melihcatal commited on
Commit
f0d1891
·
verified ·
1 Parent(s): 50e01c7

Delete granite-4.0-h-tiny/base

Browse files
granite-4.0-h-tiny/base/canary_meta.json DELETED
The diff for this file is too large to render. See raw diff
 
granite-4.0-h-tiny/base/metrics.jsonl DELETED
@@ -1,3 +0,0 @@
1
- {"timestamp": 1773822187.1417096, "event": "train_step", "step": 10, "epoch": 1, "metrics": {"train/step_loss": 4.135385597453398, "train/step_real_loss": 3.4641597270965576, "train/lr": 4.545454545454546e-05, "train/step_canary_loss": 14.875, "perf/step_duration_sec": 4.6632686029188335, "perf/samples_per_sec": 7.291023291842704, "perf/tokens_per_sec": 5700.722446774896, "perf/logical_batch_size": 34.0, "perf/logical_token_count": 26584.0, "perf/gradient_accumulation_steps": 4.0, "system/cuda_memory_allocated_gb": 16.85233783721924, "system/cuda_max_memory_allocated_gb": 60.90630769729614}}
2
- {"timestamp": 1773822228.5490818, "event": "train_step", "step": 20, "epoch": 1, "metrics": {"train/step_loss": 2.740965247154236, "train/step_real_loss": 2.740965247154236, "train/lr": 9.090909090909092e-05, "perf/step_duration_sec": 3.847110118251294, "perf/samples_per_sec": 8.317931906390456, "perf/tokens_per_sec": 6799.649398102124, "perf/logical_batch_size": 32.0, "perf/logical_token_count": 26159.0, "perf/gradient_accumulation_steps": 4.0, "system/cuda_memory_allocated_gb": 16.85233783721924, "system/cuda_max_memory_allocated_gb": 60.90630769729614}}
3
- {"timestamp": 1773822269.2440736, "event": "train_step", "step": 30, "epoch": 1, "metrics": {"train/step_loss": 1.4690485894680023, "train/step_real_loss": 1.4690485894680023, "train/lr": 9.990789447882137e-05, "perf/step_duration_sec": 3.921983283944428, "perf/samples_per_sec": 8.159137273990844, "perf/tokens_per_sec": 6951.839930480011, "perf/logical_batch_size": 32.0, "perf/logical_token_count": 27265.0, "perf/gradient_accumulation_steps": 4.0, "system/cuda_memory_allocated_gb": 16.85233783721924, "system/cuda_max_memory_allocated_gb": 60.90630769729614}}
 
 
 
 
granite-4.0-h-tiny/base/pretrain_lm_head.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:23d4c2cffb51b108b4c377ffa44775b5e654a4b01b09c46ca4e90494d144fd82
3
- size 309818984
 
 
 
