devoppro commited on
Commit
0039f68
·
verified ·
1 Parent(s): 5acd908

Training in progress, step 100, checkpoint

Browse files
.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
+ last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
last-checkpoint/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# 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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
last-checkpoint/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernLLMForCausalLM"
4
+ ],
5
+ "auto_map": {
6
+ "AutoConfig": "configuration_modern_llm.ModernLLMConfig",
7
+ "AutoModelForCausalLM": "modeling_modern_llm.ModernLLMForCausalLM"
8
+ },
9
+ "bos_token_id": 151643,
10
+ "dtype": "float32",
11
+ "eos_token_id": 151643,
12
+ "hidden_size": 768,
13
+ "intermediate_size": 2048,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "modern_llm",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "num_key_value_heads": 4,
19
+ "pad_token_id": 151643,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_theta": 1000000.0,
22
+ "transformers_version": "5.16.1",
23
+ "use_cache": false,
24
+ "vocab_size": 151936
25
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82604167769c5e31a61169397afe28cfe54822ae940e1ae59ec38b9bc14916c6
3
+ size 1235573136
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50c96d50d6374b48eae65ce0d02648465d139f9b138974f56314ebdc4bed7ea6
3
+ size 2471218763
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
3
+ size 14645
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4393a84a3109995aa1202073b039b12062e3189ed89aa0b94ef0510ba843009
3
+ size 1383
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:116b971bb63560610677655e38ba8be2afb415c6fd29c1d069804301bcde855e
3
+ size 1465
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e2b7649a086fbb9771cd78ec5b7ffa7069e16a82424a382950fedfa1e057861
3
+ size 11421991
last-checkpoint/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
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.025,
6
+ "eval_steps": 500,
7
+ "global_step": 100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0025,
14
+ "grad_norm": 63.713592529296875,
15
+ "learning_rate": 2.6999999999999996e-05,
16
+ "loss": 191.98138427734375,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.005,
21
+ "grad_norm": 38.076576232910156,
22
+ "learning_rate": 5.6999999999999996e-05,
23
+ "loss": 181.990380859375,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.0075,
28
+ "grad_norm": 26.96797752380371,
29
+ "learning_rate": 8.699999999999999e-05,
30
+ "loss": 169.53270263671874,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.01,
35
+ "grad_norm": 27.646766662597656,
36
+ "learning_rate": 0.000117,
37
+ "loss": 156.652734375,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.0125,
42
+ "grad_norm": 17.624582290649414,
43
+ "learning_rate": 0.000147,
44
+ "loss": 141.47476806640626,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.015,
49
+ "grad_norm": 16.46175765991211,
50
+ "learning_rate": 0.00017699999999999997,
51
+ "loss": 130.09698486328125,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.0175,
56
+ "grad_norm": 14.617616653442383,
57
+ "learning_rate": 0.00020699999999999996,
58
+ "loss": 125.59556884765625,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.02,
63
+ "grad_norm": 19.31058120727539,
64
+ "learning_rate": 0.000237,
65
+ "loss": 124.4946044921875,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.0225,
70
+ "grad_norm": 17.25510597229004,
71
+ "learning_rate": 0.000267,
72
+ "loss": 123.69156494140626,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.025,
77
+ "grad_norm": 18.677974700927734,
78
+ "learning_rate": 0.00029699999999999996,
79
+ "loss": 121.91258544921875,
80
+ "step": 100
81
+ }
82
+ ],
83
+ "logging_steps": 10,
84
+ "max_steps": 4000,
85
+ "num_input_tokens_seen": 0,
86
+ "num_train_epochs": 9223372036854775807,
87
+ "save_steps": 100,
88
+ "stateful_callbacks": {
89
+ "TrainerControl": {
90
+ "args": {
91
+ "should_epoch_stop": false,
92
+ "should_evaluate": false,
93
+ "should_log": false,
94
+ "should_save": true,
95
+ "should_training_stop": false
96
+ },
97
+ "attributes": {}
98
+ }
99
+ },
100
+ "total_flos": 1656326519032320.0,
101
+ "train_batch_size": 1,
102
+ "trial_name": null,
103
+ "trial_params": null
104
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21db9453d7d8ac6bfa4936e13632c57e87862815455df5498192c2b63e078d30
3
+ size 5201