Ggboykxz commited on
Commit
1f856fe
·
verified ·
1 Parent(s): 106e0ca

checkpoint ckpt-00000374 (full)

Browse files
.gitattributes CHANGED
@@ -59,3 +59,4 @@ ckpt-00000321/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
59
  ckpt-00000340/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
60
  ckpt-00000347/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
61
  ckpt-00000356/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
59
  ckpt-00000340/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
60
  ckpt-00000347/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
61
  ckpt-00000356/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
62
+ ckpt-00000374/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
ckpt-00000374/SHA256SUMS ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ efd6f53eb5fb54ae9b5584597413d0d85bb50a52af293caddf631e12ffde1788 adapter_config.json
2
+ ad5e79502d939c626444db296145af54f777aa6c769dd2fb06605faacbcd5d09 adapter_model.safetensors
3
+ 9ffd3858bd2907e7f8056e0bf4541d7ce285ec429e3d521f3fa62e04c524cb2d config.json
4
+ 8156c1f400dcbe21d2d5275222c768dbb29a6ea64b7b8a07ed3d1e6b3c6899c8 env.json
5
+ 466e038ef025d6961e223badefb0e885886454baf8c4d2dc952fac28741609e2 optimizer.pt
6
+ 112c92514399ea0e1690c11da38efce5c92dc1a33f71ca32a6b2c59669b1485a rng_state.pt
7
+ e8ba9ac8b9e72613cc21e708101d08b5d93eaa400e645b4c9e1132c81cb6a14a scheduler.pt
8
+ 87a2728cb8dc9fe424d624542f6060ec05a1d285ebbec578bb078900e33396b5 tokenizer/chat_template.jinja
9
+ be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506 tokenizer/tokenizer.json
10
+ ddb9f850ca6559a928bb25d511f72e3c6eff81395334a4e0eeec670448333d09 tokenizer/tokenizer_config.json
11
+ 221f39d7551f1867ccee69e10cebd91a252557de35c069bcf65ddc31ab3c87d6 trainer_state.json
ckpt-00000374/adapter_config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3-1.7B-Base",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "kasa_config": null,
16
+ "layer_replication": null,
17
+ "layers_pattern": null,
18
+ "layers_to_transform": null,
19
+ "loftq_config": {},
20
+ "lora_alpha": 64,
21
+ "lora_bias": false,
22
+ "lora_dropout": 0.0,
23
+ "lora_ga_config": null,
24
+ "megatron_config": null,
25
+ "megatron_core": "megatron.core",
26
+ "modules_to_save": null,
27
+ "monteclora_config": null,
28
+ "peft_type": "LORA",
29
+ "peft_version": "0.21.2",
30
+ "qalora_group_size": 16,
31
+ "r": 32,
32
+ "rank_pattern": {},
33
+ "revision": null,
34
+ "target_modules": [
35
+ "down_proj",
36
+ "gate_proj",
37
+ "up_proj",
38
+ "q_proj",
39
+ "k_proj",
40
+ "o_proj",
41
+ "v_proj"
42
+ ],
43
+ "target_parameters": null,
44
+ "task_type": "CAUSAL_LM",
45
+ "trainable_token_indices": null,
46
+ "use_bdlora": null,
47
+ "use_dora": false,
48
+ "use_qalora": false,
49
+ "use_rslora": true,
50
+ "velora_config": null
51
+ }
ckpt-00000374/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5e79502d939c626444db296145af54f777aa6c769dd2fb06605faacbcd5d09
3
+ size 139512976
ckpt-00000374/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data": {
3
+ "local_dir": null,
4
+ "max_tokens_per_shard": 50000000,
5
+ "revision": "file-sha256:2472824c641a4c22b30823da4042d42358e8cf39b986fc4c92a7f6ff6d3a2e74",
6
