24.08.05 Initial Commit
Browse files- config.json +31 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +30 -0
- tokenizer.model +3 -0
- tokenizer_config.json +44 -0
- trainer_state.json +1194 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Jiayi-Pan/Tiny-Vicuna-1B",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 2048,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 5632,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"medusa_num_heads": 5,
|
16 |
+
"medusa_num_layers": 1,
|
17 |
+
"mlp_bias": false,
|
18 |
+
"model_type": "llama",
|
19 |
+
"num_attention_heads": 32,
|
20 |
+
"num_hidden_layers": 22,
|
21 |
+
"num_key_value_heads": 4,
|
22 |
+
"pretraining_tp": 1,
|
23 |
+
"rms_norm_eps": 1e-05,
|
24 |
+
"rope_scaling": null,
|
25 |
+
"rope_theta": 10000.0,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "bfloat16",
|
28 |
+
"transformers_version": "4.43.0",
|
29 |
+
"use_cache": false,
|
30 |
+
"vocab_size": 32000
|
31 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 1,
|
3 |
+
"eos_token_id": 2,
|
4 |
+
"max_length": 2048,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.43.0"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6db3c859d2c997ce6bf6e2eb8ded208591c93bf4c34ef4f36bae092291f5afdc
|
3 |
+
size 2897445048
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f1916e2b73af6d2c1064abca8bcf01f3049aea2d68bdb1f4f6b23d3bc417fa0
|
3 |
+
size 698764714
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98e1bbdc545aac10636ea761b8098d077311c614411b78b59ac376bac6d5db34
|
3 |
+
size 1064
|
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 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
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 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": false,
|
35 |
+
"model_max_length": 2048,
|
36 |
+
"pad_token": "<unk>",
|
37 |
+
"padding_side": "right",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false,
|
43 |
+
"use_fast": true
|
44 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 3.0168392658233643,
|
3 |
+
"best_model_checkpoint": "./vicuna_1b_stage1/checkpoint-160",
|
4 |
+
"epoch": 0.06805614632071459,
|
5 |
+
"eval_steps": 40,
|
6 |
+
"global_step": 160,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0004253509145044662,
|
13 |
+
"grad_norm": 0.64453125,
|
14 |
+
"learning_rate": 1.25e-05,
|
15 |
+
"loss": 8.2835,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0008507018290089324,
|
20 |
+
"grad_norm": 0.58984375,
|
21 |
+
"learning_rate": 2.5e-05,
|
22 |
+
"loss": 7.9977,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0012760527435133986,
|
27 |
+
"grad_norm": 0.55078125,
|
28 |
+
"learning_rate": 3.75e-05,
|
29 |
+
"loss": 8.0608,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.0017014036580178648,
|
34 |
+
"grad_norm": 0.5390625,
|
35 |
+
"learning_rate": 5e-05,
|
36 |
+
"loss": 7.6677,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.002126754572522331,
|
41 |
+
"grad_norm": 0.50390625,
|
42 |
+
"learning_rate": 6.25e-05,
|
43 |
+
"loss": 7.7683,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.002552105487026797,
|
48 |
+
"grad_norm": 0.484375,
|
49 |
+
"learning_rate": 7.5e-05,
|
50 |
+
"loss": 7.6699,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.0029774564015312634,
|
55 |
+
"grad_norm": 0.470703125,
|
56 |
+
"learning_rate": 8.75e-05,
|
57 |
+
"loss": 7.3249,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.0034028073160357296,
|
62 |
+
"grad_norm": 0.474609375,
|
63 |
+
"learning_rate": 0.0001,
|
64 |
+
"loss": 7.3464,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.0038281582305401958,
|
69 |
+
"grad_norm": 0.58203125,
|
70 |
+
"learning_rate": 0.00011250000000000001,
|
71 |
+
"loss": 7.3995,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.004253509145044662,
|
76 |
+
"grad_norm": 0.5078125,
|
77 |
+
"learning_rate": 0.000125,
|
78 |
+
"loss": 6.8603,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.004678860059549128,
|
83 |
+
"grad_norm": 0.515625,
|
84 |
+
"learning_rate": 0.0001375,
|
85 |
+
"loss": 6.7678,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.005104210974053594,
|
90 |
+
"grad_norm": 0.546875,
|
91 |
+
"learning_rate": 0.00015,
|
92 |
+
"loss": 6.4618,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.00552956188855806,
|
97 |
+
"grad_norm": 0.578125,
|
98 |
+
"learning_rate": 0.00016250000000000002,
|
99 |
+
"loss": 6.3417,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.005954912803062527,
|
104 |
