Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- README.md +50 -0
- added_tokens.json +28 -0
- all_results.json +8 -0
- chat_template.jinja +89 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +3 -0
- checkpoint-87/global_step87/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
- checkpoint-87/global_step87/zero_pp_rank_10_mp_rank_00_model_states.pt +3 -0
- checkpoint-87/global_step87/zero_pp_rank_11_mp_rank_00_model_states.pt +3 -0
- checkpoint-87/global_step87/zero_pp_rank_12_mp_rank_00_model_states.pt +3 -0
- checkpoint-87/global_step87/zero_pp_rank_13_mp_rank_00_model_states.pt +3 -0
- checkpoint-87/global_step87/zero_pp_rank_14_mp_rank_00_model_states.pt +3 -0
- checkpoint-87/global_step87/zero_pp_rank_15_mp_rank_00_model_states.pt +3 -0
- checkpoint-87/global_step87/zero_pp_rank_16_mp_rank_00_model_states.pt +3 -0
- checkpoint-87/global_step87/zero_pp_rank_17_mp_rank_00_model_states.pt +3 -0
- checkpoint-87/global_step87/zero_pp_rank_18_mp_rank_00_model_states.pt +3 -0
- checkpoint-87/global_step87/zero_pp_rank_19_mp_rank_00_model_states.pt +3 -0
- checkpoint-87/global_step87/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
- checkpoint-87/global_step87/zero_pp_rank_20_mp_rank_00_model_states.pt +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
---
|
3 |
+
|
4 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
5 |
+
should probably proofread and complete it, then remove this comment. -->
|
6 |
+
|
7 |
+
# Qwen3-0.6B-code-scorev1
|
8 |
+
|
9 |
+
This model is a fine-tuned version of [./model/Qwen3-0.6B](https://huggingface.co/./model/Qwen3-0.6B) on the score_model_train_datav1 dataset.
|
10 |
+
|
11 |
+
## Model description
|
12 |
+
|
13 |
+
More information needed
|
14 |
+
|
15 |
+
## Intended uses & limitations
|
16 |
+
|
17 |
+
More information needed
|
18 |
+
|
19 |
+
## Training and evaluation data
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Training procedure
|
24 |
+
|
25 |
+
### Training hyperparameters
|
26 |
+
|
27 |
+
The following hyperparameters were used during training:
|
28 |
+
- learning_rate: 1e-05
|
29 |
+
- train_batch_size: 16
|
30 |
+
- eval_batch_size: 8
|
31 |
+
- seed: 42
|
32 |
+
- distributed_type: multi-GPU
|
33 |
+
- num_devices: 32
|
34 |
+
- total_train_batch_size: 512
|
35 |
+
- total_eval_batch_size: 256
|
36 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
37 |
+
- lr_scheduler_type: linear
|
38 |
+
- lr_scheduler_warmup_ratio: 0.1
|
39 |
+
- num_epochs: 1
|
40 |
+
|
41 |
+
### Training results
|
42 |
+
|
43 |
+
|
44 |
+
|
45 |
+
### Framework versions
|
46 |
+
|
47 |
+
- Transformers 4.52.4
|
48 |
+
- Pytorch 2.6.0+cu124
|
49 |
+
- Datasets 3.6.0
|
50 |
+
- Tokenizers 0.21.1
|
added_tokens.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</think>": 151668,
|
3 |
+
"</tool_call>": 151658,
|
4 |
+
"</tool_response>": 151666,
|
5 |
+
"<think>": 151667,
|
6 |
+
"<tool_call>": 151657,
|
7 |
+
"<tool_response>": 151665,
|
8 |
+
"<|box_end|>": 151649,
|
9 |
+
"<|box_start|>": 151648,
|
10 |
+
"<|endoftext|>": 151643,
|
11 |
+
"<|file_sep|>": 151664,
|
12 |
+
"<|fim_middle|>": 151660,
|
13 |
+
"<|fim_pad|>": 151662,
|
14 |
+
"<|fim_prefix|>": 151659,
|
15 |
+
"<|fim_suffix|>": 151661,
|
16 |
+
"<|im_end|>": 151645,
|
17 |
+
"<|im_start|>": 151644,
|
18 |
+
"<|image_pad|>": 151655,
|
19 |
+
"<|object_ref_end|>": 151647,
|
20 |
+
"<|object_ref_start|>": 151646,
|
21 |
+
"<|quad_end|>": 151651,
|
22 |
+
"<|quad_start|>": 151650,