 
granite-4.0-h-tiny/base/resolved_config.yaml DELETED
@@ -1,110 +0,0 @@
1
- model:
2
- name: ibm-granite/granite-4.0-h-tiny
3
- tokenizer_name: ibm-granite/granite-4.0-h-tiny
4
- max_length: 1024
5
- dtype: bfloat16
6
- trust_remote_code: true
7
- use_fast_tokenizer: true
8
- cache_dir: null
9
- local_files_only: false
10
- low_cpu_mem_usage: true
11
- tie_word_embeddings: true
12
- gradient_checkpointing: false
13
- use_chat_template: false
14
- dataset:
15
- name: melihcatal/codedp-cpt
16
- split: train
17
- mode: cpt
18
- text_column: text
19
- validation_ratio: 0.05
20
- max_samples: -1
21
- lora:
22
- enabled: true
23
- r: 16
24
- alpha: 32
25
- dropout: 0.05
26
- target_modules:
27
- - q_proj
28
- - k_proj
29
- - v_proj
30
- - o_proj
31
- modules_to_save:
32
- - lm_head
33
- bias: none
34
- training:
35
- seed: 42
36
- epochs: 2
37
- warmup_steps: null
38
- warmup_ratio: 0.05
39
- mixed_precision: false
40
- mixed_precision_dtype: bfloat16
41
- batch_size: 8
42
- eval_batch_size: 8
43
- eval_every_steps: 50
44
- eval_every_epochs: 1
45
- learning_rate: 0.0001
46
- optimizer: adamw
47
- lr_scheduler: cosine
48
- adam_beta1: 0.9
49
- adam_beta2: 0.999
50
- adam_epsilon: 1.0e-08
51
- sgd_momentum: 0.9
52
- weight_decay: 0.01
53
- max_grad_norm: 1.0
54
- log_every: 10
55
- gradient_accumulation_steps: 4
56
- num_workers: 4
57
- output_dir: runs/cpt/granite-4.0-h-tiny/base
58
- distributed:
59
- strategy: dpddp
60
- backend: nccl
61
- devices: null
62
- dp:
63
- module_validator: auto
64
- target_delta: 1.0e-05
65
- noise_multiplier: null
66
- max_grad_norm: 1.0
67
- grad_sample_mode: hooks
68
- clipping: flat
69
- secure_mode: false
70
- enabled: false
71
- target_epsilon: 8.0
72
- audit:
73
- enabled: true
74
- run_every_epoch: true
75
- epoch_device: cuda
76
- q_canary: auto
77
- num_canaries: 500
78
- prefix_length: 49
79
- num_digits: 12
80
- batch_size: 32
81
- delta: 1.0e-05
82
- p_values:
83
- - 0.05
84
- - 0.01
85
- paper_guess_fraction: 0.2
86
- paper_guess_steps: 20
87
- enable_holdout_empirical_epsilon: false
88
- holdout_seed: 42
89
- tie_seed: 42
90
- tracking:
91
- enabled: true
92
- tensorboard: true
93
- wandb: false
94
- wandb_project: codedp-finetune-h200-audit
95
- wandb_run_name: granite-4.0-h-tiny-cpt-base
96
- wandb_mode: online
97
- codecarbon: true
98
- codecarbon_output_file: codecarbon.csv
99
- codecarbon_measure_power_secs: 15
100
- codecarbon_country_iso_code: null
101
- codecarbon_project_name: codedp-granite-4.0-h-tiny-cpt-base
102
- moe:
103
- output_router_logits: false
104
- router_aux_loss_coef: 0.0
105
- freeze_router: true
106
- profile:
107
- enabled: false
108
- num_batches: 8
109
- top_experts: 8
110
- output_file: moe_expert_profile.json
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
granite-4.0-h-tiny/base/scalars.csv DELETED
@@ -1,35 +0,0 @@
1
- timestamp,event,step,epoch,key,value
2
- 1773822187.1417096,train_step,10,1,train/step_loss,4.135385597453398
3
- 1773822187.1417096,train_step,10,1,train/step_real_loss,3.4641597270965576
4
- 1773822187.1417096,train_step,10,1,train/lr,4.545454545454546e-05
5
- 1773822187.1417096,train_step,10,1,train/step_canary_loss,14.875
6
- 1773822187.1417096,train_step,10,1,perf/step_duration_sec,4.6632686029188335