+
"grad_norm": 0.515625,
|
105 |
+
"learning_rate": 0.000175,
|
106 |
+
"loss": 5.9831,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.0063802637175669925,
|
111 |
+
"grad_norm": 0.515625,
|
112 |
+
"learning_rate": 0.0001875,
|
113 |
+
"loss": 5.5884,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.006805614632071459,
|
118 |
+
"grad_norm": 0.53125,
|
119 |
+
"learning_rate": 0.0002,
|
120 |
+
"loss": 5.4738,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.007230965546575925,
|
125 |
+
"grad_norm": 0.8359375,
|
126 |
+
"learning_rate": 0.0002125,
|
127 |
+
"loss": 4.9796,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.0076563164610803916,
|
132 |
+
"grad_norm": 0.70703125,
|
133 |
+
"learning_rate": 0.00022500000000000002,
|
134 |
+
"loss": 5.1167,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.008081667375584857,
|
139 |
+
"grad_norm": 0.83203125,
|
140 |
+
"learning_rate": 0.0002375,
|
141 |
+
"loss": 4.872,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.008507018290089324,
|
146 |
+
"grad_norm": 0.640625,
|
147 |
+
"learning_rate": 0.00025,
|
148 |
+
"loss": 4.7869,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.00893236920459379,
|
153 |
+
"grad_norm": 0.70703125,
|
154 |
+
"learning_rate": 0.00026250000000000004,
|
155 |
+
"loss": 4.4585,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.009357720119098255,
|
160 |
+
"grad_norm": 0.58984375,
|
161 |
+
"learning_rate": 0.000275,
|
162 |
+
"loss": 4.5412,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.009783071033602722,
|
167 |
+
"grad_norm": 0.56640625,
|
168 |
+
"learning_rate": 0.0002875,
|
169 |
+
"loss": 4.4428,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.010208421948107189,
|
174 |
+
"grad_norm": 0.5234375,
|
175 |
+
"learning_rate": 0.0003,
|
176 |
+
"loss": 4.1456,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.010633772862611655,
|
181 |
+
"grad_norm": 0.54296875,
|
182 |
+
"learning_rate": 0.0003125,
|
183 |
+
"loss": 4.0197,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.01105912377711612,
|
188 |
+
"grad_norm": 0.51171875,
|
189 |
+
"learning_rate": 0.00032500000000000004,
|
190 |
+
"loss": 4.2874,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.011484474691620587,
|
195 |
+
"grad_norm": 0.435546875,
|
196 |
+
"learning_rate": 0.0003375,
|
197 |
+
"loss": 3.9194,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.011909825606125054,
|
202 |
+
"grad_norm": 0.4375,
|
203 |
+
"learning_rate": 0.00035,
|
204 |
+
"loss": 4.1732,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.01233517652062952,
|
209 |
+
"grad_norm": 0.462890625,
|
210 |
+
"learning_rate": 0.0003625,
|
211 |
+
"loss": 3.7387,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.012760527435133985,
|
216 |
+
"grad_norm": 0.4609375,
|
217 |
+
"learning_rate": 0.000375,
|
218 |
+
"loss": 4.1143,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.013185878349638452,
|
223 |
+
"grad_norm": 0.388671875,
|
224 |
+
"learning_rate": 0.00038750000000000004,
|
225 |
+
"loss": 3.9235,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.013611229264142918,
|
230 |
+
"grad_norm": 0.408203125,
|
231 |
+
"learning_rate": 0.0004,
|
232 |
+
"loss": 3.8736,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.014036580178647383,
|
237 |
+
"grad_norm": 0.37890625,
|
238 |
+
"learning_rate": 0.0004125,
|
239 |
+
"loss": 3.6178,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.01446193109315185,
|
244 |
+
"grad_norm": 0.4296875,
|
245 |
+
"learning_rate": 0.000425,
|
246 |
+
"loss": 3.7336,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.014887282007656316,
|
251 |
+
"grad_norm": 0.408203125,
|
252 |
+
"learning_rate": 0.0004375,
|
253 |
+
"loss": 3.7709,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.015312632922160783,
|
258 |
+
"grad_norm": 0.32421875,
|
259 |
+
"learning_rate": 0.00045000000000000004,
|
260 |
+
"loss": 3.5944,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.015737983836665248,
|
265 |
+
"grad_norm": 0.3359375,
|
266 |
+
"learning_rate": 0.0004625,
|
267 |
+
"loss": 3.5084,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.016163334751169715,
|
272 |
+
"grad_norm": 0.37109375,
|
273 |
+
"learning_rate": 0.000475,
|
274 |
+
"loss": 3.4737,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.01658868566567418,
|
279 |
+
"grad_norm": 0.3515625,
|
280 |
+
"learning_rate": 0.0004875,
|
281 |
+
"loss": 3.6158,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.017014036580178648,
