Hugging Face's logo

harsha070
/
expfinal-phi-mbpp-s42-lambda-0p0

Text Generation
Transformers
Safetensors
phi3
Generated from Trainer
trl
grpo
conversational
custom_code
text-generation-inference
Model card Files
xet
 Community
harsha070 commited on
Commit
dd458bd
·
verified ·
1 Parent(s): 3902b98

Training in progress, step 10, checkpoint

Browse files
Files changed (8) hide show
  1. last-checkpoint/chat_template.jinja +8 -0
  2. last-checkpoint/config.json +140 -0
  3. last-checkpoint/generation_config.json +11 -0
  4. last-checkpoint/model.safetensors +3 -0
  5. last-checkpoint/tokenizer.json +0 -0
  6. last-checkpoint/tokenizer_config.json +16 -0
  7. last-checkpoint/trainer_state.json +62 -0
  8. last-checkpoint/training_args.bin +3 -0
last-checkpoint/chat_template.jinja ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>
2
+ ' + message['content'] + '<|end|>
3
+ '}}{% elif message['role'] == 'user' %}{{'<|user|>
4
+ ' + message['content'] + '<|end|>
5
+ '}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>
6
+ ' + message['content'] + '<|end|>
7
+ '}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
8
+ ' }}{% else %}{{ eos_token }}{% endif %}
last-checkpoint/config.json ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Phi3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "dtype": "bfloat16",
13
+ "embd_pdrop": 0.0,
14
+ "eos_token_id": 32000,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "model_type": "phi3",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 32,
24
+ "original_max_position_embeddings": 4096,
25
+ "pad_token_id": 32000,
26
+ "resid_pdrop": 0.0,
27
+ "rms_norm_eps": 1e-05,
28
+ "rope_parameters": {
29
+ "long_factor": [
30
+ 1.0800000429153442,
31
+ 1.1100000143051147,
32
+ 1.1399999856948853,
33
+ 1.340000033378601,
34
+ 1.5899999141693115,
35
+ 1.600000023841858,
36
+ 1.6200000047683716,
37
+ 2.620000123977661,
38
+ 3.2300000190734863,
39
+ 3.2300000190734863,
40
+ 4.789999961853027,
41
+ 7.400000095367432,
42
+ 7.700000286102295,
43
+ 9.09000015258789,
44
+ 12.199999809265137,
45
+ 17.670000076293945,
46
+ 24.46000099182129,
47
+ 28.57000160217285,
48
+ 30.420001983642578,
49
+ 30.840002059936523,
50
+ 32.590003967285156,
51
+ 32.93000411987305,
52
+ 42.320003509521484,
53
+ 44.96000289916992,
54
+ 50.340003967285156,
55
+ 50.45000457763672,
56
+ 57.55000305175781,
57
+ 57.93000411987305,
58
+ 58.21000289916992,
59
+ 60.1400032043457,
60
+ 62.61000442504883,
61
+ 62.62000274658203,
62
+ 62.71000289916992,
63
+ 63.1400032043457,
64
+ 63.1400032043457,
65
+ 63.77000427246094,
66
+ 63.93000411987305,
67
+ 63.96000289916992,
68
+ 63.970001220703125,
69
+ 64.02999877929688,
70
+ 64.06999969482422,
71
+ 64.08000183105469,
72
+ 64.12000274658203,
73
+ 64.41000366210938,
74
+ 64.4800033569336,
75
+ 64.51000213623047,
76
+ 64.52999877929688,
77
+ 64.83999633789062
78
+ ],
79
+ "original_max_position_embeddings": 4096,
80
+ "partial_rotary_factor": 1.0,
81
+ "rope_theta": 10000.0,
82
+ "rope_type": "longrope",
83
+ "short_factor": [
84
+ 1.0,
85
+ 1.0199999809265137,
86
+ 1.0299999713897705,
87
+ 1.0299999713897705,
88
+ 1.0499999523162842,
89
+ 1.0499999523162842,
90
+ 1.0499999523162842,
91
+ 1.0499999523162842,
92
+ 1.0499999523162842,
93
+ 1.0699999332427979,
94
+ 1.0999999046325684,
95
+ 1.1099998950958252,
96
+ 1.1599998474121094,
97
+ 1.1599998474121094,
98
+ 1.1699998378753662,
99
+ 1.2899998426437378,
100
+ 1.339999794960022,
101
+ 1.679999828338623,
