Training in progress, step 300, checkpoint
Browse files- last-checkpoint/README.md +60 -0
- last-checkpoint/adapter_config.json +26 -0
- last-checkpoint/adapter_model.safetensors +3 -0
- last-checkpoint/global_step300/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step300/mp_rank_00_model_states.pt +3 -0
- last-checkpoint/latest +1 -0
- last-checkpoint/rng_state_0.pth +3 -0
- last-checkpoint/rng_state_1.pth +3 -0
- last-checkpoint/trainer_state.json +1827 -0
- last-checkpoint/training_args.bin +3 -0
- last-checkpoint/zero_to_fp32.py +587 -0
last-checkpoint/README.md
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- quant_method: bitsandbytes
|
9 |
+
- load_in_8bit: False
|
10 |
+
- load_in_4bit: True
|
11 |
+
- llm_int8_threshold: 6.0
|
12 |
+
- llm_int8_skip_modules: None
|
13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
14 |
+
- llm_int8_has_fp16_weight: True
|
15 |
+
- bnb_4bit_quant_type: nf4
|
16 |
+
- bnb_4bit_use_double_quant: True
|
17 |
+
- bnb_4bit_compute_dtype: bfloat16
|
18 |
+
|
19 |
+
The following `bitsandbytes` quantization config was used during training:
|
20 |
+
- quant_method: bitsandbytes
|
21 |
+
- load_in_8bit: False
|
22 |
+
- load_in_4bit: True
|
23 |
+
- llm_int8_threshold: 6.0
|
24 |
+
- llm_int8_skip_modules: None
|
25 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
26 |
+
- llm_int8_has_fp16_weight: True
|
27 |
+
- bnb_4bit_quant_type: nf4
|
28 |
+
- bnb_4bit_use_double_quant: True
|
29 |
+
- bnb_4bit_compute_dtype: bfloat16
|
30 |
+
|
31 |
+
The following `bitsandbytes` quantization config was used during training:
|
32 |
+
- quant_method: bitsandbytes
|
33 |
+
- load_in_8bit: False
|
34 |
+
- load_in_4bit: True
|
35 |
+
- llm_int8_threshold: 6.0
|
36 |
+
- llm_int8_skip_modules: None
|
37 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
38 |
+
- llm_int8_has_fp16_weight: True
|
39 |
+
- bnb_4bit_quant_type: nf4
|
40 |
+
- bnb_4bit_use_double_quant: True
|
41 |
+
- bnb_4bit_compute_dtype: bfloat16
|
42 |
+
|
43 |
+
The following `bitsandbytes` quantization config was used during training:
|
44 |
+
- quant_method: bitsandbytes
|
45 |
+
- load_in_8bit: False
|
46 |
+
- load_in_4bit: True
|
47 |
+
- llm_int8_threshold: 6.0
|
48 |
+
- llm_int8_skip_modules: None
|
49 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
50 |
+
- llm_int8_has_fp16_weight: True
|
51 |
+
- bnb_4bit_quant_type: nf4
|
52 |
+
- bnb_4bit_use_double_quant: True
|
53 |
+
- bnb_4bit_compute_dtype: bfloat16
|
54 |
+
### Framework versions
|
55 |
+
|
56 |
+
- PEFT 0.5.0
|
57 |
+
- PEFT 0.5.0
|
58 |
+
- PEFT 0.5.0
|
59 |
+
|
60 |
+
- PEFT 0.5.0
|
last-checkpoint/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 32,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 64,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"q_proj",
|
18 |
+
"v_proj",
|
19 |
+
"up_proj",
|
20 |
+
"k_proj",
|
21 |
+
"o_proj",
|
22 |
+
"gate_proj",
|
23 |
+
"down_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
last-checkpoint/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3292b605913b97d05f8a16583a995dc94fc1588668a402e1784a8e0868dee3df
|
3 |
+
size 335605144
|
last-checkpoint/global_step300/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70fe0a71c8f26897be2331c9786b68c4e3482c41ef6d0a297eaa3066626d6a24
|
3 |
+
size 1006661136
|
last-checkpoint/global_step300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd822321034aab707986931ca61ce44b4fb3a9646458d392113c239f8245c51c
|
3 |
+
size 1006661264
|
last-checkpoint/global_step300/mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:603c77216377256c089cc0f1eac3f60042a6c86407f3a941e089fe1b31998d0b
|
3 |
+
size 8365038600
|
last-checkpoint/latest
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
global_step300
|
last-checkpoint/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2981b7d07dbd40ffa300bdce2b2824c636c4c181ebf87cf28fe3945ccbe0c23b
|
3 |
+
size 14512
|
last-checkpoint/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04ee61073b659003784ef66df69f7c6a27137bf83502c0cfaa924c54bd6a6078
|
3 |
+
size 14512
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,1827 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.3873900175094604,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-300",
|
4 |
+
"epoch": 1.6666666666666665,
|
5 |
+
"eval_steps": 300,
|
6 |
+
"global_step": 300,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01,
|
13 |
+
"learning_rate": 0.0,
|
14 |
+
"loss": 2.8496,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 3.0102999566398115e-05,
|
20 |
+
"loss": 2.3809,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.02,
|
25 |
+
"learning_rate": 4.771212547196624e-05,
|
26 |
+
"loss": 2.3604,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.02,
|
31 |
+
"learning_rate": 6.020599913279623e-05,
|
32 |
+
"loss": 2.2425,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.03,
|
37 |
+
"learning_rate": 6.989700043360187e-05,
|
38 |
+
"loss": 2.0888,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.03,
|
43 |
+
"learning_rate": 7.781512503836436e-05,
|
44 |
+
"loss": 1.9669,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.04,
|
49 |
+
"learning_rate": 8.450980400142567e-05,
|
50 |
+
"loss": 1.8589,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.04,
|
55 |
+
"learning_rate": 9.030899869919434e-05,
|
56 |
+
"loss": 1.7722,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.05,
|
61 |
+
"learning_rate": 9.542425094393248e-05,
|
62 |
+
"loss": 1.6765,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.06,
|
67 |
+
"learning_rate": 9.999999999999999e-05,
|
68 |
+
"loss": 1.611,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.06,
|
73 |
+
"learning_rate": 0.00010413926851582249,
|
74 |
+
"loss": 1.5547,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.07,
|
79 |
+
"learning_rate": 0.00010791812460476247,
|
80 |
+
"loss": 1.5342,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.07,
|
85 |
+
"learning_rate": 0.00011139433523068365,
|
86 |
+
"loss": 1.5394,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.08,
|
91 |
+
"learning_rate": 0.00011461280356782378,
|
92 |
+
"loss": 1.5291,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.08,
|
97 |
+
"learning_rate": 0.00011760912590556812,
|
98 |
+
"loss": 1.4864,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.09,
|
103 |
+
"learning_rate": 0.00012041199826559246,
|
104 |
+
"loss": 1.4938,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.09,
|
109 |
+
"learning_rate": 0.0001230448921378274,
|
110 |
+
"loss": 1.4965,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.1,
|
115 |
+
"learning_rate": 0.00012552725051033058,
|
116 |
+
"loss": 1.4751,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.11,
|
121 |
+
"learning_rate": 0.00012787536009528286,
|
122 |
+
"loss": 1.4768,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.11,
|
127 |
+
"learning_rate": 0.0001301029995663981,
|
128 |
+
"loss": 1.4578,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.12,
|
133 |
+
"learning_rate": 0.0001322219294733919,
|
134 |
+
"loss": 1.4627,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.12,
|
139 |
+
"learning_rate": 0.00013424226808222061,
|
140 |
+
"loss": 1.4535,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.13,
|
145 |
+
"learning_rate": 0.00013617278360175927,
|
146 |
+
"loss": 1.451,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.13,
|
151 |
+
"learning_rate": 0.0001380211241711606,
|
152 |
+
"loss": 1.4446,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.14,
|
157 |
+
"learning_rate": 0.00013979400086720374,
|
158 |
+
"loss": 1.4443,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.14,
|
163 |
+
"learning_rate": 0.00014149733479708177,
|
164 |
+
"loss": 1.4401,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.15,
|
169 |
+
"learning_rate": 0.00014313637641589873,
|
170 |
+
"loss": 1.4506,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.16,
|
175 |
+
"learning_rate": 0.0001447158031342219,
|
176 |
+
"loss": 1.4289,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.16,
|
181 |
+
"learning_rate": 0.0001462397997898956,
|
182 |
+
"loss": 1.433,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.17,
|
187 |
+
"learning_rate": 0.00014771212547196622,
|
188 |
+