|
23 |
+
"<|repo_name|>": 151663,
|
24 |
+
"<|video_pad|>": 151656,
|
25 |
+
"<|vision_end|>": 151653,
|
26 |
+
"<|vision_pad|>": 151654,
|
27 |
+
"<|vision_start|>": 151652
|
28 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 573945069699072.0,
|
4 |
+
"train_loss": 2.7985938061242814,
|
5 |
+
"train_runtime": 14173.0448,
|
6 |
+
"train_samples_per_second": 3.119,
|
7 |
+
"train_steps_per_second": 0.006
|
8 |
+
}
|
chat_template.jinja
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{%- if tools %}
|
2 |
+
{{- '<|im_start|>system\n' }}
|
3 |
+
{%- if messages[0].role == 'system' %}
|
4 |
+
{{- messages[0].content + '\n\n' }}
|
5 |
+
{%- endif %}
|
6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
7 |
+
{%- for tool in tools %}
|
8 |
+
{{- "\n" }}
|
9 |
+
{{- tool | tojson }}
|
10 |
+
{%- endfor %}
|
11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
12 |
+
{%- else %}
|
13 |
+
{%- if messages[0].role == 'system' %}
|
14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
15 |
+
{%- endif %}
|
16 |
+
{%- endif %}
|
17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
18 |
+
{%- for message in messages[::-1] %}
|
19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
21 |
+
{%- set ns.multi_step_tool = false %}
|
22 |
+
{%- set ns.last_query_index = index %}
|
23 |
+
{%- endif %}
|
24 |
+
{%- endfor %}
|
25 |
+
{%- for message in messages %}
|
26 |
+
{%- if message.content is string %}
|
27 |
+
{%- set content = message.content %}
|
28 |
+
{%- else %}
|
29 |
+
{%- set content = '' %}
|
30 |
+
{%- endif %}
|
31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
33 |
+
{%- elif message.role == "assistant" %}
|
34 |
+
{%- set reasoning_content = '' %}
|
35 |
+
{%- if message.reasoning_content is string %}
|
36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
37 |
+
{%- else %}
|
38 |
+
{%- if '</think>' in content %}
|
39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
41 |
+
{%- endif %}
|
42 |
+
{%- endif %}
|
43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
46 |
+
{%- else %}
|
47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
48 |
+
{%- endif %}
|
49 |
+
{%- else %}
|
50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
51 |
+
{%- endif %}
|
52 |
+
{%- if message.tool_calls %}
|
53 |
+
{%- for tool_call in message.tool_calls %}
|
54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
55 |
+
{{- '\n' }}
|
56 |
+
{%- endif %}
|
57 |
+
{%- if tool_call.function %}
|
58 |
+
{%- set tool_call = tool_call.function %}
|
59 |
+
{%- endif %}
|
60 |
+
{{- '<tool_call>\n{"name": "' }}
|
61 |
+
{{- tool_call.name }}
|
62 |
+
{{- '", "arguments": ' }}
|
63 |
+
{%- if tool_call.arguments is string %}
|
64 |
+
{{- tool_call.arguments }}
|
65 |
+
{%- else %}
|
66 |
+
{{- tool_call.arguments | tojson }}
|
67 |
+
{%- endif %}
|
68 |
+
{{- '}\n</tool_call>' }}
|
69 |
+
{%- endfor %}
|
70 |
+
{%- endif %}
|
71 |
+
{{- '<|im_end|>\n' }}
|
72 |
+
{%- elif message.role == "tool" %}
|
73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
74 |
+
{{- '<|im_start|>user' }}
|
75 |
+
{%- endif %}
|
76 |
+
{{- '\n<tool_response>\n' }}
|
77 |
+
{{- content }}
|
78 |
+
{{- '\n</tool_response>' }}
|
79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
80 |
+
{{- '<|im_end|>\n' }}
|
81 |
+
{%- endif %}
|
82 |
+
{%- endif %}
|
83 |
+
{%- endfor %}
|
84 |
+
{%- if add_generation_prompt %}
|
85 |
+
{{- '<|im_start|>assistant\n' }}
|
86 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
