Hugging Face's logo

alwaysgood
/
qwen3-st2

Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
unsloth
sft
trl
text-generation-inference
Model card Files
xet
 Community
alwaysgood commited on
Commit
cf093ce
·
verified ·
1 Parent(s): 258b864

Upload final model from parallel-cpt-qwen3-st2

Browse files
Files changed (24) hide show
  1. .gitattributes +3 -0
  2. README.md +59 -0
  3. all_results.json +12 -0
  4. checkpoint-90/config.json +74 -0
  5. checkpoint-90/generation_config.json +9 -0
  6. checkpoint-90/model.safetensors +3 -0
  7. checkpoint-90/optimizer.pt +3 -0
  8. checkpoint-90/rng_state.pth +3 -0
  9. checkpoint-90/scheduler.pt +3 -0
  10. checkpoint-90/tokenizer.json +3 -0
  11. checkpoint-90/tokenizer_config.json +15 -0
  12. checkpoint-90/trainer_state.json +105 -0
  13. checkpoint-90/training_args.bin +3 -0
  14. config.json +74 -0
  15. eval_results.json +7 -0
  16. generation_config.json +9 -0
  17. model.safetensors +3 -0
  18. tokenizer.json +3 -0
  19. tokenizer/tokenizer.json +3 -0
  20. tokenizer/tokenizer_config.json +15 -0
  21. tokenizer_config.json +15 -0
  22. train_results.json +8 -0
  23. trainer_state.json +114 -0
  24. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ 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
+ checkpoint-90/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: alwaysgood/qwen3-st1
3
+ library_name: transformers
4
+ model_name: checkpoints
5
+ tags:
6
+ - generated_from_trainer
7
+ - unsloth
8
+ - sft
9
+ - trl
10
+ licence: license
11
+ ---
12
+
13
+ # Model Card for checkpoints
14
+
15
+ This model is a fine-tuned version of [alwaysgood/qwen3-st1](https://huggingface.co/alwaysgood/qwen3-st1).
16
+ It has been trained using [TRL](https://github.com/huggingface/trl).
17
+
18
+ ## Quick start
19
+
20
+ ```python
21
+ from transformers import pipeline
22
+
23
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
24
+ generator = pipeline("text-generation", model="None", device="cuda")
25
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
26
+ print(output["generated_text"])
27
+ ```
28
+
29
+ ## Training procedure
30
+
31
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/hiloong/parallel-cpt/runs/7ibqec5k)
32
+
33
+
34
+ This model was trained with SFT.
35
+
36
+ ### Framework versions
37
+
38
+ - TRL: 0.24.0
39
+ - Transformers: 5.5.4
40
+ - Pytorch: 2.9.0+cu128
41
+ - Datasets: 4.3.0
42
+ - Tokenizers: 0.22.2
43
+
44
+ ## Citations
45
+
46
+
47
+
48
+ Cite TRL as:
49
+
50
+ ```bibtex
51
+ @misc{vonwerra2022trl,
52
+ title = {{TRL: Transformer Reinforcement Learning}},
53
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
54
+ year = 2020,
55
+ journal = {GitHub repository},
56
+ publisher = {GitHub},
57
+ howpublished = {\url{https://github.com/huggingface/trl}}
58
+ }
59
+ ```
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 1.7960469722747803,
4
+ "eval_runtime": 1.4557,
5
+ "eval_samples_per_second": 49.461,
6
+ "eval_steps_per_second": 6.183,
7
+ "total_flos": 1.6013083311596544e+16,
8
+ "train_loss": 1.9456637912326389,
9
+ "train_runtime": 195.6651,
10
+ "train_samples_per_second": 18.21,
11
+ "train_steps_per_second": 0.46
12
+ }
checkpoint-90/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151643,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2560,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 9728,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention"
52
+ ],
53
+ "max_position_embeddings": 32768,
54
+ "max_window_layers": 36,
55
+ "model_name": "alwaysgood/qwen3-st1",
56
+ "model_type": "qwen3",
57
+ "num_attention_heads": 32,
58
+ "num_hidden_layers": 36,
59
+ "num_key_value_heads": 8,
60
+ "pad_token_id": 151669,
61
+ "rms_norm_eps": 1e-06,
