Training in progress, step 20, checkpoint
Browse files- last-checkpoint/config.json +31 -0
- last-checkpoint/generation_config.json +8 -0
- last-checkpoint/model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state_0.pth +3 -0
- last-checkpoint/rng_state_1.pth +3 -0
- last-checkpoint/rng_state_2.pth +3 -0
- last-checkpoint/rng_state_3.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +30 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer.model +3 -0
- last-checkpoint/tokenizer_config.json +43 -0
- last-checkpoint/trainer_state.json +63 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "trl-internal-testing/tiny-random-LlamaForCausalLM",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"head_dim": 4,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 16,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 64,
|
15 |
+
"max_position_embeddings": 2048,
|
16 |
+
"mlp_bias": false,
|
17 |
+
"model_type": "llama",
|
18 |
+
"num_attention_heads": 4,
|
19 |
+
"num_hidden_layers": 2,
|
20 |
+
"num_key_value_heads": 4,
|
21 |
+
"pad_token_id": -1,
|
22 |
+
"pretraining_tp": 1,
|
23 |
+
"rms_norm_eps": 1e-06,
|
24 |
+
"rope_scaling": null,
|
25 |
+
"rope_theta": 10000.0,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "bfloat16",
|
28 |
+
"transformers_version": "4.48.1",
|
29 |
+
"use_cache": false,
|
30 |
+
"vocab_size": 32000
|
31 |
+
}
|
last-checkpoint/generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 1,
|
6 |
+
"pad_token_id": 2,
|
7 |
+
"transformers_version": "4.48.1"
|
8 |
+
}
|
last-checkpoint/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5acd54546310927e397d2601dbfa4802a3e8dcaae83fca1cf6eb8d637b7a3718
|
3 |
+
size 2066752
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b33c209a866661ee58b3141afc7148cd60ff320391c20638f94e38521197299
|
3 |
+
size 2162798
|
last-checkpoint/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02bd6697dd0ac01f79967d93e880e93c5ad7e5d6a672668dd596f9f42c435066
|
3 |
+
size 15024
|
last-checkpoint/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1946c0d35865c02655624537450071d8e3a581f1d24f3c539357cae293b3d2d2
|
3 |
+
size 15024
|
last-checkpoint/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9faf933c304288a566e09316737d2bdccb42e76da4138d98110982bcbf5dbf1
|
3 |
+
size 15024
|
last-checkpoint/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f2cb6de5c0f2b78c1515e90a9ab03144587d336dd27fc87023f09785c5d64cb
|
3 |
+
size 15024
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84f22729b765b6841bd185712dd3ab8bf338866cd8396b5dce62f9950913691a
|
3 |
+
size 1064
|
last-checkpoint/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
last-checkpoint/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
last-checkpoint/tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '### Instruction: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ '### Response: ' + message['content'] + eos_token}}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"extra_special_tokens": {},
|
36 |
+
"legacy": true,
|
37 |
+
"model_max_length": 2048,
|
38 |
+
"pad_token": "<unk>",
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": true,
|
42 |
+
"use_fast": true
|
43 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.3333333333333335,
|
5 |
+
"eval_steps": 20,
|
6 |
+
"global_step": 20,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.16666666666666666,
|
13 |
+
"eval_loss": 10.376375198364258,
|
14 |
+
"eval_runtime": 2.3724,
|
15 |
+
"eval_samples_per_second": 632.685,
|
16 |
+
"eval_steps_per_second": 5.058,
|
17 |
+
"step": 1
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 1.6666666666666665,
|
21 |
+
"grad_norm": 0.09375,
|
22 |
+
"learning_rate": 0.00019863613034027224,
|
23 |
+
"loss": 10.3756,
|
24 |
+
"step": 10
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 3.3333333333333335,
|
28 |
+
"grad_norm": 0.12353515625,
|
29 |
+
"learning_rate": 0.0001879473751206489,
|
30 |
+
"loss": 10.3632,
|
31 |
+
"step": 20
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 3.3333333333333335,
|
35 |
+
"eval_loss": 10.353797912597656,
|
36 |
+
"eval_runtime": 2.3258,
|
37 |
+
"eval_samples_per_second": 645.382,
|
38 |
+
"eval_steps_per_second": 5.16,
|
39 |
+
"step": 20
|
40 |
+
}
|
41 |
+
],
|
42 |
+
"logging_steps": 10,
|
43 |
+
"max_steps": 100,
|
44 |
+
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 17,
|
46 |
+
"save_steps": 20,
|
47 |
+
"stateful_callbacks": {
|
48 |
+
"TrainerControl": {
|
49 |
+
"args": {
|
50 |
+
"should_epoch_stop": false,
|
51 |
+
"should_evaluate": false,
|
52 |
+
"should_log": false,
|
53 |
+
"should_save": true,
|
54 |
+
"should_training_stop": false
|
55 |
+
},
|
56 |
+
"attributes": {}
|
57 |
+
}
|
58 |
+
},
|
59 |
+
"total_flos": 16366341980160.0,
|
60 |
+
"train_batch_size": 32,
|
61 |
+
"trial_name": null,
|
62 |
+
"trial_params": null
|
63 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff5412d93e96b25beb0162d18ccff57ca0decb0cd620511495de3ffb7fd49fd5
|
3 |
+
size 7032
|