87 |
+
{{- '<think>\n\n</think>\n\n' }}
|
88 |
+
{%- endif %}
|
89 |
+
{%- endif %}
|
checkpoint-87/global_step87/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 sha256:2ed6959ebff935081a74ea9469e7100a4db69bc7dcb707623a8423e095e7ad73
|
3 |
+
size 223523824
|
checkpoint-87/global_step87/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a88d6be7b684cf68fe46ab85f5ada259020f972122781ab4cce1a957a86522e
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2eaca0b9dc29ce7f488150081c3ce170c4da3740127eaf52f33002cc0273320
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e318f183a855ff8cdbfedfaf564d2848caadcc25b30230bf06603a827e92256
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47cb89498fef55d24dcf844dc786c8279dbce0f2ab880aac8ac06fdabb3ef756
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd19a82a516f013ecb8dd4c937f4b710c467aa62cb5094407df8b644c313ea62
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bab8b148486f370ec94982b8ae2acd32398185c0e26d15241262b71f3d0c276e
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af8914b3cfb70f57b07c32423d06f97adbd9556fe5534ebebc27d0680bd4838d
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:782b68c72f0d7e9e3d62cb6da3ad02fe50d06bb358902aa9cddfd0f22616a195
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09f8d978d88b46ae54177f11880746f00056fc88ab7f07fc9b4d71a5e6353a04
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb484c2d214aba971de199e70b03dfd5e5a5d6ca29304a0bbc880273e5aaa689
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/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 sha256:553ecc2e85fcf843ec784758a496564dec840e9f63d2c8bab38c6b29e18ea922
|
3 |
+
size 223523824
|
checkpoint-87/global_step87/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4aaa396013e3af326be61ae058d8d580cc79af876f536f2b7d89ae532bbbc29
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd424aa91a8a03469a8dc0c724f015e83fbdbc49c5331cd40dc5cf382bae329f
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a0f6a7f7a2b61cf7d3f2e299f07c5fbe7a379dd002dd82c82574740f3f8e554
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7ac47ea9382557b3dfcafb14c2a2f5b31963d51859ebd53ceae6e97d174cce1
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:557116e9980328e2efdcecba519d2d3c267b003d5cb93deebe7a13dc344fec3e
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd3a4dd8547b0248a4c0f09c0612e9c4f0ca369347b9bae3846eaf2efd808a0f
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5737d99e09f096f376f7733e879f7e2f73436e6b06f0799f2f68609c8f7d82f
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c1bc2267aeddf31b5255241796d89e6c86170b37559f39d6ee7c518de5f5cdc
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6a516ac4b45a4e5228ebf05fb41dc2c52d812b1568cb36c7a6eeece36d88995
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b48050ac4092ece86c35b26c46a6426ec97e55c48d14ae74647430080f3649f
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6595d21e6ae55cb5745024d8bc879c9ca9566160d283c743d86dcf32ac805eed
|
3 |
+
size 223523824
|
checkpoint-87/global_step87/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a9010654e4d2ed85cdf5c5be4d901c7c978c9dce045843b0240e5c8b9c833ea
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96b738d61587f49e2c82f884f0242090a1d02e07e6166a91ac625203be89c616
|
3 |
+
size 223523836
|
checkpoint-87/global_step87/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cee95b7e9b8626ba5bafedd50bdd67316fb5f2ea8c632f406d93cc184e269b63
