End of training
Browse files
all_results.json
CHANGED
@@ -1,5 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 0.9936305732484076,
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 3.820096642099446e+17,
|
4 |
"train_loss": 1.8799311350553463,
|
5 |
"train_runtime": 1320.5477,
|
|
|
1 |
{
|
2 |
"epoch": 0.9936305732484076,
|
3 |
+
"eval_loss": 1.9203951358795166,
|
4 |
+
"eval_runtime": 1.4435,
|
5 |
+
"eval_samples": 16,
|
6 |
+
"eval_samples_per_second": 2.771,
|
7 |
+
"eval_steps_per_second": 0.693,
|
8 |
"total_flos": 3.820096642099446e+17,
|
9 |
"train_loss": 1.8799311350553463,
|
10 |
"train_runtime": 1320.5477,
|
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_attn_implementation_autoset": true,
|
3 |
+
"_name_or_path": "mistralai/Mistral-7B-v0.3",
|
4 |
+
"architectures": [
|
5 |
+
"MistralForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 32768,
|
9 |
+
"eos_token_id": 32769,
|
10 |
+
"head_dim": 128,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 4096,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 14336,
|
15 |
+
"max_position_embeddings": 32768,
|
16 |
+
"model_type": "mistral",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 32,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"pad_token_id": 32769,
|
21 |
+
"quantization_config": {
|
22 |
+
"_load_in_4bit": false,
|
23 |
+
"_load_in_8bit": true,
|
24 |
+
"bnb_4bit_compute_dtype": "float32",
|
25 |
+
"bnb_4bit_quant_storage": "uint8",
|
26 |
+
"bnb_4bit_quant_type": "fp4",
|
27 |
+
"bnb_4bit_use_double_quant": false,
|
28 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
29 |
+
"llm_int8_has_fp16_weight": false,
|
30 |
+
"llm_int8_skip_modules": null,
|
31 |
+
"llm_int8_threshold": 6.0,
|
32 |
+
"load_in_4bit": false,
|
33 |
+
"load_in_8bit": true,
|
34 |
+
"quant_method": "bitsandbytes"
|
35 |
+
},
|
36 |
+
"rms_norm_eps": 1e-05,
|
37 |
+
"rope_theta": 1000000.0,
|
38 |
+
"sliding_window": null,
|
39 |
+
"tie_word_embeddings": false,
|
40 |
+
"transformers_version": "4.46.2",
|
41 |
+
"use_cache": true,
|
42 |
+
"vocab_size": 32770
|
43 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9936305732484076,
|
3 |
+
"eval_loss": 1.9203951358795166,
|
4 |
+
"eval_runtime": 1.4435,
|
5 |
+
"eval_samples": 16,
|
6 |
+
"eval_samples_per_second": 2.771,
|
7 |
+
"eval_steps_per_second": 0.693
|
8 |
+
}
|
runs/Nov17_10-25-16_main-ah-train-0-0/events.out.tfevents.1731859060.main-ah-train-0-0.456.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd6864c92d0b7e160dcfe98aefbd765a5278cedd68bd2f4e9ed3a00d8b725b76
|
3 |
+
size 354
|