|
286 |
+
"grad_norm": 0.390625,
|
287 |
+
"learning_rate": 0.0005,
|
288 |
+
"loss": 3.3461,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.017014036580178648,
|
293 |
+
"eval_loss": 3.5420780181884766,
|
294 |
+
"eval_runtime": 63.4722,
|
295 |
+
"eval_samples_per_second": 4.884,
|
296 |
+
"eval_steps_per_second": 2.442,
|
297 |
+
"step": 40
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.017439387494683115,
|
301 |
+
"grad_norm": 0.294921875,
|
302 |
+
"learning_rate": 0.0004999997690011592,
|
303 |
+
"loss": 3.7458,
|
304 |
+
"step": 41
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.01786473840918758,
|
308 |
+
"grad_norm": 0.28515625,
|
309 |
+
"learning_rate": 0.0004999990760050636,
|
310 |
+
"loss": 3.5723,
|
311 |
+
"step": 42
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.018290089323692044,
|
315 |
+
"grad_norm": 0.2890625,
|
316 |
+
"learning_rate": 0.0004999979210129939,
|
317 |
+
"loss": 3.3797,
|
318 |
+
"step": 43
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.01871544023819651,
|
322 |
+
"grad_norm": 0.30078125,
|
323 |
+
"learning_rate": 0.0004999963040270845,
|
324 |
+
"loss": 3.3193,
|
325 |
+
"step": 44
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.019140791152700978,
|
329 |
+
"grad_norm": 0.28125,
|
330 |
+
"learning_rate": 0.0004999942250503237,
|
331 |
+
"loss": 3.5005,
|
332 |
+
"step": 45
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.019566142067205444,
|
336 |
+
"grad_norm": 0.31640625,
|
337 |
+
"learning_rate": 0.0004999916840865531,
|
338 |
+
"loss": 3.3954,
|
339 |
+
"step": 46
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.01999149298170991,
|
343 |
+
"grad_norm": 0.27734375,
|
344 |
+
"learning_rate": 0.0004999886811404688,
|
345 |
+
"loss": 3.352,
|
346 |
+
"step": 47
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.020416843896214378,
|
350 |
+
"grad_norm": 0.29296875,
|
351 |
+
"learning_rate": 0.0004999852162176199,
|
352 |
+
"loss": 3.4112,
|
353 |
+
"step": 48
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.020842194810718844,
|
357 |
+
"grad_norm": 0.330078125,
|
358 |
+
"learning_rate": 0.0004999812893244096,
|
359 |
+
"loss": 3.2618,
|
360 |
+
"step": 49
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.02126754572522331,
|
364 |
+
"grad_norm": 0.28515625,
|
365 |
+
"learning_rate": 0.0004999769004680949,
|
366 |
+
"loss": 3.2753,
|
367 |
+
"step": 50
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.021692896639727774,
|
371 |
+
"grad_norm": 0.330078125,
|
372 |
+
"learning_rate": 0.0004999720496567863,
|
373 |
+
"loss": 3.3618,
|
374 |
+
"step": 51
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.02211824755423224,
|
378 |
+
"grad_norm": 0.248046875,
|
379 |
+
"learning_rate": 0.000499966736899448,
|
380 |
+
"loss": 3.2411,
|
381 |
+
"step": 52
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.022543598468736707,
|
385 |
+
"grad_norm": 0.30078125,
|
386 |
+
"learning_rate": 0.0004999609622058979,
|
387 |
+
"loss": 3.2062,
|
388 |
+
"step": 53
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.022968949383241174,
|
392 |
+
"grad_norm": 0.255859375,
|
393 |
+
"learning_rate": 0.0004999547255868077,
|
394 |
+
"loss": 3.2935,
|
395 |
+
"step": 54
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.02339430029774564,
|
399 |
+
"grad_norm": 0.466796875,
|
400 |
+
"learning_rate": 0.0004999480270537025,
|
401 |
+
"loss": 3.2617,
|
402 |
+
"step": 55
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.023819651212250107,
|
406 |
+
"grad_norm": 0.25390625,
|
407 |
+
"learning_rate": 0.0004999408666189613,
|
408 |
+
"loss": 3.1139,
|
409 |
+
"step": 56
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.024245002126754574,
|
413 |
+
"grad_norm": 0.3203125,
|
414 |
+
"learning_rate": 0.0004999332442958163,
|
415 |
+
"loss": 3.2424,
|
416 |
+
"step": 57
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.02467035304125904,
|
420 |
+
"grad_norm": 0.255859375,
|
421 |
+
"learning_rate": 0.0004999251600983535,
|
422 |
+
"loss": 3.062,
|
423 |
+
"step": 58
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.025095703955763504,
|
427 |
+
"grad_norm": 0.2431640625,
|
428 |
+
"learning_rate": 0.0004999166140415127,
|
429 |
+
"loss": 3.2569,
|
430 |
+
"step": 59
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.02552105487026797,
|
434 |
+
"grad_norm": 0.27734375,
|
435 |
+
"learning_rate": 0.0004999076061410866,
|
436 |
+
"loss": 3.1508,
|
437 |
+
"step": 60