|
3 |
+
size 223523824
|
checkpoint-87/global_step87/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a43797b361facb716332713f0226633442e3d3b111f028f996d7e586744b9e9
|
3 |
+
size 223523824
|
checkpoint-87/global_step87/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ae02dd2dd8234b0587609dbe6edcfb2d4974336f4f9693bc7f69f16cd5d5cb1
|
3 |
+
size 223523824
|
checkpoint-87/global_step87/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d72233a10380c57316838766fb739cd76624283536c5f55288766072f0edebb
|
3 |
+
size 223523824
|
checkpoint-87/global_step87/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfa123929b2e5cf0ed045824fe9dacb13e38c7c2eba2c7710e3d0f60b2cab7e5
|
3 |
+
size 223523824
|
checkpoint-87/global_step87/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ef0846f088cd53e179e4cbbb93a9dac875a61f2271daa2f9c547da09d02db07
|
3 |
+
size 223523824
|
checkpoint-87/global_step87/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9edf319db7d59bcdd20a9afe7253d7ccfa796b2b004c368c685787b3bd920f5
|
3 |
+
size 223523824
|
checkpoint-87/global_step87/zero_pp_rank_0_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:383308bf28e2ff7fac62826c52b8855966cb636cf03b16f265273d955cf72e87
|
3 |
+
size 156300
|
checkpoint-87/global_step87/zero_pp_rank_10_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60cde299347a2275c752c7b86de6e3c615532cb75116f6a3a24a41e5db2377ac
|
3 |
+
size 156550
|
checkpoint-87/global_step87/zero_pp_rank_11_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7947e9c6293f25a6c00236ff9e9d7ab334f14609fe954cdfeed1b6dd2b4ae18
|
3 |
+
size 156550
|
checkpoint-87/global_step87/zero_pp_rank_12_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97baea585e82bfcd375ac077e885d2c8a2edfe8fd0705f7a0a7409a759addfdc
|
3 |
+
size 156550
|
checkpoint-87/global_step87/zero_pp_rank_13_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd188509b7769f2cae2631bca63d58f2da3677a1bb55c6e1901a42c0e76ad519
|
3 |
+
size 156550
|
checkpoint-87/global_step87/zero_pp_rank_14_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80207f585378674307bf2558f30206a46ace8596d368c94d87c912caaeb2490e
|
3 |
+
size 156550
|
checkpoint-87/global_step87/zero_pp_rank_15_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca3f208e35f2613d79e915e831020ff22ad180f5569dd66fc91bc84d21cc917a
|
3 |
+
size 156550
|
checkpoint-87/global_step87/zero_pp_rank_16_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:039442f488e2c343cc150d894ff459f8132c5e956fa69b09fa9297686679cffe
|
3 |
+
size 156550
|
checkpoint-87/global_step87/zero_pp_rank_17_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5808b481a042bcdafb32d9181fa500889f65fd4593b68d54bffe037e3ad0cb3f
|
3 |
+
size 156550
|
checkpoint-87/global_step87/zero_pp_rank_18_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d6ed00417a066b433280a773ba4758b461a8437299c7c76bc3e0068762174e3
|
3 |
+
size 156550
|
checkpoint-87/global_step87/zero_pp_rank_19_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:582c4d81206aa8eedb155dea242ef33b9f6675160d98d57f72976f7672f8f391
|
3 |
+
size 156550
|
checkpoint-87/global_step87/zero_pp_rank_1_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d88b0a8b3c4cd974bbc2586eccaf540cbf0915e83a0d3cdafb53e0fcd6790c64
|
3 |
+
size 156236
|
checkpoint-87/global_step87/zero_pp_rank_20_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8a2fe35318700322996632cb31b411370ae77835bc968c139af28bb40ba56a7
|
3 |
+
size 156550
|