"loss": 1.4335,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.17,
|
193 |
+
"learning_rate": 0.00014913616938342725,
|
194 |
+
"loss": 1.4263,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.18,
|
199 |
+
"learning_rate": 0.0001505149978319906,
|
200 |
+
"loss": 1.4278,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.18,
|
205 |
+
"learning_rate": 0.00015185139398778873,
|
206 |
+
"loss": 1.4219,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.19,
|
211 |
+
"learning_rate": 0.0001531478917042255,
|
212 |
+
"loss": 1.4195,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.19,
|
217 |
+
"learning_rate": 0.00015440680443502754,
|
218 |
+
"loss": 1.4314,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.2,
|
223 |
+
"learning_rate": 0.00015563025007672872,
|
224 |
+
"loss": 1.4326,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.21,
|
229 |
+
"learning_rate": 0.0001568201724066995,
|
230 |
+
"loss": 1.4224,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.21,
|
235 |
+
"learning_rate": 0.000157978359661681,
|
236 |
+
"loss": 1.4233,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.22,
|
241 |
+
"learning_rate": 0.0001591064607026499,
|
242 |
+
"loss": 1.417,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.22,
|
247 |
+
"learning_rate": 0.0001602059991327962,
|
248 |
+
"loss": 1.417,
|
249 |
+
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.23,
|
253 |
+
"learning_rate": 0.00016127838567197352,
|
254 |
+
"loss": 1.41,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.23,
|
259 |
+
"learning_rate": 0.00016232492903979004,
|
260 |
+
"loss": 1.4319,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.24,
|
265 |
+
"learning_rate": 0.00016334684555795862,
|
266 |
+
"loss": 1.4218,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.24,
|
271 |
+
"learning_rate": 0.00016434526764861872,
|
272 |
+
"loss": 1.4196,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.25,
|
277 |
+
"learning_rate": 0.00016532125137753433,
|
278 |
+
"loss": 1.4157,
|
279 |
+
"step": 45
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.26,
|
283 |
+
"learning_rate": 0.0001662757831681574,
|
284 |
+
"loss": 1.4251,
|
285 |
+
"step": 46
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.26,
|
289 |
+
"learning_rate": 0.0001672097857935717,
|
290 |
+
"loss": 1.4248,
|
291 |
+
"step": 47
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.27,
|
295 |
+
"learning_rate": 0.0001681241237375587,
|
296 |
+
"loss": 1.4189,
|
297 |
+
"step": 48
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.27,
|
301 |
+
"learning_rate": 0.00016901960800285134,
|
302 |
+
"loss": 1.4165,
|
303 |
+
"step": 49
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.28,
|
307 |
+
"learning_rate": 0.00016989700043360185,
|
308 |
+
"loss": 1.4167,
|
309 |
+
"step": 50
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.28,
|
313 |
+
"learning_rate": 0.00017075701760979362,
|
314 |
+
"loss": 1.4146,
|
315 |
+
"step": 51
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.29,
|
319 |
+
"learning_rate": 0.0001716003343634799,
|
320 |
+
"loss": 1.4133,
|
321 |
+
"step": 52
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.29,
|
325 |
+
"learning_rate": 0.0001724275869600789,
|
326 |
+
"loss": 1.4074,
|
327 |
+
"step": 53
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.3,
|
331 |
+
"learning_rate": 0.00017323937598229684,
|
332 |
+
"loss": 1.4164,
|
333 |
+
"step": 54
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.31,
|
337 |
+
"learning_rate": 0.00017403626894942436,
|
338 |
+
"loss": 1.4178,
|
339 |
+
"step": 55
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.31,
|
343 |
+
"learning_rate": 0.00017481880270062004,
|
344 |
+
"loss": 1.4239,
|
345 |
+
"step": 56
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.32,
|
349 |
+
"learning_rate": 0.00017558748556724914,
|
350 |
+
"loss": 1.4074,
|
351 |
+
"step": 57
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.32,
|
355 |
+
"learning_rate": 0.0001763427993562937,
|
356 |
+
"loss": 1.4118,
|
357 |
+
"step": 58
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.33,
|
361 |
+
"learning_rate": 0.0001770852011642144,
|
362 |
+
"loss": 1.4088,
|
363 |
+
"step": 59
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.33,
|
367 |
+
"learning_rate": 0.00017781512503836432,
|
368 |
+
"loss": 1.4211,
|
369 |
+
"step": 60
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.34,
|
373 |
+
"learning_rate": 0.00017853298350107669,
|
374 |
+
"loss": 1.4019,
|
375 |
+
"step": 61
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.34,
|
379 |
+
"learning_rate": 0.00017923916894982539,
|
380 |
+
"loss": 1.4284,
|
381 |
+
"step": 62
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.35,
|
385 |
+
"learning_rate": 0.00017993405494535816,
|
386 |
+
"loss": 1.4092,
|
387 |
+
"step": 63
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.36,
|
391 |
+
"learning_rate": 0.00018061799739838867,
|
392 |
+
"loss": 1.415,
|
393 |
+
"step": 64
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.36,
|
397 |
+
"learning_rate": 0.00018129133566428552,
|
398 |
+
"loss": 1.4249,
|
399 |
+
"step": 65
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.37,
|
403 |
+
"learning_rate": 0.00018195439355418684,
|
404 |
+
"loss": 1.4114,
|
405 |
+
"step": 66
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.37,
|
409 |
+
"learning_rate": 0.0001826074802700826,
|
410 |
+
"loss": 1.4209,
|
411 |
+
"step": 67
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.38,
|
415 |
+
"learning_rate": 0.00018325089127062364,
|
416 |
+
"loss": 1.4141,
|
417 |
+
"step": 68
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.38,
|
421 |
+
"learning_rate": 0.00018388490907372552,
|
422 |
+
"loss": 1.4092,
|
423 |
+
"step": 69
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.39,
|
427 |
+
"learning_rate": 0.00018450980400142568,
|
428 |
+
"loss": 1.4177,
|
429 |
+
"step": 70
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.39,
|
433 |
+
"learning_rate": 0.00018512583487190751,
|
434 |
+
"loss": 1.4134,
|
435 |
+
"step": 71
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.4,
|
439 |
+
"learning_rate": 0.00018573324964312683,
|
440 |
+
"loss": 1.4015,
|
441 |
+
"step": 72
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.41,
|
445 |
+
"learning_rate": 0.00018633228601204555,
|
446 |
+
"loss": 1.4165,
|
447 |
+
"step": 73
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.41,
|
451 |
+
"learning_rate": 0.0001869231719730976,
|
452 |
+
"loss": 1.4043,
|
453 |
+
"step": 74
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.42,
|
457 |
+
"learning_rate": 0.00018750612633916996,
|
458 |
+
"loss": 1.4045,
|
459 |
+
"step": 75
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.42,
|
463 |
+
"learning_rate": 0.00018808135922807913,
|
464 |
+
"loss": 1.4063,
|
465 |
+
"step": 76
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.43,
|
469 |
+
"learning_rate": 0.00018864907251724816,
|
470 |
+
"loss": 1.4057,
|
471 |
+
"step": 77
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.43,
|
475 |
+
"learning_rate": 0.00018920946026904802,
|
476 |
+
"loss": 1.4009,
|
477 |
+
"step": 78
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.44,
|
481 |
+
"learning_rate": 0.00018976270912904412,
|
482 |
+
"loss": 1.4017,
|
483 |
+
"step": 79
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.44,
|
487 |
+
"learning_rate": 0.00019030899869919432,
|
488 |
+
"loss": 1.4172,
|
489 |
+
"step": 80
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.45,
|
493 |
+
"learning_rate": 0.00019084850188786495,
|
494 |
+
"loss": 1.4061,
|
495 |
+
"step": 81
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.46,
|
499 |
+
"learning_rate": 0.00019138138523837166,
|
500 |
+
"loss": 1.4047,
|
501 |
+
"step": 82
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.46,
|
505 |
+
"learning_rate": 0.00019190780923760738,
|
506 |
+
"loss": 1.408,
|
507 |
+
"step": 83
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.47,
|
511 |
+
"learning_rate": 0.00019242792860618813,
|
512 |
+
"loss": 1.4054,
|
513 |
+
"step": 84
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.47,
|
517 |
+
"learning_rate": 0.00019294189257142928,
|
518 |
+
"loss": 1.399,
|
519 |
+
"step": 85