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.025946405784772437,
|
441 |
+
"grad_norm": 0.294921875,
|
442 |
+
"learning_rate": 0.0004998981364137219,
|
443 |
+
"loss": 3.3856,
|
444 |
+
"step": 61
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.026371756699276903,
|
448 |
+
"grad_norm": 0.306640625,
|
449 |
+
"learning_rate": 0.0004998882048769186,
|
450 |
+
"loss": 3.3477,
|
451 |
+
"step": 62
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.02679710761378137,
|
455 |
+
"grad_norm": 0.263671875,
|
456 |
+
"learning_rate": 0.0004998778115490299,
|
457 |
+
"loss": 3.1799,
|
458 |
+
"step": 63
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.027222458528285837,
|
462 |
+
"grad_norm": 0.255859375,
|
463 |
+
"learning_rate": 0.0004998669564492626,
|
464 |
+
"loss": 3.4091,
|
465 |
+
"step": 64
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.027647809442790303,
|
469 |
+
"grad_norm": 0.2734375,
|
470 |
+
"learning_rate": 0.0004998556395976771,
|
471 |
+
"loss": 3.1154,
|
472 |
+
"step": 65
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 0.028073160357294766,
|
476 |
+
"grad_norm": 0.2373046875,
|
477 |
+
"learning_rate": 0.0004998438610151865,
|
478 |
+
"loss": 3.1238,
|
479 |
+
"step": 66
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.028498511271799233,
|
483 |
+
"grad_norm": 0.25390625,
|
484 |
+
"learning_rate": 0.0004998316207235577,
|
485 |
+
"loss": 3.1522,
|
486 |
+
"step": 67
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 0.0289238621863037,
|
490 |
+
"grad_norm": 0.259765625,
|
491 |
+
"learning_rate": 0.0004998189187454107,
|
492 |
+
"loss": 3.1832,
|
493 |
+
"step": 68
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.029349213100808166,
|
497 |
+
"grad_norm": 0.25390625,
|
498 |
+
"learning_rate": 0.0004998057551042184,
|
499 |
+
"loss": 3.1962,
|
500 |
+
"step": 69
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.029774564015312633,
|
504 |
+
"grad_norm": 0.396484375,
|
505 |
+
"learning_rate": 0.0004997921298243073,
|
506 |
+
"loss": 3.1773,
|
507 |
+
"step": 70
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.0301999149298171,
|
511 |
+
"grad_norm": 0.267578125,
|
512 |
+
"learning_rate": 0.0004997780429308567,
|
513 |
+
"loss": 3.0593,
|
514 |
+
"step": 71
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.030625265844321566,
|
518 |
+
"grad_norm": 0.267578125,
|
519 |
+
"learning_rate": 0.000499763494449899,
|
520 |
+
"loss": 3.1213,
|
521 |
+
"step": 72
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.031050616758826033,
|
525 |
+
"grad_norm": 0.2578125,
|
526 |
+
"learning_rate": 0.0004997484844083197,
|
527 |
+
"loss": 3.0083,
|
528 |
+
"step": 73
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 0.031475967673330496,
|
532 |
+
"grad_norm": 0.220703125,
|
533 |
+
"learning_rate": 0.0004997330128338574,
|
534 |
+
"loss": 3.2451,
|
535 |
+
"step": 74
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 0.031901318587834966,
|
539 |
+
"grad_norm": 0.3046875,
|
540 |
+
"learning_rate": 0.0004997170797551031,
|
541 |
+
"loss": 3.145,
|
542 |
+
"step": 75
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.03232666950233943,
|
546 |
+
"grad_norm": 0.2578125,
|
547 |
+
"learning_rate": 0.0004997006852015013,
|
548 |
+
"loss": 2.9934,
|
549 |
+
"step": 76
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.0327520204168439,
|
553 |
+
"grad_norm": 0.30859375,
|
554 |
+
"learning_rate": 0.0004996838292033488,
|
555 |
+
"loss": 3.073,
|
556 |
+
"step": 77
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.03317737133134836,
|
560 |
+
"grad_norm": 0.2890625,
|
561 |
+
"learning_rate": 0.0004996665117917953,
|
562 |
+
"loss": 2.9907,
|
563 |
+
"step": 78
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.033602722245852826,
|
567 |
+
"grad_norm": 0.283203125,
|
568 |
+
"learning_rate": 0.0004996487329988433,
|
569 |
+
"loss": 3.1801,
|
570 |
+
"step": 79
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.034028073160357296,
|
574 |
+
"grad_norm": 0.265625,
|
575 |
+
"learning_rate": 0.0004996304928573477,
|
576 |
+
"loss": 3.2004,
|
577 |
+
"step": 80
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 0.034028073160357296,
|
581 |
+
"eval_loss": 3.158095121383667,
|
582 |
+
"eval_runtime": 63.4104,
|
583 |
+
"eval_samples_per_second": 4.889,
|
584 |
+
"eval_steps_per_second": 2.444,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.03445342407486176,
|
589 |
+
"grad_norm": 0.267578125,
|
590 |
+