7
- 1773822187.1417096,train_step,10,1,perf/samples_per_sec,7.291023291842704
8
- 1773822187.1417096,train_step,10,1,perf/tokens_per_sec,5700.722446774896
9
- 1773822187.1417096,train_step,10,1,perf/logical_batch_size,34.0
10
- 1773822187.1417096,train_step,10,1,perf/logical_token_count,26584.0
11
- 1773822187.1417096,train_step,10,1,perf/gradient_accumulation_steps,4.0
12
- 1773822187.1417096,train_step,10,1,system/cuda_memory_allocated_gb,16.85233783721924
13
- 1773822187.1417096,train_step,10,1,system/cuda_max_memory_allocated_gb,60.90630769729614
14
- 1773822228.5490818,train_step,20,1,train/step_loss,2.740965247154236
15
- 1773822228.5490818,train_step,20,1,train/step_real_loss,2.740965247154236
16
- 1773822228.5490818,train_step,20,1,train/lr,9.090909090909092e-05
17
- 1773822228.5490818,train_step,20,1,perf/step_duration_sec,3.847110118251294
18
- 1773822228.5490818,train_step,20,1,perf/samples_per_sec,8.317931906390456
19
- 1773822228.5490818,train_step,20,1,perf/tokens_per_sec,6799.649398102124
20
- 1773822228.5490818,train_step,20,1,perf/logical_batch_size,32.0
21
- 1773822228.5490818,train_step,20,1,perf/logical_token_count,26159.0
22
- 1773822228.5490818,train_step,20,1,perf/gradient_accumulation_steps,4.0
23
- 1773822228.5490818,train_step,20,1,system/cuda_memory_allocated_gb,16.85233783721924
24
- 1773822228.5490818,train_step,20,1,system/cuda_max_memory_allocated_gb,60.90630769729614
25
- 1773822269.2440736,train_step,30,1,train/step_loss,1.4690485894680023
26
- 1773822269.2440736,train_step,30,1,train/step_real_loss,1.4690485894680023
27
- 1773822269.2440736,train_step,30,1,train/lr,9.990789447882137e-05
28
- 1773822269.2440736,train_step,30,1,perf/step_duration_sec,3.921983283944428
29
- 1773822269.2440736,train_step,30,1,perf/samples_per_sec,8.159137273990844
30
- 1773822269.2440736,train_step,30,1,perf/tokens_per_sec,6951.839930480011
31
- 1773822269.2440736,train_step,30,1,perf/logical_batch_size,32.0
32
- 1773822269.2440736,train_step,30,1,perf/logical_token_count,27265.0
33
- 1773822269.2440736,train_step,30,1,perf/gradient_accumulation_steps,4.0
34
- 1773822269.2440736,train_step,30,1,system/cuda_memory_allocated_gb,16.85233783721924
35
- 1773822269.2440736,train_step,30,1,system/cuda_max_memory_allocated_gb,60.90630769729614
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
granite-4.0-h-tiny/base/summary.json DELETED
@@ -1,14 +0,0 @@
1
- {
2
- "perf/gradient_accumulation_steps": 4.0,
3
- "perf/logical_batch_size": 32.0,
4
- "perf/logical_token_count": 27265.0,
5
- "perf/samples_per_sec": 8.159137273990844,
6
- "perf/step_duration_sec": 3.921983283944428,
7
- "perf/tokens_per_sec": 6951.839930480011,
8
- "system/cuda_max_memory_allocated_gb": 60.90630769729614,
9
- "system/cuda_memory_allocated_gb": 16.85233783721924,
10
- "train/lr": 9.990789447882137e-05,
11
- "train/step_canary_loss": 14.875,
12
- "train/step_loss": 1.4690485894680023,
13
- "train/step_real_loss": 1.4690485894680023
14
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
granite-4.0-h-tiny/base/tensorboard/events.out.tfevents.1773821287.7b654b6988b0.8584.0 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe0c167665fdbf45f83b676d478f6af92c2626d071a9437e3ca43a57bfbff0e7
3
- size 2492
 