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.48,
|
523 |
+
"learning_rate": 0.00019344984512435672,
|
524 |
+
"loss": 1.4015,
|
525 |
+
"step": 86
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.48,
|
529 |
+
"learning_rate": 0.00019395192526186183,
|
530 |
+
"loss": 1.4108,
|
531 |
+
"step": 87
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.49,
|
535 |
+
"learning_rate": 0.00019444826721501686,
|
536 |
+
"loss": 1.407,
|
537 |
+
"step": 88
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.49,
|
541 |
+
"learning_rate": 0.00019493900066449123,
|
542 |
+
"loss": 1.4018,
|
543 |
+
"step": 89
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.5,
|
547 |
+
"learning_rate": 0.00019542425094393247,
|
548 |
+
"loss": 1.4013,
|
549 |
+
"step": 90
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.51,
|
553 |
+
"learning_rate": 0.00019590413923210932,
|
554 |
+
"loss": 1.4123,
|
555 |
+
"step": 91
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.51,
|
559 |
+
"learning_rate": 0.0001963787827345555,
|
560 |
+
"loss": 1.4064,
|
561 |
+
"step": 92
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.52,
|
565 |
+
"learning_rate": 0.0001968482948553935,
|
566 |
+
"loss": 1.4009,
|
567 |
+
"step": 93
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.52,
|
571 |
+
"learning_rate": 0.00019731278535996984,
|
572 |
+
"loss": 1.4046,
|
573 |
+
"step": 94
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.53,
|
577 |
+
"learning_rate": 0.00019777236052888474,
|
578 |
+
"loss": 1.4029,
|
579 |
+
"step": 95
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.53,
|
583 |
+
"learning_rate": 0.00019822712330395682,
|
584 |
+
"loss": 1.4063,
|
585 |
+
"step": 96
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.54,
|
589 |
+
"learning_rate": 0.00019867717342662446,
|
590 |
+
"loss": 1.3971,
|
591 |
+
"step": 97
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.54,
|
595 |
+
"learning_rate": 0.00019912260756924948,
|
596 |
+
"loss": 1.3985,
|
597 |
+
"step": 98
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.55,
|
601 |
+
"learning_rate": 0.00019956351945975496,
|
602 |
+
"loss": 1.402,
|
603 |
+
"step": 99
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.56,
|
607 |
+
"learning_rate": 0.00019999999999999998,
|
608 |
+
"loss": 1.4014,
|
609 |
+
"step": 100
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.56,
|
613 |
+
"learning_rate": 0.0002,
|
614 |
+
"loss": 1.3979,
|
615 |
+
"step": 101
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.57,
|
619 |
+
"learning_rate": 0.00019975,
|
620 |
+
"loss": 1.4003,
|
621 |
+
"step": 102
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.57,
|
625 |
+
"learning_rate": 0.00019950000000000002,
|
626 |
+
"loss": 1.3969,
|
627 |
+
"step": 103
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.58,
|
631 |
+
"learning_rate": 0.00019925,
|
632 |
+
"loss": 1.4054,
|
633 |
+
"step": 104
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.58,
|
637 |
+
"learning_rate": 0.000199,
|
638 |
+
"loss": 1.3978,
|
639 |
+
"step": 105
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.59,
|
643 |
+
"learning_rate": 0.00019875,
|
644 |
+
"loss": 1.3996,
|
645 |
+
"step": 106
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 0.59,
|
649 |
+
"learning_rate": 0.00019850000000000003,
|
650 |
+
"loss": 1.3895,
|
651 |
+
"step": 107
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 0.6,
|
655 |
+
"learning_rate": 0.00019825,
|
656 |
+
"loss": 1.3965,
|
657 |
+
"step": 108
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.61,
|
661 |
+
"learning_rate": 0.00019800000000000002,
|
662 |
+
"loss": 1.4077,
|
663 |
+
"step": 109
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.61,
|
667 |
+
"learning_rate": 0.00019775,
|
668 |
+
"loss": 1.3999,
|
669 |
+
"step": 110
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.62,
|
673 |
+
"learning_rate": 0.00019750000000000003,
|
674 |
+
"loss": 1.3975,
|
675 |
+
"step": 111
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.62,
|
679 |
+
"learning_rate": 0.00019725,
|
680 |
+
"loss": 1.3985,
|
681 |
+
"step": 112
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.63,
|
685 |
+
"learning_rate": 0.00019700000000000002,
|
686 |
+
"loss": 1.3939,
|
687 |
+
"step": 113
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 0.63,
|
691 |
+
"learning_rate": 0.00019675,
|
692 |
+
"loss": 1.4033,
|
693 |
+
"step": 114
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.64,
|
697 |
+
"learning_rate": 0.0001965,
|
698 |
+
"loss": 1.4035,
|
699 |
+
"step": 115
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.64,
|
703 |
+
"learning_rate": 0.00019625,
|
704 |
+
"loss": 1.3979,
|
705 |
+
"step": 116
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.65,
|
709 |
+
"learning_rate": 0.000196,
|
710 |
+
"loss": 1.4002,
|
711 |
+
"step": 117
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.66,
|
715 |
+
"learning_rate": 0.00019575000000000001,
|
716 |
+
"loss": 1.3949,
|
717 |
+
"step": 118
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.66,
|
721 |
+
"learning_rate": 0.0001955,
|
722 |
+
"loss": 1.3906,
|
723 |
+
"step": 119
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.67,
|
727 |
+
"learning_rate": 0.00019525,
|
728 |
+
"loss": 1.4039,
|
729 |
+
"step": 120
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.67,
|
733 |
+
"learning_rate": 0.000195,
|
734 |
+
"loss": 1.4,
|
735 |
+
"step": 121
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 0.68,
|
739 |
+
"learning_rate": 0.00019475000000000002,
|
740 |
+
"loss": 1.3961,
|
741 |
+
"step": 122
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.68,
|
745 |
+
"learning_rate": 0.0001945,
|
746 |
+
"loss": 1.3997,
|
747 |
+
"step": 123
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.69,
|
751 |
+
"learning_rate": 0.00019425,
|
752 |
+
"loss": 1.414,
|
753 |
+
"step": 124
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.69,
|
757 |
+
"learning_rate": 0.000194,
|
758 |
+
"loss": 1.3942,
|
759 |
+
"step": 125
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.7,
|
763 |
+
"learning_rate": 0.00019375000000000002,
|
764 |
+
"loss": 1.406,
|
765 |
+
"step": 126
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.71,
|
769 |
+
"learning_rate": 0.00019350000000000001,
|
770 |
+
"loss": 1.4017,
|
771 |
+
"step": 127
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.71,
|
775 |
+
"learning_rate": 0.00019325,
|
776 |
+
"loss": 1.3917,
|
777 |
+
"step": 128
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.72,
|
781 |
+
"learning_rate": 0.000193,
|
782 |
+
"loss": 1.3945,
|
783 |
+
"step": 129
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.72,
|
787 |
+
"learning_rate": 0.00019275,
|
788 |
+
"loss": 1.3966,
|
789 |
+
"step": 130
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.73,
|
793 |
+
"learning_rate": 0.00019250000000000002,
|
794 |
+
"loss": 1.3942,
|
795 |
+
"step": 131
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.73,
|
799 |
+
"learning_rate": 0.00019225,
|
800 |
+
"loss": 1.3968,
|
801 |
+
"step": 132
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.74,
|
805 |
+
"learning_rate": 0.000192,
|
806 |
+
"loss": 1.3921,
|
807 |
+
"step": 133
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.74,
|
811 |
+
"learning_rate": 0.00019175,
|
812 |
+
"loss": 1.3931,
|
813 |
+
"step": 134
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.75,
|
817 |
+
"learning_rate": 0.00019150000000000002,
|
818 |
+
"loss": 1.3917,
|
819 |
+
"step": 135
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.76,
|
823 |
+
"learning_rate": 0.00019125000000000001,
|
824 |
+
"loss": 1.4025,
|
825 |
+
"step": 136
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.76,
|
829 |
+
"learning_rate": 0.000191,
|
830 |
+
"loss": 1.3997,
|
831 |
+
"step": 137
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.77,
|
835 |
+
"learning_rate": 0.00019075,
|
836 |
+
"loss": 1.4027,
|
837 |
+
"step": 138
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.77,
|
841 |
+
"learning_rate": 0.00019050000000000002,
|
842 |
+
"loss": 1.4068,
|
843 |
+
"step": 139
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.78,
|
847 |
+
"learning_rate": 0.00019025000000000002,
|
848 |
+
"loss": 1.4075,
|
849 |
+
"step": 140