+ "seq_len": 2048,
7
+ "sft_file": "data/python-sft/train.jsonl",
8
+ "source_manifest": null
9
+ },
10
+ "eval": {
11
+ "domain_set": null,
12
+ "general_samples": 0,
13
+ "seed": 3407
14
+ },
15
+ "lora": {
16
+ "alpha": 64,
17
+ "dropout": 0.0,
18
+ "r": 32,
19
+ "target": [
20
+ "q_proj",
21
+ "k_proj",
22
+ "v_proj",
23
+ "o_proj",
24
+ "gate_proj",
25
+ "up_proj",
26
+ "down_proj"
27
+ ],
28
+ "use_rslora": true
29
+ },
30
+ "model": {
31
+ "attn": "sdpa",
32
+ "base": "Qwen/Qwen3-1.7B-Base",
33
+ "gradient_checkpointing": "unsloth",
34
+ "load_in_4bit": false,
35
+ "trust_remote_code": false
36
+ },
37
+ "resilience": {
38
+ "ckpt_every_minutes": 6,
39
+ "ckpt_every_steps": 20,
40
+ "heartbeat_seconds": 120,
41
+ "keep_last": 3,
42
+ "keep_milestones_every": 250,
43
+ "max_rollbacks": 3,
44
+ "push_backpressure_minutes": 15,
45
+ "resume_loss_tolerance": 0.05,
46
+ "time_budget_minutes": 20
47
+ },
48
+ "run": {
49
+ "base_slug": "qwen3-1.7b-python-sft",
50
+ "data_repo": "Ggboykxz/t4llm-python-data",
51
+ "data_revision": "file-sha256:2472824c641a4c22b30823da4042d42358e8cf39b986fc4c92a7f6ff6d3a2e74",
52
+ "hub_repo": "Ggboykxz/t4llm-python-sft",
53
+ "phase": "sft",
54
+ "seed": 3407
55
+ },
56
+ "train": {
57
+ "dtype": "fp16",
58
+ "grad_accum": 16,
59
+ "logging_steps": 1,
60
+ "lr": 0.0001,
61
+ "max_grad_norm": 1.0,
62
+ "max_steps": 625,
63
+ "micro_batch": 1,
64
+ "neftune_noise_alpha": 5.0,
65
+ "num_train_epochs": 1,
66
+ "optim": "paged_adamw_8bit",
67
+ "packing": false,
68
+ "scheduler": "cosine",
69
+ "seq_len": 2048,
70
+ "train_on_responses_only": true,
71
+ "warmup_ratio": 0.02,
72
+ "weight_decay": 0.0
73
+ }
74
+ }
ckpt-00000374/env.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bf16_reported": true,
3
+ "cc_major": 7,
4
+ "cc_minor": 5,
5
+ "compute_capability": "7.5",
6
+ "cuda_available": true,
7
+ "cuda_version": "13.0",
8
+ "git_sha": "bf33c5e53e9ddb0aeb431e5514ce6d557a3f8b00",
9
+ "gpu_name": "Tesla T4",
10
+ "platform": "Linux-6.6.159+-x86_64-with-glibc2.39",
11
+ "python": "3.13.16",
12
+ "reasons": [],
13
+ "sdpa": true,
14
+ "torch_version": "2.14.1+cu130",
15
+ "training_capable": true,
16
+ "vram_gib": 14.56
17
+ }
ckpt-00000374/manifest.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config_hash": "06787eba",
3
+ "consumed_tokens": 1147314,
4
+ "created_utc": "2026-11-16T16:58:32+00:00",
5
+ "cursor": {
6
+ "consumed_tokens": 1147314,
7
+ "data_revision": "file-sha256:2472824c641a4c22b30823da4042d42358e8cf39b986fc4c92a7f6ff6d3a2e74",
8
+ "sample_idx": 5984,
9
+ "shard_idx": 0
10
+ },
11
+ "files": {
12
+ "SHA256SUMS": {
13
+ "bytes": 938,
14
+ "sha256": "7bc3463ca9c9dbf0c49bbada4f7e22142896e5d9a7ce0b89899fe4ee48692419"
15
+ },
16
+ "adapter_config.json": {
17
+ "bytes": 1174,
18
+ "sha256": "efd6f53eb5fb54ae9b5584597413d0d85bb50a52af293caddf631e12ffde1788"
19
+ },
20
+ "adapter_model.safetensors": {
21
+ "bytes": 139512976,
22
+ "sha256": "ad5e79502d939c626444db296145af54f777aa6c769dd2fb06605faacbcd5d09"
23
+ },
24
+ "config.json": {
25
+ "bytes": 1761,
26
+ "sha256": "9ffd3858bd2907e7f8056e0bf4541d7ce285ec429e3d521f3fa62e04c524cb2d"
27
+ },
28
+ "env.json": {
29
+ "bytes": 422,
30