 
 
 
granite-4.0-h-tiny/base/tensorboard/events.out.tfevents.1773822014.7b654b6988b0.12188.0 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c89973f5dc5ca9db8dcf8d89fc15537086c1412b4d7c2e86ad24c71a708e9ed6
3
- size 4553
 
 
 
 
granite-4.0-h-tiny/base/tensorboard/events.out.tfevents.1773836879.7b654b6988b0.1831.0 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4603c9fd1760750a02bdd5cce3f70b508e5e399bc1686fea2bc7fb5b4404b93a
3
- size 2492
 
 
 
 
granite-4.0-h-tiny/base/tensorboard/events.out.tfevents.1773837130.7b654b6988b0.5644.0 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:909bbcf11aa31d7c69e14116801363182c686b6a26ebfca558fd1ec6569005e3
3
- size 2492
 
 
 
 
granite-4.0-h-tiny/base/tokenizer/chat_template.jinja DELETED
@@ -1,118 +0,0 @@
1
- {%- set tools_system_message_prefix = 'You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>' %}
2
- {%- set tools_system_message_suffix = '\n</tools>\n\nFor each tool 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>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.' %}
3
- {%- set documents_system_message_prefix = 'You are a helpful assistant with access to the following documents. You may use one or more documents to assist with the user query.\n\nYou are given a list of documents within <documents></documents> XML tags:\n<documents>' %}
4
- {%- set documents_system_message_suffix = '\n</documents>\n\nWrite the response to the user\'s input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.' %}
5
- {%- set g4_default_system_message = 'You are a helpful assistant. Please ensure responses are professional, accurate, and safe.' %}
6
- {%- if available_tools is defined and available_tools %}
7
- {%- set tools = available_tools %}
8
- {%- endif %}
9
- {%- set ns = namespace(tools_system_message=tools_system_message_prefix,
10
- documents_system_message=documents_system_message_prefix,
11
- default_system_message=g4_default_system_message,
12
- system_message=''
13
- ) %}
14
- {%- if tools %}
15
- {%- for tool in tools %}
16
- {%- set ns.tools_system_message = ns.tools_system_message + '\n' + (tool | tojson) %}
17
- {%- endfor %}
18
- {%- set ns.tools_system_message = ns.tools_system_message + tools_system_message_suffix %}
19
- {%- else %}
20
- {%- set ns.tools_system_message = '' %}
21
- {%- endif %}
22
- {%- if documents %}
23
- {%- for document in documents %}
24
- {%- set ns.documents_system_message = ns.documents_system_message + '\n' + (document | tojson) %}
25
- {%- endfor %}
26
- {%- set ns.documents_system_message = ns.documents_system_message + documents_system_message_suffix %}
27
- {%- else %}
28
- {%- set ns.documents_system_message = '' %}
29
- {%- endif %}
30
- {%- if messages[0].role == 'system' %}
31
- {%- if messages[0].content is string %}
32
- {%- set ns.system_message = messages[0].content %}
33
- {%- elif messages[0].content is iterable %}
34
- {%- for entry in messages[0].content %}
35
- {%- if entry.type== 'text' %}
36
- {%- if ns.system_message != '' %}
37
- {%- set ns.system_message = ns.system_message + '\n' %}
38
- {%- endif %}
39
- {%- set ns.system_message = ns.system_message + entry.text %}
40
- {%- endif %}
41
- {%- endfor %}
42
- {%- endif %}
43
- {%- if tools and documents %}
44
- {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message + '\n\n' + ns.documents_system_message %}
45
- {%- elif tools %}
46
- {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message %}
47
- {%- elif documents %}
48
- {%- set ns.system_message = ns.system_message + '\n\n' + ns.documents_system_message %}
49
- {%- endif %}
50
- {%- else %}
51
- {%- if tools and documents %}