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.78,
|
853 |
+
"learning_rate": 0.00019,
|
854 |
+
"loss": 1.3986,
|
855 |
+
"step": 141
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.79,
|
859 |
+
"learning_rate": 0.00018975,
|
860 |
+
"loss": 1.3996,
|
861 |
+
"step": 142
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.79,
|
865 |
+
"learning_rate": 0.0001895,
|
866 |
+
"loss": 1.3973,
|
867 |
+
"step": 143
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.8,
|
871 |
+
"learning_rate": 0.00018925000000000002,
|
872 |
+
"loss": 1.4034,
|
873 |
+
"step": 144
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.81,
|
877 |
+
"learning_rate": 0.00018899999999999999,
|
878 |
+
"loss": 1.4142,
|
879 |
+
"step": 145
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.81,
|
883 |
+
"learning_rate": 0.00018875,
|
884 |
+
"loss": 1.3989,
|
885 |
+
"step": 146
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.82,
|
889 |
+
"learning_rate": 0.0001885,
|
890 |
+
"loss": 1.3939,
|
891 |
+
"step": 147
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.82,
|
895 |
+
"learning_rate": 0.00018825000000000002,
|
896 |
+
"loss": 1.3948,
|
897 |
+
"step": 148
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.83,
|
901 |
+
"learning_rate": 0.000188,
|
902 |
+
"loss": 1.3951,
|
903 |
+
"step": 149
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.83,
|
907 |
+
"learning_rate": 0.00018775,
|
908 |
+
"loss": 1.3982,
|
909 |
+
"step": 150
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.84,
|
913 |
+
"learning_rate": 0.0001875,
|
914 |
+
"loss": 1.3982,
|
915 |
+
"step": 151
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 0.84,
|
919 |
+
"learning_rate": 0.00018725000000000002,
|
920 |
+
"loss": 1.404,
|
921 |
+
"step": 152
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.85,
|
925 |
+
"learning_rate": 0.00018700000000000002,
|
926 |
+
"loss": 1.3949,
|
927 |
+
"step": 153
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.86,
|
931 |
+
"learning_rate": 0.00018675,
|
932 |
+
"loss": 1.3955,
|
933 |
+
"step": 154
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.86,
|
937 |
+
"learning_rate": 0.0001865,
|
938 |
+
"loss": 1.3873,
|
939 |
+
"step": 155
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.87,
|
943 |
+
"learning_rate": 0.00018625,
|
944 |
+
"loss": 1.3995,
|
945 |
+
"step": 156
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.87,
|
949 |
+
"learning_rate": 0.00018600000000000002,
|
950 |
+
"loss": 1.389,
|
951 |
+
"step": 157
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.88,
|
955 |
+
"learning_rate": 0.00018575,
|
956 |
+
"loss": 1.3944,
|
957 |
+
"step": 158
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.88,
|
961 |
+
"learning_rate": 0.0001855,
|
962 |
+
"loss": 1.389,
|
963 |
+
"step": 159
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.89,
|
967 |
+
"learning_rate": 0.00018525,
|
968 |
+
"loss": 1.4016,
|
969 |
+
"step": 160
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.89,
|
973 |
+
"learning_rate": 0.00018500000000000002,
|
974 |
+
"loss": 1.3953,
|
975 |
+
"step": 161
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.9,
|
979 |
+
"learning_rate": 0.00018475,
|
980 |
+
"loss": 1.4005,
|
981 |
+
"step": 162
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.91,
|
985 |
+
"learning_rate": 0.0001845,
|
986 |
+
"loss": 1.3977,
|
987 |
+
"step": 163
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.91,
|
991 |
+
"learning_rate": 0.00018425,
|
992 |
+
"loss": 1.3914,
|
993 |
+
"step": 164
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.92,
|
997 |
+
"learning_rate": 0.00018400000000000003,
|
998 |
+
"loss": 1.391,
|
999 |
+
"step": 165
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.92,
|
1003 |
+
"learning_rate": 0.00018375,
|
1004 |
+
"loss": 1.4055,
|
1005 |
+
"step": 166
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.93,
|
1009 |
+
"learning_rate": 0.00018350000000000002,
|
1010 |
+
"loss": 1.3956,
|
1011 |
+
"step": 167
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.93,
|
1015 |
+
"learning_rate": 0.00018325,
|
1016 |
+
"loss": 1.3845,
|
1017 |
+
"step": 168
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.94,
|
1021 |
+
"learning_rate": 0.000183,
|
1022 |
+
"loss": 1.3882,
|
1023 |
+
"step": 169
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.94,
|
1027 |
+
"learning_rate": 0.00018275,
|
1028 |
+
"loss": 1.3891,
|
1029 |
+
"step": 170
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.95,
|
1033 |
+
"learning_rate": 0.0001825,
|
1034 |
+
"loss": 1.3868,
|
1035 |
+
"step": 171
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.96,
|
1039 |
+
"learning_rate": 0.00018225,
|
1040 |
+
"loss": 1.3909,
|
1041 |
+
"step": 172
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.96,
|
1045 |
+
"learning_rate": 0.000182,
|
1046 |
+
"loss": 1.392,
|
1047 |
+
"step": 173
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.97,
|
1051 |
+
"learning_rate": 0.00018175,
|
1052 |
+
"loss": 1.3919,
|
1053 |
+
"step": 174
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.97,
|
1057 |
+
"learning_rate": 0.0001815,
|
1058 |
+
"loss": 1.3952,
|
1059 |
+
"step": 175
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.98,
|
1063 |
+
"learning_rate": 0.00018125000000000001,
|
1064 |
+
"loss": 1.3903,
|
1065 |
+
"step": 176
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.98,
|
1069 |
+
"learning_rate": 0.000181,
|
1070 |
+
"loss": 1.4049,
|
1071 |
+
"step": 177
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.99,
|
1075 |
+
"learning_rate": 0.00018075000000000003,
|
1076 |
+
"loss": 1.3926,
|
1077 |
+
"step": 178
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.99,
|
1081 |
+
"learning_rate": 0.0001805,
|
1082 |
+
"loss": 1.3918,
|
1083 |
+
"step": 179
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 1.0,
|
1087 |
+
"learning_rate": 0.00018025000000000002,
|
1088 |
+
"loss": 1.4015,
|
1089 |
+
"step": 180
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 1.01,
|
1093 |
+
"learning_rate": 0.00018,
|
1094 |
+
"loss": 1.3907,
|
1095 |
+
"step": 181
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 1.01,
|
1099 |
+
"learning_rate": 0.00017975,
|
1100 |
+
"loss": 1.3876,
|
1101 |
+
"step": 182
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 1.02,
|
1105 |
+
"learning_rate": 0.0001795,
|
1106 |
+
"loss": 1.3907,
|
1107 |
+
"step": 183
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 1.02,
|
1111 |
+
"learning_rate": 0.00017925000000000002,
|
1112 |
+
"loss": 1.3936,
|
1113 |
+
"step": 184
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 1.03,
|
1117 |
+
"learning_rate": 0.00017900000000000001,
|
1118 |
+
"loss": 1.3907,
|
1119 |
+
"step": 185
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 1.03,
|
1123 |
+
"learning_rate": 0.00017875,
|
1124 |
+
"loss": 1.4007,
|
1125 |
+
"step": 186
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 1.04,
|
1129 |
+
"learning_rate": 0.0001785,
|
1130 |
+
"loss": 1.3944,
|
1131 |
+
"step": 187
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 1.04,
|
1135 |
+
"learning_rate": 0.00017825,
|
1136 |
+
"loss": 1.3884,
|
1137 |
+
"step": 188
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 1.05,
|
1141 |
+
"learning_rate": 0.00017800000000000002,
|
1142 |
+
"loss": 1.3892,
|
1143 |
+
"step": 189
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 1.06,
|
1147 |
+
"learning_rate": 0.00017775,
|
1148 |
+
"loss": 1.3897,
|
1149 |
+
"step": 190
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 1.06,
|
1153 |
+
"learning_rate": 0.0001775,
|
1154 |
+
"loss": 1.3958,
|
1155 |
+
"step": 191
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 1.07,
|
1159 |
+
"learning_rate": 0.00017725,
|
1160 |
+
"loss": 1.3904,
|
1161 |
+
"step": 192
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 1.07,
|
1165 |
+
"learning_rate": 0.00017700000000000002,
|
1166 |
+
"loss": 1.3907,
|
1167 |
+
"step": 193
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 1.08,
|
1171 |
+
"learning_rate": 0.00017675000000000001,
|
1172 |
+
"loss": 1.395,
|
1173 |
+
"step": 194
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 1.08,
|
1177 |
+
"learning_rate": 0.0001765,
|
1178 |
+
"loss": 1.3898,
|
1179 |
+
"step": 195
