learning_rate":
|
75 |
-
"loss": 0.
|
76 |
"step": 2500
|
77 |
},
|
78 |
{
|
79 |
-
"epoch":
|
80 |
-
"eval_loss": 0.
|
81 |
-
"eval_runtime":
|
82 |
-
"eval_samples_per_second": 1.
|
83 |
-
"eval_steps_per_second": 1.
|
84 |
"step": 2500
|
85 |
}
|
86 |
],
|
87 |
"logging_steps": 500,
|
88 |
-
"max_steps":
|
89 |
"num_input_tokens_seen": 0,
|
90 |
"num_train_epochs": 50,
|
91 |
"save_steps": 500,
|
92 |
-
"total_flos":
|
93 |
-
"train_batch_size":
|
94 |
"trial_name": null,
|
95 |
"trial_params": null
|
96 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.184796854521625,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 2500,
|
7 |
"is_hyper_param_search": false,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.46,
|
13 |
+
"grad_norm": 0.36198097467422485,
|
14 |
+
"learning_rate": 6.0716454159077105e-05,
|
15 |
+
"loss": 0.4455,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.46,
|
20 |
+
"eval_loss": 0.6183120608329773,
|
21 |
+
"eval_runtime": 195.3588,
|
22 |
+
"eval_samples_per_second": 2.37,
|
23 |
+
"eval_steps_per_second": 2.37,
|
24 |
"step": 500
|
25 |
},
|
26 |
{
|
27 |
+
"epoch": 0.91,
|
28 |
+
"grad_norm": 0.1898297369480133,
|
29 |
+
"learning_rate": 0.00012143290831815421,
|
30 |
+
"loss": 0.0995,
|
31 |
"step": 1000
|
32 |
},
|
33 |
{
|
34 |
+
"epoch": 0.91,
|
35 |
+
"eval_loss": 0.6644699573516846,
|
36 |
+
"eval_runtime": 195.5381,
|
37 |
+
"eval_samples_per_second": 2.368,
|
38 |
+
"eval_steps_per_second": 2.368,
|
39 |
"step": 1000
|
40 |
},
|
41 |
{
|
42 |
+
"epoch": 1.37,
|
43 |
+
"grad_norm": 0.25010770559310913,
|
44 |
+
"learning_rate": 0.00018214936247723133,
|
45 |
+
"loss": 0.0858,
|
46 |
"step": 1500
|
47 |
},
|
48 |
{
|
49 |
+
"epoch": 1.37,
|
50 |
+
"eval_loss": 0.6735700368881226,
|
51 |
+
"eval_runtime": 195.292,
|
52 |
+
"eval_samples_per_second": 2.371,
|
53 |
+
"eval_steps_per_second": 2.371,
|
54 |
"step": 1500
|
55 |
},
|
56 |
{
|
57 |
+
"epoch": 1.7479248580166011,
|
58 |
+
"grad_norm": 0.12149681895971298,
|
59 |
+
"learning_rate": 0.00019897628145050826,
|
60 |
+
"loss": 0.0836,
|
61 |
"step": 2000
|
62 |
},
|
63 |
{
|
64 |
+
"epoch": 1.7479248580166011,
|
65 |
+
"eval_loss": 0.2921118438243866,
|
66 |
+
"eval_runtime": 49.9169,
|
67 |
+
"eval_samples_per_second": 1.863,
|
68 |
+
"eval_steps_per_second": 1.863,
|
69 |
"step": 2000
|
70 |
},
|
71 |
{
|
72 |
+
"epoch": 2.184796854521625,
|
73 |
+
"grad_norm": 0.07184480875730515,
|
74 |
+
"learning_rate": 0.00019717396006055802,
|
75 |
+
"loss": 0.0731,
|
76 |
"step": 2500
|
77 |
},
|
78 |
{
|
79 |
+
"epoch": 2.184796854521625,
|
80 |
+
"eval_loss": 0.2528606653213501,
|
81 |
+
"eval_runtime": 49.8116,
|
82 |
+
"eval_samples_per_second": 1.867,
|
83 |
+
"eval_steps_per_second": 1.867,
|
84 |
"step": 2500
|
85 |
}
|
86 |
],
|
87 |
"logging_steps": 500,
|
88 |
+
"max_steps": 57200,
|
89 |
"num_input_tokens_seen": 0,
|
90 |
"num_train_epochs": 50,
|
91 |
"save_steps": 500,
|
92 |
+
"total_flos": 2.1111966032161997e+17,
|
93 |
+
"train_batch_size": 4,
|
94 |
"trial_name": null,
|
95 |
"trial_params": null
|
96 |
}
|
checkpoint-2500/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:623ba81014c1eb50f2c15b8946e12738563128d0fbbc243c8fbacd7dba6cd4b4
|
3 |
size 5048
|