52
- {%- set ns.system_message = ns.tools_system_message + '\n\n' + ns.documents_system_message %}
53
- {%- elif tools %}
54
- {%- set ns.system_message = ns.tools_system_message %}
55
- {%- elif documents %}
56
- {%- set ns.system_message = ns.documents_system_message %}
57
- {%- endif %}
58
- {%- endif %}
59
- {%- if ns.system_message %}
60
- {{- '<|start_of_role|>system<|end_of_role|>' + ns.system_message + '<|end_of_text|>\n' }}
61
- {%- else %}
62
- {{- '<|start_of_role|>system<|end_of_role|>' + ns.default_system_message + '<|end_of_text|>\n' }}
63
- {%- endif %}
64
- {%- for message in messages %}
65
- {%- set content = namespace(val='') %}
66
- {%- if message.content is string %}
67
- {%- set content.val = message.content %}
68
- {%- else %}
69
- {%- if message.content is iterable %}
70
- {%- for entry in message.content %}
71
- {%- if entry.type== 'text' %}
72
- {%- if content.val != '' %}
73
- {%- set content.val = content.val + '\n' %}
74
- {%- endif %}
75
- {%- set content.val = content.val + entry.text %}
76
- {%- endif %}
77
- {%- endfor %}
78
- {%- endif %}
79
- {%- endif %}
80
- {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) %}
81
- {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val + '<|end_of_text|>\n' }}
82
- {%- elif message.role == 'assistant' %}
83
- {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val }}
84
- {%- if message.tool_calls %}
85
- {%- for tool_call in message.tool_calls %}
86
- {%- if (loop.first and content.val) or (not loop.first) %}
87
- {{- '\n' }}
88
- {%- endif %}
89
- {%- if tool_call.function %}
90
- {%- set tool_call = tool_call.function %}
91
- {%- endif %}
92
- {{- '<tool_call>\n{"name": "' }}
93
- {{- tool_call.name }}
94
- {{- '", "arguments": ' }}
95
- {%- if tool_call.arguments is string %}
96
- {{- tool_call.arguments }}
97
- {%- else %}
98
- {{- tool_call.arguments | tojson }}
99
- {%- endif %}
100
- {{- '}\n</tool_call>' }}
101
- {%- endfor %}
102
- {%- endif %}
103
- {{- '<|end_of_text|>\n' }}
104
- {%- elif message.role == 'tool' %}
105
- {%- if loop.first or (messages[loop.index0 - 1].role != 'tool') %}
106
- {{- '<|start_of_role|>user<|end_of_role|>' }}
107
- {%- endif %}
108
- {{- '\n<tool_response>\n' }}
109
- {{- content.val }}
110
- {{- '\n</tool_response>' }}
111
- {%- if loop.last or (messages[loop.index0 + 1].role != 'tool') %}
112
- {{- '<|end_of_text|>\n' }}
113
- {%- endif %}
114
- {%- endif %}
115
- {%- endfor %}
116
- {%- if add_generation_prompt %}
117
- {{- '<|start_of_role|>assistant<|end_of_role|>' }}
118
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
granite-4.0-h-tiny/base/tokenizer/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
granite-4.0-h-tiny/base/tokenizer/tokenizer_config.json DELETED
@@ -1,516 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "backend": "tokenizers",
4
- "bos_token": "<|end_of_text|>",
5
- "clean_up_tokenization_spaces": false,
6
- "eos_token": "<|end_of_text|>",
7
- "errors": "replace",
8
- "extra_special_tokens": [
9
- "865331112869",
10
- "569765693871",
11
- "485177821815",
12
- "135441121756",
13
- "367459894796",
14
- "877482678543",
15
- "457919547633",
16
- "765474393376",
17
- "114848338811",
18
- "746285987371",
19
- "649291669397",
20
- "927914615679",
21
- "445925149649",
22
- "691587454538",
23
- "143777992227",
24
- "997981281989",
25
- "425949483533",
26
- "982993456429",
27
- "718726519731",
28
- "172599315861",
29
- "643489267333",
30
- "282322838685",
31
- "781653545886",
32
- "796415361892",
33
- "841991688488",
34
- "211411365397",
35
- "698218415444",
36
- "355977139358",
37
- "682564697312",
38
- "383837596997",