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 1.09,
|
1183 |
+
"learning_rate": 0.00017625,
|
1184 |
+
"loss": 1.3949,
|
1185 |
+
"step": 196
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 1.09,
|
1189 |
+
"learning_rate": 0.00017600000000000002,
|
1190 |
+
"loss": 1.3917,
|
1191 |
+
"step": 197
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 1.1,
|
1195 |
+
"learning_rate": 0.00017575000000000002,
|
1196 |
+
"loss": 1.3944,
|
1197 |
+
"step": 198
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 1.11,
|
1201 |
+
"learning_rate": 0.0001755,
|
1202 |
+
"loss": 1.3873,
|
1203 |
+
"step": 199
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 1.11,
|
1207 |
+
"learning_rate": 0.00017525,
|
1208 |
+
"loss": 1.389,
|
1209 |
+
"step": 200
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 1.12,
|
1213 |
+
"learning_rate": 0.000175,
|
1214 |
+
"loss": 1.3887,
|
1215 |
+
"step": 201
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 1.12,
|
1219 |
+
"learning_rate": 0.00017475000000000002,
|
1220 |
+
"loss": 1.3971,
|
1221 |
+
"step": 202
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 1.13,
|
1225 |
+
"learning_rate": 0.0001745,
|
1226 |
+
"loss": 1.3831,
|
1227 |
+
"step": 203
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 1.13,
|
1231 |
+
"learning_rate": 0.00017425,
|
1232 |
+
"loss": 1.3864,
|
1233 |
+
"step": 204
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 1.14,
|
1237 |
+
"learning_rate": 0.000174,
|
1238 |
+
"loss": 1.3874,
|
1239 |
+
"step": 205
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 1.14,
|
1243 |
+
"learning_rate": 0.00017375000000000002,
|
1244 |
+
"loss": 1.3887,
|
1245 |
+
"step": 206
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 1.15,
|
1249 |
+
"learning_rate": 0.00017350000000000002,
|
1250 |
+
"loss": 1.3884,
|
1251 |
+
"step": 207
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 1.16,
|
1255 |
+
"learning_rate": 0.00017325,
|
1256 |
+
"loss": 1.3909,
|
1257 |
+
"step": 208
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 1.16,
|
1261 |
+
"learning_rate": 0.000173,
|
1262 |
+
"loss": 1.392,
|
1263 |
+
"step": 209
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 1.17,
|
1267 |
+
"learning_rate": 0.00017275000000000002,
|
1268 |
+
"loss": 1.3925,
|
1269 |
+
"step": 210
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 1.17,
|
1273 |
+
"learning_rate": 0.00017250000000000002,
|
1274 |
+
"loss": 1.3947,
|
1275 |
+
"step": 211
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 1.18,
|
1279 |
+
"learning_rate": 0.00017225,
|
1280 |
+
"loss": 1.3922,
|
1281 |
+
"step": 212
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 1.18,
|
1285 |
+
"learning_rate": 0.000172,
|
1286 |
+
"loss": 1.3901,
|
1287 |
+
"step": 213
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 1.19,
|
1291 |
+
"learning_rate": 0.00017175,
|
1292 |
+
"loss": 1.3882,
|
1293 |
+
"step": 214
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 1.19,
|
1297 |
+
"learning_rate": 0.00017150000000000002,
|
1298 |
+
"loss": 1.3886,
|
1299 |
+
"step": 215
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 1.2,
|
1303 |
+
"learning_rate": 0.00017125,
|
1304 |
+
"loss": 1.3953,
|
1305 |
+
"step": 216
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 1.21,
|
1309 |
+
"learning_rate": 0.000171,
|
1310 |
+
"loss": 1.3935,
|
1311 |
+
"step": 217
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 1.21,
|
1315 |
+
"learning_rate": 0.00017075,
|
1316 |
+
"loss": 1.3845,
|
1317 |
+
"step": 218
|
1318 |
+
},
|
1319 |
+
{
|
1320 |
+
"epoch": 1.22,
|
1321 |
+
"learning_rate": 0.00017050000000000002,
|
1322 |
+
"loss": 1.3986,
|
1323 |
+
"step": 219
|
1324 |
+
},
|
1325 |
+
{
|
1326 |
+
"epoch": 1.22,
|
1327 |
+
"learning_rate": 0.00017025,
|
1328 |
+
"loss": 1.3949,
|
1329 |
+
"step": 220
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 1.23,
|
1333 |
+
"learning_rate": 0.00017,
|
1334 |
+
"loss": 1.3914,
|
1335 |
+
"step": 221
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 1.23,
|
1339 |
+
"learning_rate": 0.00016975,
|
1340 |
+
"loss": 1.3975,
|
1341 |
+
"step": 222
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 1.24,
|
1345 |
+
"learning_rate": 0.00016950000000000003,
|
1346 |
+
"loss": 1.3911,
|
1347 |
+
"step": 223
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 1.24,
|
1351 |
+
"learning_rate": 0.00016925,
|
1352 |
+
"loss": 1.3945,
|
1353 |
+
"step": 224
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 1.25,
|
1357 |
+
"learning_rate": 0.00016900000000000002,
|
1358 |
+
"loss": 1.394,
|
1359 |
+
"step": 225
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 1.26,
|
1363 |
+
"learning_rate": 0.00016875,
|
1364 |
+
"loss": 1.385,
|
1365 |
+
"step": 226
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 1.26,
|
1369 |
+
"learning_rate": 0.0001685,
|
1370 |
+
"loss": 1.3867,
|
1371 |
+
"step": 227
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 1.27,
|
1375 |
+
"learning_rate": 0.00016825000000000002,
|
1376 |
+
"loss": 1.3976,
|
1377 |
+
"step": 228
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 1.27,
|
1381 |
+
"learning_rate": 0.000168,
|
1382 |
+
"loss": 1.392,
|
1383 |
+
"step": 229
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 1.28,
|
1387 |
+
"learning_rate": 0.00016775,
|
1388 |
+
"loss": 1.3883,
|
1389 |
+
"step": 230
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 1.28,
|
1393 |
+
"learning_rate": 0.0001675,
|
1394 |
+
"loss": 1.3884,
|
1395 |
+
"step": 231
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 1.29,
|
1399 |
+
"learning_rate": 0.00016725000000000003,
|
1400 |
+
"loss": 1.3893,
|
1401 |
+
"step": 232
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"epoch": 1.29,
|
1405 |
+
"learning_rate": 0.000167,
|
1406 |
+
"loss": 1.3888,
|
1407 |
+
"step": 233
|
1408 |
+
},
|
1409 |
+
{
|
1410 |
+
"epoch": 1.3,
|
1411 |
+
"learning_rate": 0.00016675000000000001,
|
1412 |
+
"loss": 1.3886,
|
1413 |
+
"step": 234
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 1.31,
|
1417 |
+
"learning_rate": 0.0001665,
|
1418 |
+
"loss": 1.385,
|
1419 |
+
"step": 235
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 1.31,
|
1423 |
+
"learning_rate": 0.00016625000000000003,
|
1424 |
+
"loss": 1.3939,
|
1425 |
+
"step": 236
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 1.32,
|
1429 |
+
"learning_rate": 0.000166,
|
1430 |
+
"loss": 1.3952,
|
1431 |
+
"step": 237
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 1.32,
|
1435 |
+
"learning_rate": 0.00016575000000000002,
|
1436 |
+
"loss": 1.3913,
|
1437 |
+
"step": 238
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 1.33,
|
1441 |
+
"learning_rate": 0.0001655,
|
1442 |
+
"loss": 1.3863,
|
1443 |
+
"step": 239
|
1444 |
+
},
|
1445 |
+
{
|
1446 |
+
"epoch": 1.33,
|
1447 |
+
"learning_rate": 0.00016525,
|
1448 |
+
"loss": 1.3908,
|
1449 |
+
"step": 240
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 1.34,
|
1453 |
+
"learning_rate": 0.000165,
|
1454 |
+
"loss": 1.3864,
|
1455 |
+
"step": 241
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"epoch": 1.34,
|
1459 |
+
"learning_rate": 0.00016475,
|
1460 |
+
"loss": 1.3878,
|
1461 |
+
"step": 242
|
1462 |
+
},
|
1463 |
+
{
|
1464 |
+
"epoch": 1.35,
|
1465 |
+
"learning_rate": 0.00016450000000000001,
|
1466 |
+
"loss": 1.3949,
|
1467 |
+
"step": 243
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 1.36,
|
1471 |
+
"learning_rate": 0.00016425,
|
1472 |
+
"loss": 1.3902,
|
1473 |
+
"step": 244
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 1.36,
|
1477 |
+
"learning_rate": 0.000164,
|
1478 |
+
"loss": 1.3879,
|
1479 |
+
"step": 245
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 1.37,
|
1483 |
+
"learning_rate": 0.00016375,
|
1484 |
+
"loss": 1.3876,
|
1485 |
+
"step": 246
|
1486 |
+
},
|
1487 |
+
{
|
1488 |
+
"epoch": 1.37,
|
1489 |
+
"learning_rate": 0.00016350000000000002,
|
1490 |
+
"loss": 1.3838,
|
1491 |
+
"step": 247
|
1492 |
+
},
|
1493 |
+
{
|
1494 |
+
"epoch": 1.38,
|
1495 |
+
"learning_rate": 0.00016325,
|
1496 |
+
"loss": 1.3934,
|
1497 |
+
"step": 248
|
1498 |
+
},
|
1499 |
+
{
|
1500 |
+
"epoch": 1.38,
|
1501 |
+
"learning_rate": 0.000163,
|
1502 |
+
"loss": 1.3891,
|
1503 |
+
"step": 249
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 1.39,