"learning_rate": 0.0004996117914010164,
|
591 |
+
"loss": 3.1116,
|
592 |
+
"step": 81
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.03487877498936623,
|
596 |
+
"grad_norm": 0.236328125,
|
597 |
+
"learning_rate": 0.0004995926286644093,
|
598 |
+
"loss": 3.1122,
|
599 |
+
"step": 82
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.03530412590387069,
|
603 |
+
"grad_norm": 0.328125,
|
604 |
+
"learning_rate": 0.0004995730046829389,
|
605 |
+
"loss": 3.2151,
|
606 |
+
"step": 83
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.03572947681837516,
|
610 |
+
"grad_norm": 0.27734375,
|
611 |
+
"learning_rate": 0.0004995529194928704,
|
612 |
+
"loss": 3.1821,
|
613 |
+
"step": 84
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.036154827732879626,
|
617 |
+
"grad_norm": 0.29296875,
|
618 |
+
"learning_rate": 0.0004995323731313209,
|
619 |
+
"loss": 3.0647,
|
620 |
+
"step": 85
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.03658017864738409,
|
624 |
+
"grad_norm": 0.296875,
|
625 |
+
"learning_rate": 0.0004995113656362598,
|
626 |
+
"loss": 3.1514,
|
627 |
+
"step": 86
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.03700552956188856,
|
631 |
+
"grad_norm": 0.2373046875,
|
632 |
+
"learning_rate": 0.0004994898970465088,
|
633 |
+
"loss": 3.001,
|
634 |
+
"step": 87
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.03743088047639302,
|
638 |
+
"grad_norm": 0.263671875,
|
639 |
+
"learning_rate": 0.0004994679674017417,
|
640 |
+
"loss": 3.129,
|
641 |
+
"step": 88
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.03785623139089749,
|
645 |
+
"grad_norm": 0.232421875,
|
646 |
+
"learning_rate": 0.0004994455767424843,
|
647 |
+
"loss": 3.0329,
|
648 |
+
"step": 89
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.038281582305401955,
|
652 |
+
"grad_norm": 0.24609375,
|
653 |
+
"learning_rate": 0.0004994227251101143,
|
654 |
+
"loss": 3.0059,
|
655 |
+
"step": 90
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.038706933219906425,
|
659 |
+
"grad_norm": 0.271484375,
|
660 |
+
"learning_rate": 0.0004993994125468613,
|
661 |
+
"loss": 3.118,
|
662 |
+
"step": 91
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.03913228413441089,
|
666 |
+
"grad_norm": 0.234375,
|
667 |
+
"learning_rate": 0.0004993756390958067,
|
668 |
+
"loss": 3.1142,
|
669 |
+
"step": 92
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.03955763504891536,
|
673 |
+
"grad_norm": 0.306640625,
|
674 |
+
"learning_rate": 0.0004993514048008836,
|
675 |
+
"loss": 3.0709,
|
676 |
+
"step": 93
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.03998298596341982,
|
680 |
+
"grad_norm": 0.2890625,
|
681 |
+
"learning_rate": 0.0004993267097068768,
|
682 |
+
"loss": 3.0208,
|
683 |
+
"step": 94
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.040408336877924285,
|
687 |
+
"grad_norm": 0.2236328125,
|
688 |
+
"learning_rate": 0.0004993015538594226,
|
689 |
+
"loss": 3.0419,
|
690 |
+
"step": 95
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.040833687792428755,
|
694 |
+
"grad_norm": 0.224609375,
|
695 |
+
"learning_rate": 0.0004992759373050087,
|
696 |
+
"loss": 3.0623,
|
697 |
+
"step": 96
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.04125903870693322,
|
701 |
+
"grad_norm": 0.2421875,
|
702 |
+
"learning_rate": 0.0004992498600909742,
|
703 |
+
"loss": 3.021,
|
704 |
+
"step": 97
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.04168438962143769,
|
708 |
+
"grad_norm": 0.24609375,
|
709 |
+
"learning_rate": 0.0004992233222655099,
|
710 |
+
"loss": 2.9667,
|
711 |
+
"step": 98
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.04210974053594215,
|
715 |
+
"grad_norm": 0.25390625,
|
716 |
+
"learning_rate": 0.000499196323877657,
|
717 |
+
"loss": 3.1639,
|
718 |
+
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.04253509145044662,
|
722 |
+
"grad_norm": 0.2080078125,
|
723 |
+
"learning_rate": 0.0004991688649773087,
|
724 |
+
"loss": 3.0522,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.042960442364951085,
|
729 |
+
"grad_norm": 0.265625,
|
730 |
+
"learning_rate": 0.0004991409456152083,
|
731 |
+
"loss": 3.0198,
|
732 |
+
"step": 101
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.04338579327945555,
|
736 |
+
"grad_norm": 0.291015625,
|
737 |
+
"learning_rate": 0.000499112565842951,
|
738 |
+
"loss": 3.0343,
|
739 |
+
"step": 102
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.04381114419396002,
|
743 |
+
"grad_norm": 0.259765625,
|
744 |
+