39
- "689362171782",
40
- "749966767285",
41
- "753159165157",
42
- "795693824762",
43
- "669689115557",
44
- "327491773134",
45
- "983569279932",
46
- "612128769512",
47
- "374327157578",
48
- "311632789559",
49
- "523918658846",
50
- "765981581453",
51
- "794825141891",
52
- "873898736873",
53
- "447445629421",
54
- "473822473819",
55
- "181439694557",
56
- "592538279337",
57
- "668134915514",
58
- "643692393748",
59
- "696651276628",
60
- "853859348234",
61
- "778466723723",
62
- "929826356991",
63
- "272362973463",
64
- "694235616268",
65
- "281673864127",
66
- "479676316326",
67
- "646979124677",
68
- "922327493433",
69
- "883685933161",
70
- "264259917554",
71
- "836746273134",
72
- "658481324922",
73
- "481884157827",
74
- "587787496812",
75
- "579184949249",
76
- "912193598348",
77
- "529679678956",
78
- "795838284624",
79
- "159337222655",
80
- "173781362446",
81
- "773687856563",
82
- "535787224917",
83
- "351885857332",
84
- "578827344666",
85
- "198462689911",
86
- "722618266242",
87
- "952872416512",
88
- "517778845323",
89
- "749665846687",
90
- "661436365453",
91
- "259666844669",
92
- "242851284913",
93
- "514532995959",
94
- "161588262349",
95
- "742765629356",
96
- "225164373623",
97
- "676539973863",
98
- "826214551218",
99
- "182345464792",
100
- "232776999554",
101
- "337326533813",
102
- "676676697292",
103
- "929185622831",
104
- "545512344383",
105
- "499444466686",
106
- "314697386682",
107
- "517379856925",
108
- "379557332953",
109
- "614797267726",
110
- "429781429464",
111
- "922466849763",
112
- "721737645236",
113
- "479227349997",
114
- "136931728327",
115
- "259533577263",
116
- "488538864842",
117
- "937495658852",
118
- "489991411364",
119
- "499148455254",
120
- "441373944925",
121
- "899151413682",
122
- "467893531755",
123
- "527117488925",
124
- "928335588653",
125
- "374439448821",
126
- "879425227932",
127
- "867678158885",
128
- "399749397872",
129
- "129693547287",
130
- "689285841825",
131
- "771619544974",
132
- "724883568652",
133
- "516968424863",
134
- "733737988257",
135
- "852347289392",
136
- "296953381169",
137
- "377273562477",
138
- "262296912232",
139
- "547149832394",
140
- "298464134954",
141
- "216667245274",
142
- "843998562287",
143
- "572154333646",
144
- "124589118494",
145
- "841824384614",
146
- "232896526252",
147
- "295448593321",
148
- "123741461297",
149
- "653573457168",
150
- "196735786156",
151
- "377338713663",
152
- "964342468552",
153
- "586855179568",
154
- "484773717614",
155
- "894885246797",
156
- "677896358599",
157
- "848845611563",
158
- "851852651677",
159
- "398549545767",
160
- "454244839926",
161
- "799364566435",
162
- "967114116556",
163
- "817378986438",
164
- "233795848681",
165
- "824387273757",
166
- "916198946615",
167
- "563117729724",
168
- "951794811935",
169
- "374598961236",
170
- "922867396683",
171
- "765737843639",
172
- "175469284871",
173
- "231853711778",
174
- "662426712668",
175
- "711412347158",
176
- "753466987363",
177
- "513361312532",
178
- "712992815957",
179
- "971621888444",
180
- "829235161526",
181
- "585544633356",
182
- "582471228164",
183
- "678666359123",
184
- "557533689478",
185
- "632962475133",
186
- "484489193824",
187
- "489562189822",
188
- "589547936288",
189
- "363214487524",
190
- "244885399387",
191
- "431751228368",
192
- "433581868192",
193
- "486391569221",
194
- "185438575221",
195
- "126574388585",
196
- "741757479784",
197
- "529854679937",
198
- "996116119839",
199
- "616248973917",
200
- "763531783491",
201
- "955456118295",
202
- "364196983365",
203
- "195792996468",
204
- "151859598873",
205
- "399223169721",
206
- "938488813964",