102
+ 1.7899998426437378,
103
+ 1.8199998140335083,
104
+ 1.8499997854232788,
105
+ 1.8799997568130493,
106
+ 1.9099997282028198,
107
+ 1.9399996995925903,
108
+ 1.9899996519088745,
109
+ 2.0199997425079346,
110
+ 2.0199997425079346,
111
+ 2.0199997425079346,
112
+ 2.0199997425079346,
113
+ 2.0199997425079346,
114
+ 2.0199997425079346,
115
+ 2.0299997329711914,
116
+ 2.0299997329711914,
117
+ 2.0299997329711914,
118
+ 2.0299997329711914,
119
+ 2.0299997329711914,
120
+ 2.0299997329711914,
121
+ 2.0299997329711914,
122
+ 2.0299997329711914,
123
+ 2.0299997329711914,
124
+ 2.0799996852874756,
125
+ 2.0899996757507324,
126
+ 2.189999580383301,
127
+ 2.2199995517730713,
128
+ 2.5899994373321533,
129
+ 2.729999542236328,
130
+ 2.749999523162842,
131
+ 2.8399994373321533
132
+ ],
133
+ "type": "longrope"
134
+ },
135
+ "sliding_window": 262144,
136
+ "tie_word_embeddings": false,
137
+ "transformers_version": "5.8.0",
138
+ "use_cache": false,
139
+ "vocab_size": 32064
140
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 32007,
6
+ 32001,
7
+ 32000
8
+ ],
9
+ "pad_token_id": 32000,
10
+ "transformers_version": "5.8.0"
11
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89ccd0076c711222ee1fb3b174ad3d323b45b18851b2980f1e50c70d928779c9
3
+ size 7642181896
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<|endoftext|>",
6
+ "is_local": false,
7
+ "legacy": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 131072,
10
+ "pad_token": "<|endoftext|>",
11
+ "padding_side": "left",
12
+ "sp_model_kwargs": {},
13
+ "tokenizer_class": "TokenizersBackend",
14
+ "unk_token": "<unk>",
15
+ "use_default_system_prompt": false
16
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.06666666666666667,
6
+ "eval_steps": 500,
7
+ "global_step": 10,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "clip_ratio/high_max": 0.0,
14
+ "clip_ratio/high_mean": 0.0,
15
+ "clip_ratio/low_mean": 0.0,
16
+ "clip_ratio/low_min": 0.0,
17
+ "clip_ratio/region_mean": 0.0,
18
+ "completions/clipped_ratio": 0.1125,
19
+ "completions/max_length": 454.4,
20
+ "completions/max_terminated_length": 419.3,
21
+ "completions/mean_length": 344.7875,
22
+ "completions/mean_terminated_length": 326.5529846191406,
23
+ "completions/min_length": 239.3,
24
+ "completions/min_terminated_length": 239.3,
25
+ "entropy": 0.23321253526955843,
26
+ "epoch": 0.06666666666666667,
27
+ "frac_reward_zero_std": 0.55,
28
+ "grad_norm": 0.96875,
29
+ "kl": 0.02590957849060942,
30
+ "learning_rate": 9.357142857142859e-06,
31
+ "loss": -0.009455035626888274,
32
+ "num_tokens": 42791.0,
33
+ "reward": 0.825,
34
+ "reward_std": 0.2794355183839798,
35
+ "rewards/JointRewardFunction/mean": 0.825,
36
+ "rewards/JointRewardFunction/std": 0.2794355243444443,
37
+ "step": 10,
38
+ "step_time": 16.641905103900353
39
+ }
40
+ ],
41
+ "logging_steps": 10,
42
+ "max_steps": 140,
43
+ "num_input_tokens_seen": 42791,
44
+ "num_train_epochs": 1,
45
+ "save_steps": 10,
46
+ "stateful_callbacks": {
47
+ "TrainerControl": {
48
+ "args": {
49
+ "should_epoch_stop": false,
50
+ "should_evaluate": false,
51
+ "should_log": false,
52
+ "should_save": true,
53
+ "should_training_stop": false
54
+ },
55
+ "attributes": {}
56
+ }
57
+ },
58
+ "total_flos": 0.0,
59
+ "train_batch_size": 1,
60
+ "trial_name": null,
61
+ "trial_params": null
62
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f41b31d4ea45f8f956c91084507520e50a808172be0ee21f4d074399d03c903
3
+ size 7249