"learning_rate": 0.000499083725712982,
|
745 |
+
"loss": 2.9781,
|
746 |
+
"step": 103
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.04423649510846448,
|
750 |
+
"grad_norm": 0.234375,
|
751 |
+
"learning_rate": 0.0004990544252785979,
|
752 |
+
"loss": 3.0414,
|
753 |
+
"step": 104
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.04466184602296895,
|
757 |
+
"grad_norm": 0.2080078125,
|
758 |
+
"learning_rate": 0.0004990246645939453,
|
759 |
+
"loss": 2.9408,
|
760 |
+
"step": 105
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 0.045087196937473414,
|
764 |
+
"grad_norm": 0.236328125,
|
765 |
+
"learning_rate": 0.000498994443714022,
|
766 |
+
"loss": 3.1833,
|
767 |
+
"step": 106
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 0.045512547851977884,
|
771 |
+
"grad_norm": 0.2392578125,
|
772 |
+
"learning_rate": 0.0004989637626946757,
|
773 |
+
"loss": 3.1308,
|
774 |
+
"step": 107
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.04593789876648235,
|
778 |
+
"grad_norm": 0.25390625,
|
779 |
+
"learning_rate": 0.0004989326215926046,
|
780 |
+
"loss": 3.0492,
|
781 |
+
"step": 108
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.04636324968098681,
|
785 |
+
"grad_norm": 0.19921875,
|
786 |
+
"learning_rate": 0.0004989010204653573,
|
787 |
+
"loss": 3.2026,
|
788 |
+
"step": 109
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.04678860059549128,
|
792 |
+
"grad_norm": 0.2255859375,
|
793 |
+
"learning_rate": 0.0004988689593713325,
|
794 |
+
"loss": 2.9132,
|
795 |
+
"step": 110
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.047213951509995744,
|
799 |
+
"grad_norm": 0.2236328125,
|
800 |
+
"learning_rate": 0.0004988364383697785,
|
801 |
+
"loss": 3.0651,
|
802 |
+
"step": 111
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 0.047639302424500214,
|
806 |
+
"grad_norm": 0.275390625,
|
807 |
+
"learning_rate": 0.000498803457520794,
|
808 |
+
"loss": 2.9879,
|
809 |
+
"step": 112
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 0.04806465333900468,
|
813 |
+
"grad_norm": 0.2333984375,
|
814 |
+
"learning_rate": 0.0004987700168853273,
|
815 |
+
"loss": 2.96,
|
816 |
+
"step": 113
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 0.04849000425350915,
|
820 |
+
"grad_norm": 0.263671875,
|
821 |
+
"learning_rate": 0.0004987361165251763,
|
822 |
+
"loss": 3.0139,
|
823 |
+
"step": 114
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.04891535516801361,
|
827 |
+
"grad_norm": 0.240234375,
|
828 |
+
"learning_rate": 0.0004987017565029886,
|
829 |
+
"loss": 2.8503,
|
830 |
+
"step": 115
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.04934070608251808,
|
834 |
+
"grad_norm": 0.228515625,
|
835 |
+
"learning_rate": 0.0004986669368822612,
|
836 |
+
"loss": 2.9551,
|
837 |
+
"step": 116
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.049766056997022544,
|
841 |
+
"grad_norm": 0.255859375,
|
842 |
+
"learning_rate": 0.0004986316577273404,
|
843 |
+
"loss": 2.9945,
|
844 |
+
"step": 117
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 0.05019140791152701,
|
848 |
+
"grad_norm": 0.2080078125,
|
849 |
+
"learning_rate": 0.0004985959191034218,
|
850 |
+
"loss": 2.9352,
|
851 |
+
"step": 118
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 0.05061675882603148,
|
855 |
+
"grad_norm": 0.291015625,
|
856 |
+
"learning_rate": 0.0004985597210765501,
|
857 |
+
"loss": 3.3124,
|
858 |
+
"step": 119
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 0.05104210974053594,
|
862 |
+
"grad_norm": 0.2216796875,
|
863 |
+
"learning_rate": 0.0004985230637136189,
|
864 |
+
"loss": 3.0095,
|
865 |
+
"step": 120
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 0.05104210974053594,
|
869 |
+
"eval_loss": 3.0505518913269043,
|
870 |
+
"eval_runtime": 63.4046,
|
871 |
+
"eval_samples_per_second": 4.889,
|
872 |
+
"eval_steps_per_second": 2.445,
|
873 |
+
"step": 120
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.05146746065504041,
|
877 |
+
"grad_norm": 0.228515625,
|
878 |
+
"learning_rate": 0.0004984859470823705,
|
879 |
+
"loss": 2.7989,
|
880 |
+
"step": 121
|
881 |
+
},
|
882 |
+
{
|
883 |
+
"epoch": 0.051892811569544874,
|
884 |
+
"grad_norm": 0.259765625,
|
885 |
+
"learning_rate": 0.0004984483712513962,
|
886 |
+
"loss": 3.0605,
|
887 |
+
"step": 122
|
888 |
+
},
|
889 |
+
{
|
890 |
+
"epoch": 0.052318162484049344,
|
891 |
+
"grad_norm": 0.2109375,
|
892 |
+
"learning_rate": 0.0004984103362901358,
|
893 |
+
"loss": 3.137,
|
894 |
+
"step": 123