|
1507 |
+
"learning_rate": 0.00016275,
|
1508 |
+
"loss": 1.3939,
|
1509 |
+
"step": 250
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 1.39,
|
1513 |
+
"learning_rate": 0.00016250000000000002,
|
1514 |
+
"loss": 1.3834,
|
1515 |
+
"step": 251
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 1.4,
|
1519 |
+
"learning_rate": 0.00016225000000000001,
|
1520 |
+
"loss": 1.3885,
|
1521 |
+
"step": 252
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 1.41,
|
1525 |
+
"learning_rate": 0.000162,
|
1526 |
+
"loss": 1.3857,
|
1527 |
+
"step": 253
|
1528 |
+
},
|
1529 |
+
{
|
1530 |
+
"epoch": 1.41,
|
1531 |
+
"learning_rate": 0.00016175,
|
1532 |
+
"loss": 1.389,
|
1533 |
+
"step": 254
|
1534 |
+
},
|
1535 |
+
{
|
1536 |
+
"epoch": 1.42,
|
1537 |
+
"learning_rate": 0.0001615,
|
1538 |
+
"loss": 1.3825,
|
1539 |
+
"step": 255
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 1.42,
|
1543 |
+
"learning_rate": 0.00016125000000000002,
|
1544 |
+
"loss": 1.3851,
|
1545 |
+
"step": 256
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 1.43,
|
1549 |
+
"learning_rate": 0.000161,
|
1550 |
+
"loss": 1.3811,
|
1551 |
+
"step": 257
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 1.43,
|
1555 |
+
"learning_rate": 0.00016075,
|
1556 |
+
"loss": 1.3925,
|
1557 |
+
"step": 258
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 1.44,
|
1561 |
+
"learning_rate": 0.0001605,
|
1562 |
+
"loss": 1.3881,
|
1563 |
+
"step": 259
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 1.44,
|
1567 |
+
"learning_rate": 0.00016025000000000002,
|
1568 |
+
"loss": 1.3926,
|
1569 |
+
"step": 260
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 1.45,
|
1573 |
+
"learning_rate": 0.00016,
|
1574 |
+
"loss": 1.3912,
|
1575 |
+
"step": 261
|
1576 |
+
},
|
1577 |
+
{
|
1578 |
+
"epoch": 1.46,
|
1579 |
+
"learning_rate": 0.00015975,
|
1580 |
+
"loss": 1.3906,
|
1581 |
+
"step": 262
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"epoch": 1.46,
|
1585 |
+
"learning_rate": 0.0001595,
|
1586 |
+
"loss": 1.3881,
|
1587 |
+
"step": 263
|
1588 |
+
},
|
1589 |
+
{
|
1590 |
+
"epoch": 1.47,
|
1591 |
+
"learning_rate": 0.00015925000000000002,
|
1592 |
+
"loss": 1.3869,
|
1593 |
+
"step": 264
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 1.47,
|
1597 |
+
"learning_rate": 0.00015900000000000002,
|
1598 |
+
"loss": 1.3915,
|
1599 |
+
"step": 265
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 1.48,
|
1603 |
+
"learning_rate": 0.00015875,
|
1604 |
+
"loss": 1.3899,
|
1605 |
+
"step": 266
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 1.48,
|
1609 |
+
"learning_rate": 0.0001585,
|
1610 |
+
"loss": 1.387,
|
1611 |
+
"step": 267
|
1612 |
+
},
|
1613 |
+
{
|
1614 |
+
"epoch": 1.49,
|
1615 |
+
"learning_rate": 0.00015825,
|
1616 |
+
"loss": 1.3874,
|
1617 |
+
"step": 268
|
1618 |
+
},
|
1619 |
+
{
|
1620 |
+
"epoch": 1.49,
|
1621 |
+
"learning_rate": 0.00015800000000000002,
|
1622 |
+
"loss": 1.3911,
|
1623 |
+
"step": 269
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 1.5,
|
1627 |
+
"learning_rate": 0.00015774999999999999,
|
1628 |
+
"loss": 1.3832,
|
1629 |
+
"step": 270
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 1.51,
|
1633 |
+
"learning_rate": 0.0001575,
|
1634 |
+
"loss": 1.3916,
|
1635 |
+
"step": 271
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 1.51,
|
1639 |
+
"learning_rate": 0.00015725,
|
1640 |
+
"loss": 1.3882,
|
1641 |
+
"step": 272
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 1.52,
|
1645 |
+
"learning_rate": 0.00015700000000000002,
|
1646 |
+
"loss": 1.3844,
|
1647 |
+
"step": 273
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 1.52,
|
1651 |
+
"learning_rate": 0.00015675,
|
1652 |
+
"loss": 1.391,
|
1653 |
+
"step": 274
|
1654 |
+
},
|
1655 |
+
{
|
1656 |
+
"epoch": 1.53,
|
1657 |
+
"learning_rate": 0.0001565,
|
1658 |
+
"loss": 1.3868,
|
1659 |
+
"step": 275
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 1.53,
|
1663 |
+
"learning_rate": 0.00015625,
|
1664 |
+
"loss": 1.384,
|
1665 |
+
"step": 276
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 1.54,
|
1669 |
+
"learning_rate": 0.00015600000000000002,
|
1670 |
+
"loss": 1.3825,
|
1671 |
+
"step": 277
|
1672 |
+
},
|
1673 |
+
{
|
1674 |
+
"epoch": 1.54,
|
1675 |
+
"learning_rate": 0.00015575000000000002,
|
1676 |
+
"loss": 1.3843,
|
1677 |
+
"step": 278
|
1678 |
+
},
|
1679 |
+
{
|
1680 |
+
"epoch": 1.55,
|
1681 |
+
"learning_rate": 0.0001555,
|
1682 |
+
"loss": 1.3842,
|
1683 |
+
"step": 279
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 1.56,
|
1687 |
+
"learning_rate": 0.00015525,
|
1688 |
+
"loss": 1.3806,
|
1689 |
+
"step": 280
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 1.56,
|
1693 |
+
"learning_rate": 0.000155,
|
1694 |
+
"loss": 1.382,
|
1695 |
+
"step": 281
|
1696 |
+
},
|
1697 |
+
{
|
1698 |
+
"epoch": 1.57,
|
1699 |
+
"learning_rate": 0.00015475000000000002,
|
1700 |
+
"loss": 1.3885,
|
1701 |
+
"step": 282
|
1702 |
+
},
|
1703 |
+
{
|
1704 |
+
"epoch": 1.57,
|
1705 |
+
"learning_rate": 0.0001545,
|
1706 |
+
"loss": 1.3863,
|
1707 |
+
"step": 283
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 1.58,
|
1711 |
+
"learning_rate": 0.00015425,
|
1712 |
+
"loss": 1.3881,
|
1713 |
+
"step": 284
|
1714 |
+
},
|
1715 |
+
{
|
1716 |
+
"epoch": 1.58,
|
1717 |
+
"learning_rate": 0.000154,
|
1718 |
+
"loss": 1.3901,
|
1719 |
+
"step": 285
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 1.59,
|
1723 |
+
"learning_rate": 0.00015375000000000002,
|
1724 |
+
"loss": 1.3802,
|
1725 |
+
"step": 286
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 1.59,
|
1729 |
+
"learning_rate": 0.0001535,
|
1730 |
+
"loss": 1.3903,
|
1731 |
+
"step": 287
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 1.6,
|
1735 |
+
"learning_rate": 0.00015325,
|
1736 |
+
"loss": 1.3905,
|
1737 |
+
"step": 288
|
1738 |
+
},
|
1739 |
+
{
|
1740 |
+
"epoch": 1.61,
|
1741 |
+
"learning_rate": 0.000153,
|
1742 |
+
"loss": 1.3858,
|
1743 |
+
"step": 289
|
1744 |
+
},
|
1745 |
+
{
|
1746 |
+
"epoch": 1.61,
|
1747 |
+
"learning_rate": 0.00015275000000000003,
|
1748 |
+
"loss": 1.3914,
|
1749 |
+
"step": 290
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 1.62,
|
1753 |
+
"learning_rate": 0.0001525,
|
1754 |
+
"loss": 1.3874,
|
1755 |
+
"step": 291
|
1756 |
+
},
|
1757 |
+
{
|
1758 |
+
"epoch": 1.62,
|
1759 |
+
"learning_rate": 0.00015225000000000001,
|
1760 |
+
"loss": 1.3876,
|
1761 |
+
"step": 292
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 1.63,
|
1765 |
+
"learning_rate": 0.000152,
|
1766 |
+
"loss": 1.385,
|
1767 |
+
"step": 293
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 1.63,
|
1771 |
+
"learning_rate": 0.00015175,
|
1772 |
+
"loss": 1.3858,
|
1773 |
+
"step": 294
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 1.64,
|
1777 |
+
"learning_rate": 0.0001515,
|
1778 |
+
"loss": 1.3849,
|
1779 |
+
"step": 295
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 1.64,
|
1783 |
+
"learning_rate": 0.00015125,
|
1784 |
+
"loss": 1.39,
|
1785 |
+
"step": 296
|
1786 |
+
},
|
1787 |
+
{
|
1788 |
+
"epoch": 1.65,
|
1789 |
+
"learning_rate": 0.000151,
|
1790 |
+
"loss": 1.3869,
|
1791 |
+
"step": 297
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 1.66,
|
1795 |
+
"learning_rate": 0.00015075,
|
1796 |
+
"loss": 1.3896,
|
1797 |
+
"step": 298
|
1798 |
+
},
|
1799 |
+
{
|
1800 |
+
"epoch": 1.66,
|
1801 |
+
"learning_rate": 0.0001505,
|
1802 |
+
"loss": 1.3926,
|
1803 |
+
"step": 299
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 1.67,
|
1807 |
+
"learning_rate": 0.00015025,
|
1808 |
+
"loss": 1.3823,
|
1809 |
+
"step": 300
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 1.67,
|
1813 |
+
"eval_loss": 1.3873900175094604,
|
1814 |
+
"eval_runtime": 1.5789,
|
1815 |
+
"eval_samples_per_second": 63.336,
|
1816 |
+
"eval_steps_per_second": 4.433,
|
1817 |
+
"step": 300
|
1818 |
+
}
|
1819 |
+
],
|
1820 |
+
"logging_steps": 1,
|
1821 |
+
"max_steps": 900,
|
1822 |
+
"num_train_epochs": 5,
|
1823 |
+
"save_steps": 300,
|
1824 |
+
"total_flos": 6.755002364618342e+16,
|
1825 |
+
"trial_name": null,
|
1826 |
+
"trial_params": null
|
1827 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d0551ad96bb3a47f40b27101c8057f425b3b65b4a89dd1b9631ee395474864c