207
- "961981959227",
208
- "183368827562",
209
- "533417736566",
210
- "786391632558",
211
- "665661658354",
212
- "693281533643",
213
- "475794684356",
214
- "652154162978",
215
- "753233719644",
216
- "668514843129",
217
- "819162623892",
218
- "941169431859",
219
- "877385381798",
220
- "752644929761",
221
- "881136466196",
222
- "275597777299",
223
- "731681792655",
224
- "961133895172",
225
- "864718285734",
226
- "963852916563",
227
- "319584985416",
228
- "563365646341",
229
- "811371928234",
230
- "837131396371",
231
- "267514771964",
232
- "944513428457",
233
- "117298239631",
234
- "158142752582",
235
- "252867443568",
236
- "839269684865",
237
- "612788593128",
238
- "145669731981",
239
- "121557291859",
240
- "245416776926",
241
- "799417897197",
242
- "997958836435",
243
- "892336777248",
244
- "158929292238",
245
- "581976444672",
246
- "897784492783",
247
- "492373714791",
248
- "512659818733",
249
- "881112998642",
250
- "619454958782",
251
- "431149748713",
252
- "624221476921",
253
- "125866399464",
254
- "339882449689",
255
- "186198784585",
256
- "943193294691",
257
- "955668961269",
258
- "232787996724",
259
- "215671314196",
260
- "286173241916",
261
- "745977673725",
262
- "556976448182",
263
- "599961512792",
264
- "766294538337",
265
- "934912591213",
266
- "295118729589",
267
- "529455466433",
268
- "196119929397",
269
- "379571934299",
270
- "251789649997",
271
- "564544131355",
272
- "244371196654",
273
- "384598329253",
274
- "887753195844",
275
- "364947325679",
276
- "655517954651",
277
- "673948786567",
278
- "857231548835",
279
- "816115936673",
280
- "644234165531",
281
- "182782912224",
282
- "234316622259",
283
- "421369185549",
284
- "434632855397",
285
- "921889371893",
286
- "415956914763",
287
- "598916996413",
288
- "773671349113",
289
- "952465217972",
290
- "117657531962",
291
- "729825168745",
292
- "691315125346",
293
- "768461952319",
294
- "664847713559",
295
- "953267689786",
296
- "886464195129",
297
- "824488329416",
298
- "837873762491",
299
- "532833541879",
300
- "669183782449",
301
- "941976537588",
302
- "739394546916",
303
- "267954879268",
304
- "637551427887",
305
- "217756494954",
306
- "524444658383",
307
- "117783274348",
308
- "138218735276",
309
- "814611949491",
310
- "711641973413",
311
- "499156317423",
312
- "515856611931",
313
- "454164859837",
314
- "345271433112",
315
- "462294118988",
316
- "511785788222",
317
- "497294727353",
318
- "866519986723",
319
- "334513529294",
320
- "549946382131",
321
- "284445431422",
322
- "396521188476",
323
- "421435255895",
324
- "133373659361",
325
- "322683334381",
326
- "228358422847",
327
- "291762694874",
328
- "143182978129",
329
- "511923256573",
330
- "327158398268",
331
- "879764613759",
332
- "564395222747",
333
- "451161679736",
334
- "538631466654",
335
- "221762325616",
336
- "218391991184",
337
- "322589379462",
338
- "876537814263",
339
- "152676556624",
340
- "332522971941",
341
- "884354318946",
342
- "513349618943",
343
- "116639746413",
344
- "635185846287",
345
- "993832498489",
346
- "813981174797",
347
- "438745114173",
348
- "983493951323",
349
- "724492262421",
350
- "622553389126",
351
- "889965243135",
352
- "364492359246",
353
- "154962668224",
354
- "179564995814",
355
- "418412875665",
356
- "718951851413",
357
- "699446724178",
358
- "624266421831",
359
- "815458725125",
360
- "455423278865",
361
- "393741199486",
362
- "328552864359",
363
- "211662639865",
364
- "218784516525",
365
- "762486672996",
366
- "142799718159",
367
- "858146415154",
368
- "767858144912",
369
- "571317457151",
370
- "635127952696",
371
- "116427191984",