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.05274351339855381,
|
898 |
+
"grad_norm": 0.25390625,
|
899 |
+
"learning_rate": 0.0004983718422688776,
|
900 |
+
"loss": 3.0276,
|
901 |
+
"step": 124
|
902 |
+
},
|
903 |
+
{
|
904 |
+
"epoch": 0.05316886431305827,
|
905 |
+
"grad_norm": 0.255859375,
|
906 |
+
"learning_rate": 0.0004983328892587582,
|
907 |
+
"loss": 3.1853,
|
908 |
+
"step": 125
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 0.05359421522756274,
|
912 |
+
"grad_norm": 0.2490234375,
|
913 |
+
"learning_rate": 0.0004982934773317624,
|
914 |
+
"loss": 3.0186,
|
915 |
+
"step": 126
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 0.0540195661420672,
|
919 |
+
"grad_norm": 0.193359375,
|
920 |
+
"learning_rate": 0.0004982536065607228,
|
921 |
+
"loss": 2.963,
|
922 |
+
"step": 127
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 0.05444491705657167,
|
926 |
+
"grad_norm": 0.25390625,
|
927 |
+
"learning_rate": 0.0004982132770193206,
|
928 |
+
"loss": 3.1289,
|
929 |
+
"step": 128
|
930 |
+
},
|
931 |
+
{
|
932 |
+
"epoch": 0.054870267971076137,
|
933 |
+
"grad_norm": 0.2421875,
|
934 |
+
"learning_rate": 0.0004981724887820842,
|
935 |
+
"loss": 2.9712,
|
936 |
+
"step": 129
|
937 |
+
},
|
938 |
+
{
|
939 |
+
"epoch": 0.05529561888558061,
|
940 |
+
"grad_norm": 0.208984375,
|
941 |
+
"learning_rate": 0.00049813124192439,
|
942 |
+
"loss": 3.0866,
|
943 |
+
"step": 130
|
944 |
+
},
|
945 |
+
{
|
946 |
+
"epoch": 0.05572096980008507,
|
947 |
+
"grad_norm": 0.216796875,
|
948 |
+
"learning_rate": 0.0004980895365224617,
|
949 |
+
"loss": 3.0152,
|
950 |
+
"step": 131
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 0.05614632071458953,
|
954 |
+
"grad_norm": 0.24609375,
|
955 |
+
"learning_rate": 0.0004980473726533706,
|
956 |
+
"loss": 3.1521,
|
957 |
+
"step": 132
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.056571671629094,
|
961 |
+
"grad_norm": 0.2353515625,
|
962 |
+
"learning_rate": 0.000498004750395035,
|
963 |
+
"loss": 2.8592,
|
964 |
+
"step": 133
|
965 |
+
},
|
966 |
+
{
|
967 |
+
"epoch": 0.056997022543598466,
|
968 |
+
"grad_norm": 0.33203125,
|
969 |
+
"learning_rate": 0.0004979616698262206,
|
970 |
+
"loss": 3.1706,
|
971 |
+
"step": 134
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 0.057422373458102936,
|
975 |
+
"grad_norm": 0.23828125,
|
976 |
+
"learning_rate": 0.0004979181310265397,
|
977 |
+
"loss": 3.1256,
|
978 |
+
"step": 135
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 0.0578477243726074,
|
982 |
+
"grad_norm": 0.2470703125,
|
983 |
+
"learning_rate": 0.0004978741340764519,
|
984 |
+
"loss": 3.0759,
|
985 |
+
"step": 136
|
986 |
+
},
|
987 |
+
{
|
988 |
+
"epoch": 0.05827307528711187,
|
989 |
+
"grad_norm": 0.212890625,
|
990 |
+
"learning_rate": 0.0004978296790572629,
|
991 |
+
"loss": 2.9902,
|
992 |
+
"step": 137
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 0.05869842620161633,
|
996 |
+
"grad_norm": 0.2275390625,
|
997 |
+
"learning_rate": 0.0004977847660511251,
|
998 |
+
"loss": 3.0442,
|
999 |
+
"step": 138
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.0591237771161208,
|
1003 |
+
"grad_norm": 0.322265625,
|
1004 |
+
"learning_rate": 0.0004977393951410376,
|
1005 |
+
"loss": 3.0979,
|
1006 |
+
"step": 139
|
1007 |
+
},
|
1008 |
+
{
|
1009 |
+
"epoch": 0.059549128030625266,
|
1010 |
+
"grad_norm": 0.28125,
|
1011 |
+
"learning_rate": 0.0004976935664108452,
|
1012 |
+
"loss": 3.02,
|
1013 |
+
"step": 140
|
1014 |
+
},
|
1015 |
+
{
|
1016 |
+
"epoch": 0.05997447894512973,
|
1017 |
+
"grad_norm": 0.2314453125,
|
1018 |
+
"learning_rate": 0.0004976472799452391,
|
1019 |
+
"loss": 2.9694,
|
1020 |
+
"step": 141
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 0.0603998298596342,
|
1024 |
+
"grad_norm": 0.328125,
|
1025 |
+
"learning_rate": 0.0004976005358297562,
|
1026 |
+
"loss": 3.0462,
|
1027 |
+
"step": 142
|
1028 |
+
},
|
1029 |
+
{
|
1030 |
+
"epoch": 0.06082518077413866,
|
1031 |
+
"grad_norm": 0.2216796875,
|
1032 |
+
"learning_rate": 0.0004975533341507792,
|
1033 |
+
"loss": 2.9253,
|
1034 |
+
"step": 143
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 0.06125053168864313,
|
1038 |
+
"grad_norm": 0.224609375,
|
1039 |
+
"learning_rate": 0.0004975056749955363,
|
1040 |
+
"loss": 2.9572,
|
1041 |
+
"step": 144
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.061675882603147596,
|
1045 |
+
"grad_norm": 0.2294921875,
|
1046 |
+
"learning_rate": 0.0004974575584521013,
|
1047 |
+