+ "sha256": "8156c1f400dcbe21d2d5275222c768dbb29a6ea64b7b8a07ed3d1e6b3c6899c8"
31
+ },
32
+ "optimizer.pt": {
33
+ "bytes": 72304915,
34
+ "sha256": "466e038ef025d6961e223badefb0e885886454baf8c4d2dc952fac28741609e2"
35
+ },
36
+ "rng_state.pt": {
37
+ "bytes": 14605,
38
+ "sha256": "112c92514399ea0e1690c11da38efce5c92dc1a33f71ca32a6b2c59669b1485a"
39
+ },
40
+ "scheduler.pt": {
41
+ "bytes": 1401,
42
+ "sha256": "e8ba9ac8b9e72613cc21e708101d08b5d93eaa400e645b4c9e1132c81cb6a14a"
43
+ },
44
+ "tokenizer/chat_template.jinja": {
45
+ "bytes": 4116,
46
+ "sha256": "87a2728cb8dc9fe424d624542f6060ec05a1d285ebbec578bb078900e33396b5"
47
+ },
48
+ "tokenizer/tokenizer.json": {
49
+ "bytes": 11422650,
50
+ "sha256": "be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506"
51
+ },
52
+ "tokenizer/tokenizer_config.json": {
53
+ "bytes": 697,
54
+ "sha256": "ddb9f850ca6559a928bb25d511f72e3c6eff81395334a4e0eeec670448333d09"
55
+ },
56
+ "trainer_state.json": {
57
+ "bytes": 872,
58
+ "sha256": "221f39d7551f1867ccee69e10cebd91a252557de35c069bcf65ddc31ab3c87d6"
59
+ }
60
+ },
61
+ "forked": false,
62
+ "global_step": 374,
63
+ "loss_ema": 0.5499584562558908,
64
+ "optimizer_reset": false,
65
+ "run_id": "qwen3-1.7b-python-sft-sft-06787eba",
66
+ "schema_version": 1,
67
+ "tier": "full"
68
+ }
ckpt-00000374/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:466e038ef025d6961e223badefb0e885886454baf8c4d2dc952fac28741609e2
3
+ size 72304915
ckpt-00000374/rng_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:112c92514399ea0e1690c11da38efce5c92dc1a33f71ca32a6b2c59669b1485a
3
+ size 14605
ckpt-00000374/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8ba9ac8b9e72613cc21e708101d08b5d93eaa400e645b4c9e1132c81cb6a14a
3
+ size 1401
ckpt-00000374/tokenizer/chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 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.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
ckpt-00000374/tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
+ size 11422650
ckpt-00000374/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": false,
24
+ "local_files_only": false,
25
+ "model_max_length": 131072,
26
+ "pad_token": "<|endoftext|>",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null
30
+ }
ckpt-00000374/trainer_state.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "consumed_tokens": 1147314,
4
+ "cursor": {
5
+ "consumed_tokens": 1147314,
6
+ "data_revision": "file-sha256:2472824c641a4c22b30823da4042d42358e8cf39b986fc4c92a7f6ff6d3a2e74",
7
+ "sample_idx": 5984,
8
+ "shard_idx": 0
9
+ },
10
+ "epoch": 1147314.0,
11
+ "forked": false,
12
+ "global_step": 374,
13
+ "loss_ema": 0.5499584562558908,
14
+ "lr_scale": 1.0,
15
+ "oom_stage": 0,
16
+ "optimizer_reset": false,
17
+ "rollbacks": 0,
18
+ "run_id": "qwen3-1.7b-python-sft-sft-06787eba",
19
+ "runtime_notes": [
20
+ "unsloth unavailable; using standard non-reentrant HF checkpointing",
21
+ "phase trainer: prompt/completion masking, no packing, data_revision=file-sha256:2472824c641a4c22b30823da4042d42358e8cf39b986fc4c92a7f6ff6d3a2e74"
22
+ ],
23
+ "session_id": "7dbc14587ba6",
24
+ "skipped_steps": 0,
25
+ "tier": "full",
26
+ "total_steps": 384,
27
+ "updated_utc": "2026-11-16T16:58:30+00:00"
28
+ }