372
- "268921994538",
373
- "523937669294",
374
- "165429152138",
375
- "739246183345",
376
- "591464355756",
377
- "212985874612",
378
- "191887635211",
379
- "967214577653",
380
- "119342152414",
381
- "946444632795",
382
- "618423867817",
383
- "228565148417",
384
- "729116422489",
385
- "527874729936",
386
- "739784153482",
387
- "387763951128",
388
- "331369926711",
389
- "562716493614",
390
- "739667844957",
391
- "562389434565",
392
- "256497188281",
393
- "859927364588",
394
- "417668946583",
395
- "357621613582",
396
- "438435178228",
397
- "485692541169",
398
- "825815739116",
399
- "342221452223",
400
- "697747991249",
401
- "716763689965",
402
- "141499982867",
403
- "818479319499",
404
- "336813343298",
405
- "594688742928",
406
- "472129283475",
407
- "514354144759",
408
- "349249721685",
409
- "546276298359",
410
- "353755529131",
411
- "315534574435",
412
- "523723475786",
413
- "215826764872",
414
- "367968398551",
415
- "569853653352",
416
- "389715484387",
417
- "293847485454",
418
- "714738141818",
419
- "178478368922",
420
- "581493616981",
421
- "589439538674",
422
- "846657726193",
423
- "722339992679",
424
- "138154781148",
425
- "757785319772",
426
- "492516914298",
427
- "919181521716",
428
- "985781138935",
429
- "476969195485",
430
- "313145133463",
431
- "758963111966",
432
- "147541537162",
433
- "557163366873",
434
- "144373897488",
435
- "522515164754",
436
- "724964923582",
437
- "284776712475",
438
- "375429755114",
439
- "181233596124",
440
- "948585673431",
441
- "243165586174",
442
- "396847976144",
443
- "997724962668",
444
- "558837194455",
445
- "163165456396",
446
- "378749551722",
447
- "161238482259",
448
- "754978243758",
449
- "195388849133",
450
- "229775525672",
451
- "262437452884",
452
- "441377892146",
453
- "451885565366",
454
- "981277526855",
455
- "762495822823",
456
- "368763327262",
457
- "757422791351",
458
- "636324136426",
459
- "214193645583",
460
- "412843856172",
461
- "179386156569",
462
- "756916173536",
463
- "892697125149",
464
- "625334487352",
465
- "941861857715",
466
- "887417525236",
467
- "649516938598",
468
- "717628619782",
469
- "438124184139",
470
- "547563892268",
471
- "856317483891",
472
- "313313831273",
473
- "371496153876",
474
- "587541149322",
475
- "265847332563",
476
- "449549215429",
477
- "163497196769",
478
- "861342291298",
479
- "268433315926",
480
- "774679513717",
481
- "851254219729",
482
- "583527834464",
483
- "488496781997",
484
- "556814553861",
485
- "482829231639",
486
- "618878266619",
487
- "147444452794",
488
- "949235426629",
489
- "357299947518",
490
- "175528632226",
491
- "645527857972",
492
- "186872457894",
493
- "552738847828",
494
- "626748382482",
495
- "921894985642",
496
- "943878645871",
497
- "859289776479",
498
- "614583493135",
499
- "933775286797",
500
- "332234613346",
501
- "325196781219",
502
- "142526557681",
503
- "356722692178",
504
- "449318681694",
505
- "687284547244",
506
- "947262995132",
507
- "893974619684",
508
- "797238311233"
509
- ],
510
- "is_local": false,
511
- "model_max_length": 1000000000000000019884624838656,
512
- "pad_token": "<|pad|>",
513
- "padding_side": "left",
514
- "tokenizer_class": "GPT2Tokenizer",
515
- "unk_token": "<|unk|>"
516
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
granite-4.0-h-tiny/base/train.log DELETED
@@ -1,3 +0,0 @@
1
- 2026-03-18 08:23:07,141 [INFO] new_opacus_codex.train_steps: epoch=1 step=10 loss=3.7489
2
- 2026-03-18 08:23:48,548 [INFO] new_opacus_codex.train_steps: epoch=1 step=20 loss=3.2296
3
- 2026-03-18 08:24:29,243 [INFO] new_opacus_codex.train_steps: epoch=1 step=30 loss=2.0376