|
3 |
+
size 6200
|
last-checkpoint/zero_to_fp32.py
ADDED
@@ -0,0 +1,587 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
#!/usr/bin/env python
|
2 |
+
|
3 |
+
# Copyright (c) Microsoft Corporation.
|
4 |
+
# SPDX-License-Identifier: Apache-2.0
|
5 |
+
|
6 |
+
# DeepSpeed Team
|
7 |
+
|
8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
11 |
+
# application.
|
12 |
+
#
|
13 |
+
# example: python zero_to_fp32.py . pytorch_model.bin
|
14 |
+
|
15 |
+
import argparse
|
16 |
+
import torch
|
17 |
+
import glob
|
18 |
+
import math
|
19 |
+
import os
|
20 |
+
import re
|
21 |
+
from collections import OrderedDict
|
22 |
+
from dataclasses import dataclass
|
23 |
+
|
24 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
25 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
26 |
+
from deepspeed.utils import logger
|
27 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
28 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
29 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
30 |
+
|
31 |
+
|
32 |
+
@dataclass
|
33 |
+
class zero_model_state:
|
34 |
+
buffers: dict()
|
35 |
+
param_shapes: dict()
|
36 |
+
shared_params: list
|
37 |
+
ds_version: int
|
38 |
+
frozen_param_shapes: dict()
|
39 |
+
frozen_param_fragments: dict()
|
40 |
+
|
41 |
+
|
42 |
+
debug = 0
|
43 |
+
|
44 |
+
# load to cpu
|
45 |
+
device = torch.device('cpu')
|
46 |
+
|
47 |
+
|
48 |
+
def atoi(text):
|
49 |
+
return int(text) if text.isdigit() else text
|
50 |
+
|
51 |
+
|
52 |
+
def natural_keys(text):
|
53 |
+
'''
|
54 |
+
alist.sort(key=natural_keys) sorts in human order
|
55 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
56 |
+
(See Toothy's implementation in the comments)
|
57 |
+
'''
|
58 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
59 |
+
|
60 |
+
|
61 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
62 |
+
if not os.path.isdir(checkpoint_dir):
|
63 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
64 |
+
|
65 |
+
# there should be only one file
|
66 |
+
if zero_stage <= 2:
|
67 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
68 |
+
elif zero_stage == 3:
|
69 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
70 |
+
|
71 |
+
if not os.path.exists(file):
|
72 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
73 |
+
|
74 |
+
return file
|
75 |
+
|
76 |
+
|
77 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
78 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
79 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
80 |
+
|
81 |
+
if len(ckpt_files) == 0:
|
82 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
83 |
+
|
84 |
+
return ckpt_files
|
85 |
+
|
86 |
+
|
87 |
+
def get_optim_files(checkpoint_dir):
|
88 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
89 |
+
|
90 |
+
|
91 |
+
def get_model_state_files(checkpoint_dir):
|
92 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
93 |
+
|
94 |
+
|
95 |
+
def parse_model_states(files):
|
96 |
+
zero_model_states = []
|
97 |
+
for file in files:
|
98 |
+
state_dict = torch.load(file, map_location=device)
|
99 |
+
|
100 |
+
if BUFFER_NAMES not in state_dict:
|
101 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
102 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
103 |
+
if debug:
|
104 |
+
print("Found buffers:", buffer_names)
|
105 |
+
|
106 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
107 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
108 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
109 |
+
|
110 |
+
# collect parameters that are included in param_shapes
|
111 |
+
param_names = []
|
112 |
+
for s in param_shapes:
|
113 |
+
for name in s.keys():
|
114 |
+
param_names.append(name)
|
115 |
+
|
116 |
+
# update with frozen parameters
|
117 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
118 |
+
if frozen_param_shapes is not None:
|
119 |
+
if debug:
|
120 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
121 |
+
param_names += list(frozen_param_shapes.keys())
|
122 |
+
|
123 |
+
# handle shared params
|
124 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
125 |
+
|
126 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
127 |
+
|
128 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
129 |
+
|
130 |
+
z_model_state = zero_model_state(buffers=buffers,
|
131 |
+
param_shapes=param_shapes,
|
132 |
+
shared_params=shared_params,
|
133 |
+
ds_version=ds_version,
|
134 |
+
frozen_param_shapes=frozen_param_shapes,
|
135 |
+
frozen_param_fragments=frozen_param_fragments)
|
136 |
+
zero_model_states.append(z_model_state)
|
137 |
+
|
138 |
+
return zero_model_states
|
139 |
+
|
140 |
+
|
141 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
142 |
+
|
143 |
+
total_files = len(files)
|
144 |
+
state_dicts = []
|
145 |
+
for f in files:
|
146 |
+
state_dict = torch.load(f, map_location=device)
|
147 |
+
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
148 |
+
# and also handle the case where it was already removed by another helper script
|
149 |
+
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
150 |
+
state_dicts.append(state_dict)
|
151 |
+
|
152 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
153 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
154 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
155 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
156 |
+
|
157 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
158 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
159 |
+
# use the max of the partition_count to get the dp world_size.
|
160 |
+
|
161 |
+
if type(world_size) is list:
|
162 |
+
world_size = max(world_size)
|
163 |
+
|
164 |
+
if world_size != total_files:
|
165 |
+
raise ValueError(
|
166 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
167 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
168 |
+
)
|
169 |
+
|
170 |
+
# the groups are named differently in each stage
|
171 |
+
if zero_stage <= 2:
|
172 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
173 |
+
elif zero_stage == 3:
|
174 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
175 |
+
else:
|
176 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
177 |
+
|
178 |
+
if zero_stage <= 2:
|
179 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
180 |
+
elif zero_stage == 3:
|
181 |
+
# if there is more than one param group, there will be multiple flattened tensors - one
|
182 |
+
# flattened tensor per group - for simplicity merge them into a single tensor
|
183 |
+
#
|
184 |
+
# XXX: could make the script more memory efficient for when there are multiple groups - it
|
185 |
+
# will require matching the sub-lists of param_shapes for each param group flattened tensor
|
186 |
+
|
187 |
+
fp32_flat_groups = [
|
188 |
+
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
|
189 |
+
]
|
190 |
+
|
191 |
+
return zero_stage, world_size, fp32_flat_groups
|
192 |
+
|
193 |
+
|
194 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
|
195 |
+
"""
|
196 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
197 |
+
|
198 |
+
Args:
|
199 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
200 |
+
|
201 |
+
"""
|
202 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
203 |
+
|
204 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
205 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
206 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
207 |
+
|
208 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
209 |
+
|
210 |
+
zero_model_states = parse_model_states(model_files)
|
211 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
212 |
+
|
213 |
+
if zero_stage <= 2:
|
214 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
|
215 |
+
elif zero_stage == 3:
|
216 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
|
217 |
+
|
218 |
+
|
219 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
220 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
221 |
+
return
|
222 |
+
|
223 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
224 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
225 |
+
|
226 |
+
if debug:
|
227 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
228 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
229 |
+
|
230 |
+
wanted_params = len(frozen_param_shapes)
|
231 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
232 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
233 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
234 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
235 |
+
|
236 |
+
total_params = 0
|
237 |
+
total_numel = 0
|
238 |
+
for name, shape in frozen_param_shapes.items():
|
239 |
+
total_params += 1
|
240 |
+
unpartitioned_numel = shape.numel()
|
241 |
+
total_numel += unpartitioned_numel
|
242 |
+
|
243 |
+
state_dict[name] = frozen_param_fragments[name]
|
244 |
+
|
245 |
+
if debug:
|
246 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
247 |
+
|
248 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
249 |
+
|
250 |
+
|
251 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
252 |
+
param_shapes = zero_model_states[0].param_shapes
|
253 |
+
|
254 |
+
# Reconstruction protocol:
|
255 |
+
#
|
256 |
+
# XXX: document this
|
257 |
+
|
258 |
+
if debug:
|
259 |
+
for i in range(world_size):
|
260 |
+
for j in range(len(fp32_flat_groups[0])):
|
261 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
262 |
+
|
263 |
+
# XXX: memory usage doubles here (zero2)
|
264 |
+
num_param_groups = len(fp32_flat_groups[0])
|
265 |
+
merged_single_partition_of_fp32_groups = []
|
266 |
+
for i in range(num_param_groups):
|
267 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
268 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
269 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
270 |
+
avail_numel = sum(
|
271 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
272 |
+
|
273 |
+
if debug:
|
274 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
275 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
276 |
+
# not asserting if there is a mismatch due to possible padding
|
277 |
+
print(f"Have {avail_numel} numels to process.")