"loss": 2.9693,
|
1048 |
+
"step": 145
|
1049 |
+
},
|
1050 |
+
{
|
1051 |
+
"epoch": 0.062101233517652066,
|
1052 |
+
"grad_norm": 0.328125,
|
1053 |
+
"learning_rate": 0.000497408984609393,
|
1054 |
+
"loss": 2.8548,
|
1055 |
+
"step": 146
|
1056 |
+
},
|
1057 |
+
{
|
1058 |
+
"epoch": 0.06252658443215653,
|
1059 |
+
"grad_norm": 0.240234375,
|
1060 |
+
"learning_rate": 0.0004973599535571756,
|
1061 |
+
"loss": 3.0627,
|
1062 |
+
"step": 147
|
1063 |
+
},
|
1064 |
+
{
|
1065 |
+
"epoch": 0.06295193534666099,
|
1066 |
+
"grad_norm": 0.3359375,
|
1067 |
+
"learning_rate": 0.0004973104653860578,
|
1068 |
+
"loss": 3.2153,
|
1069 |
+
"step": 148
|
1070 |
+
},
|
1071 |
+
{
|
1072 |
+
"epoch": 0.06337728626116546,
|
1073 |
+
"grad_norm": 0.2197265625,
|
1074 |
+
"learning_rate": 0.0004972605201874934,
|
1075 |
+
"loss": 2.9571,
|
1076 |
+
"step": 149
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 0.06380263717566993,
|
1080 |
+
"grad_norm": 0.24609375,
|
1081 |
+
"learning_rate": 0.0004972101180537806,
|
1082 |
+
"loss": 2.7965,
|
1083 |
+
"step": 150
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 0.0642279880901744,
|
1087 |
+
"grad_norm": 0.2060546875,
|
1088 |
+
"learning_rate": 0.0004971592590780621,
|
1089 |
+
"loss": 2.961,
|
1090 |
+
"step": 151
|
1091 |
+
},
|
1092 |
+
{
|
1093 |
+
"epoch": 0.06465333900467886,
|
1094 |
+
"grad_norm": 0.35546875,
|
1095 |
+
"learning_rate": 0.0004971079433543249,
|
1096 |
+
"loss": 3.0112,
|
1097 |
+
"step": 152
|
1098 |
+
},
|
1099 |
+
{
|
1100 |
+
"epoch": 0.06507868991918332,
|
1101 |
+
"grad_norm": 0.31640625,
|
1102 |
+
"learning_rate": 0.0004970561709773999,
|
1103 |
+
"loss": 2.9675,
|
1104 |
+
"step": 153
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 0.0655040408336878,
|
1108 |
+
"grad_norm": 0.2294921875,
|
1109 |
+
"learning_rate": 0.0004970039420429621,
|
1110 |
+
"loss": 2.9413,
|
1111 |
+
"step": 154
|
1112 |
+
},
|
1113 |
+
{
|
1114 |
+
"epoch": 0.06592939174819226,
|
1115 |
+
"grad_norm": 0.2158203125,
|
1116 |
+
"learning_rate": 0.0004969512566475299,
|
1117 |
+
"loss": 2.9601,
|
1118 |
+
"step": 155
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 0.06635474266269673,
|
1122 |
+
"grad_norm": 0.2216796875,
|
1123 |
+
"learning_rate": 0.0004968981148884655,
|
1124 |
+
"loss": 3.1641,
|
1125 |
+
"step": 156
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 0.06678009357720119,
|
1129 |
+
"grad_norm": 0.28125,
|
1130 |
+
"learning_rate": 0.0004968445168639743,
|
1131 |
+
"loss": 3.0247,
|
1132 |
+
"step": 157
|
1133 |
+
},
|
1134 |
+
{
|
1135 |
+
"epoch": 0.06720544449170565,
|
1136 |
+
"grad_norm": 0.376953125,
|
1137 |
+
"learning_rate": 0.0004967904626731051,
|
1138 |
+
"loss": 2.9328,
|
1139 |
+
"step": 158
|
1140 |
+
},
|
1141 |
+
{
|
1142 |
+
"epoch": 0.06763079540621013,
|
1143 |
+
"grad_norm": 0.263671875,
|
1144 |
+
"learning_rate": 0.0004967359524157496,
|
1145 |
+
"loss": 3.1119,
|
1146 |
+
"step": 159
|
1147 |
+
},
|
1148 |
+
{
|
1149 |
+
"epoch": 0.06805614632071459,
|
1150 |
+
"grad_norm": 0.263671875,
|
1151 |
+
"learning_rate": 0.0004966809861926419,
|
1152 |
+
"loss": 2.714,
|
1153 |
+
"step": 160
|
1154 |
+
},
|
1155 |
+
{
|
1156 |
+
"epoch": 0.06805614632071459,
|
1157 |
+
"eval_loss": 3.0168392658233643,
|
1158 |
+
"eval_runtime": 63.2627,
|
1159 |
+
"eval_samples_per_second": 4.9,
|
1160 |
+
"eval_steps_per_second": 2.45,
|
1161 |
+
"step": 160
|
1162 |
+
}
|
1163 |
+
],
|
1164 |
+
"logging_steps": 1,
|
1165 |
+
"max_steps": 2351,
|
1166 |
+
"num_input_tokens_seen": 0,
|
1167 |
+
"num_train_epochs": 1,
|
1168 |
+
"save_steps": 40,
|
1169 |
+
"stateful_callbacks": {
|
1170 |
+
"EarlyStoppingCallback": {
|
1171 |
+
"args": {
|
1172 |
+
"early_stopping_patience": 1,
|
1173 |
+
"early_stopping_threshold": 0.0
|
1174 |
+
},
|
1175 |
+
"attributes": {
|
1176 |
+
"early_stopping_patience_counter": 0
|
1177 |
+
}
|
1178 |
+
},
|
1179 |
+
"TrainerControl": {
|
1180 |
+
"args": {
|
1181 |
+
"should_epoch_stop": false,
|
1182 |
+
"should_evaluate": false,
|
1183 |
+
"should_log": false,
|
1184 |
+
"should_save": true,
|
1185 |
+
"should_training_stop": false
|
1186 |
+
},
|
1187 |
+
"attributes": {}
|
1188 |
+
}
|
1189 |
+
},
|
1190 |
+
"total_flos": 2.175544816828416e+16,
|
1191 |
+
"train_batch_size": 2,
|
1192 |
+
"trial_name": null,
|
1193 |
+
"trial_params": null
|
1194 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:934452fd6c0d51f69580afe8ea94e27b1b2d6d0352e0dc573b287fafd9954dbf
|
3 |
+
size 5560
|