|
278 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
279 |
+
|
280 |
+
# params
|
281 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
282 |
+
# out-of-core computing solution
|
283 |
+
total_numel = 0
|
284 |
+
total_params = 0
|
285 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
286 |
+
offset = 0
|
287 |
+
avail_numel = full_single_fp32_vector.numel()
|
288 |
+
for name, shape in shapes.items():
|
289 |
+
|
290 |
+
unpartitioned_numel = shape.numel()
|
291 |
+
total_numel += unpartitioned_numel
|
292 |
+
total_params += 1
|
293 |
+
|
294 |
+
if debug:
|
295 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
296 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
297 |
+
offset += unpartitioned_numel
|
298 |
+
|
299 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
300 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
301 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
302 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
303 |
+
align_to = 2 * world_size
|
304 |
+
|
305 |
+
def zero2_align(x):
|
306 |
+
return align_to * math.ceil(x / align_to)
|
307 |
+
|
308 |
+
if debug:
|
309 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
310 |
+
|
311 |
+
offset = zero2_align(offset)
|
312 |
+
avail_numel = zero2_align(avail_numel)
|
313 |
+
|
314 |
+
if debug:
|
315 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
316 |
+
|
317 |
+
# Sanity check
|
318 |
+
if offset != avail_numel:
|
319 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
320 |
+
|
321 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
322 |
+
|
323 |
+
|
324 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
|
325 |
+
state_dict = OrderedDict()
|
326 |
+
|
327 |
+
# buffers
|
328 |
+
buffers = zero_model_states[0].buffers
|
329 |
+
state_dict.update(buffers)
|
330 |
+
if debug:
|
331 |
+
print(f"added {len(buffers)} buffers")
|
332 |
+
|
333 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
334 |
+
|
335 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
336 |
+
|
337 |
+
# recover shared parameters
|
338 |
+
for pair in zero_model_states[0].shared_params:
|
339 |
+
if pair[1] in state_dict:
|
340 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
341 |
+
|
342 |
+
return state_dict
|
343 |
+
|
344 |
+
|
345 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
346 |
+
remainder = unpartitioned_numel % world_size
|
347 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
348 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
349 |
+
return partitioned_numel, padding_numel
|
350 |
+
|
351 |
+
|
352 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
353 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
354 |
+
return
|
355 |
+
|
356 |
+
if debug:
|
357 |
+
for i in range(world_size):
|
358 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
359 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
360 |
+
|
361 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
362 |
+
wanted_params = len(frozen_param_shapes)
|
363 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
364 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
365 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
366 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
367 |
+
|
368 |
+
total_params = 0
|
369 |
+
total_numel = 0
|
370 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
371 |
+
total_params += 1
|
372 |
+
unpartitioned_numel = shape.numel()
|
373 |
+
total_numel += unpartitioned_numel
|
374 |
+
|
375 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
376 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
377 |
+
|
378 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
379 |
+
|
380 |
+
if debug:
|
381 |
+
print(
|
382 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
383 |
+
)
|
384 |
+
|
385 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
386 |
+
|
387 |
+
|
388 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
389 |
+
param_shapes = zero_model_states[0].param_shapes
|
390 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
391 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
392 |
+
# param, re-consolidating each param, while dealing with padding if any
|
393 |
+
|
394 |
+
# merge list of dicts, preserving order
|
395 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
396 |
+
|
397 |
+
if debug:
|
398 |
+
for i in range(world_size):
|
399 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
400 |
+
|
401 |
+
wanted_params = len(param_shapes)
|
402 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
403 |
+
# not asserting if there is a mismatch due to possible padding
|
404 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
405 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
406 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
407 |
+
|
408 |
+
# params
|
409 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
410 |
+
# out-of-core computing solution
|
411 |
+
offset = 0
|
412 |
+
total_numel = 0
|
413 |
+
total_params = 0
|
414 |
+
for name, shape in param_shapes.items():
|
415 |
+
|
416 |
+
unpartitioned_numel = shape.numel()
|
417 |
+
total_numel += unpartitioned_numel
|
418 |
+
total_params += 1
|
419 |
+
|
420 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
421 |
+
|
422 |
+
if debug:
|
423 |
+
print(
|
424 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
425 |
+
)
|
426 |
+
|
427 |
+
# XXX: memory usage doubles here
|
428 |
+
state_dict[name] = torch.cat(
|
429 |
+
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
|
430 |
+
0).narrow(0, 0, unpartitioned_numel).view(shape)
|
431 |
+
offset += partitioned_numel
|
432 |
+
|
433 |
+
offset *= world_size
|
434 |
+
|
435 |
+
# Sanity check
|
436 |
+
if offset != avail_numel:
|
437 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
438 |
+
|
439 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
440 |
+
|
441 |
+
|
442 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
|
443 |
+
state_dict = OrderedDict()
|
444 |
+
|
445 |
+
# buffers
|
446 |
+
buffers = zero_model_states[0].buffers
|
447 |
+
state_dict.update(buffers)
|
448 |
+
if debug:
|
449 |
+
print(f"added {len(buffers)} buffers")
|
450 |
+
|
451 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
452 |
+
|
453 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
454 |
+
|
455 |
+
# recover shared parameters
|
456 |
+
for pair in zero_model_states[0].shared_params:
|
457 |
+
if pair[1] in state_dict:
|
458 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
459 |
+
|
460 |
+
return state_dict
|
461 |
+
|
462 |
+
|
463 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
|
464 |
+
"""
|
465 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
466 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
467 |
+
via a model hub.
|
468 |
+
|
469 |
+
Args:
|
470 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
471 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
472 |
+
|
473 |
+
Returns:
|
474 |
+
- pytorch ``state_dict``
|
475 |
+
|
476 |
+
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
|
477 |
+
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
478 |
+
the checkpoint.
|
479 |
+
|
480 |
+
A typical usage might be ::
|
481 |
+
|
482 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
483 |
+
# do the training and checkpoint saving
|
484 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
485 |
+
model = model.cpu() # move to cpu
|
486 |
+
model.load_state_dict(state_dict)
|
487 |
+
# submit to model hub or save the model to share with others
|
488 |
+
|
489 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
490 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
491 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
492 |
+
|
493 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
494 |
+
|
495 |
+
"""
|
496 |
+
if tag is None:
|
497 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
498 |
+
if os.path.isfile(latest_path):
|
499 |
+
with open(latest_path, 'r') as fd:
|
500 |
+
tag = fd.read().strip()
|
501 |
+
else:
|
502 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
503 |
+
|
504 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
505 |
+
|
506 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
507 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
508 |
+
|
509 |
+
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
|
510 |
+
|
511 |
+
|
512 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
|
513 |
+
"""
|
514 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
515 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
516 |
+
|
517 |
+
Args:
|
518 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
519 |
+
- ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
|
520 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
521 |
+
"""
|
522 |
+
|
523 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
524 |
+
print(f"Saving fp32 state dict to {output_file}")
|
525 |
+
torch.save(state_dict, output_file)
|
526 |
+
|
527 |
+
|
528 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
529 |
+
"""
|
530 |
+
1. Put the provided model to cpu
|
531 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
532 |
+
3. Load it into the provided model
|
533 |
+
|
534 |
+
Args:
|
535 |
+
- ``model``: the model object to update
|
536 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
537 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
538 |
+
|
539 |
+
Returns:
|
540 |
+
- ``model`: modified model
|
541 |
+
|
542 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
543 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
544 |
+
conveniently placed for you in the checkpoint folder.
|
545 |
+
|
546 |
+
A typical usage might be ::
|
547 |
+
|
548 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
549 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
550 |
+
# submit to model hub or save the model to share with others
|
551 |
+
|
552 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
553 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
554 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
555 |
+
|
556 |
+
"""
|
557 |
+
logger.info(f"Extracting fp32 weights")
|
558 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
559 |
+
|
560 |
+
logger.info(f"Overwriting model with fp32 weights")
|
561 |
+
model = model.cpu()
|
562 |
+
model.load_state_dict(state_dict, strict=False)
|
563 |
+
|
564 |
+
return model
|
565 |
+
|
566 |
+
|
567 |
+
if __name__ == "__main__":
|
568 |
+
|
569 |
+
parser = argparse.ArgumentParser()
|
570 |
+
parser.add_argument("checkpoint_dir",
|
571 |
+
type=str,
|
572 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
573 |
+
parser.add_argument(
|
574 |
+
"output_file",
|
575 |
+
type=str,
|
576 |
+
help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
|
577 |
+
parser.add_argument("-t",
|
578 |
+
"--tag",
|
579 |
+
type=str,
|
580 |
+
default=None,
|
581 |
+
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
582 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
583 |
+
args = parser.parse_args()
|
584 |
+
|
585 |
+
debug = args.debug
|
586 |
+
|
587 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)
|