62
+ "rope_parameters": {
63
+ "rope_theta": 1000000,
64
+ "rope_type": "default"
65
+ },
66
+ "sliding_window": null,
67
+ "tie_word_embeddings": true,
68
+ "transformers_version": "5.5.4",
69
+ "unsloth_fixed": true,
70
+ "unsloth_version": "2026.4.6",
71
+ "use_cache": false,
72
+ "use_sliding_window": false,
73
+ "vocab_size": 151936
74
+ }
checkpoint-90/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token_id": [
3
+ 151643
4
+ ],
5
+ "max_length": 32768,
6
+ "max_new_tokens": 2048,
7
+ "pad_token_id": 151669,
8
+ "transformers_version": "5.5.4"
9
+ }
checkpoint-90/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:483b5c930ea9fd8e915605da837bb6dc4655d36fa9129a76c5bc76d4771b425d
3
+ size 8044982080
checkpoint-90/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01705231f9d2f07079390aa9eeafd3486d6257e2f1a05308d21a1fbccce651f5
3
+ size 16090219945
checkpoint-90/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
3
+ size 14645
checkpoint-90/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4da37e1d2639c6a3c48eabc833153fc8f9bf81ee46a2bc40f3b4e879988db4
3
+ size 1465
checkpoint-90/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45c4ffda6666cf6d75d0b1f961f25964e2a52a62e78aaecb2f458e9ba9824112
3
+ size 11422840
checkpoint-90/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "is_local": false,
9
+ "model_max_length": 32768,
10
+ "pad_token": "<|PAD_TOKEN|>",
11
+ "padding_side": "right",
12
+ "split_special_tokens": false,
13
+ "tokenizer_class": "Qwen2Tokenizer",
14
+ "unk_token": null
15
+ }
checkpoint-90/trainer_state.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 90,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.11204481792717087,
14
+ "grad_norm": 15.3125,
15
+ "learning_rate": 1e-05,
16
+ "loss": 2.2154748916625975,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.22408963585434175,
21
+ "grad_norm": 7.40625,
22
+ "learning_rate": 9.628619846344453e-06,
23
+ "loss": 1.983123207092285,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.33613445378151263,
28
+ "grad_norm": 7.375,
29
+ "learning_rate": 8.569648672789496e-06,
30
+ "loss": 1.9408803939819337,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.4481792717086835,
35
+ "grad_norm": 7.875,
36
+ "learning_rate": 6.980398830195785e-06,
37
+ "loss": 1.9281248092651366,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.5602240896358543,
42
+ "grad_norm": 5.21875,
43
+ "learning_rate": 5.096956658859122e-06,
44
+ "loss": 1.8314035415649415,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.6722689075630253,
49
+ "grad_norm": 6.0,
50
+ "learning_rate": 3.1991113759764493e-06,
51
+ "loss": 1.8851320266723632,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.7843137254901961,
56
+ "grad_norm": 5.28125,
57
+ "learning_rate": 1.5687918106563326e-06,
58
+ "loss": 1.8772430419921875,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.896358543417367,
63
+ "grad_norm": 5.25,
64
+ "learning_rate": 4.481852951692672e-07,
65
+ "loss": 1.8912254333496095,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 1.0,
70
+ "grad_norm": 28.25,
71
+ "learning_rate": 3.760237478849793e-09,
72
+ "loss": 1.9583667755126952,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 1.0,
77
+ "eval_loss": 1.795481562614441,
78
+ "eval_runtime": 2.3084,
79
+ "eval_samples_per_second": 31.191,
80
+ "eval_steps_per_second": 3.899,
81
+ "step": 90
82
+ }
83
+ ],
84
+ "logging_steps": 10,
85
+ "max_steps": 90,
86
+ "num_input_tokens_seen": 0,
87
+ "num_train_epochs": 1,
88
+ "save_steps": 200,
89
+ "stateful_callbacks": {
90
+ "TrainerControl": {
91
+ "args": {
92
+ "should_epoch_stop": false,
93
+ "should_evaluate": false,
94
+ "should_log": false,
95
+ "should_save": true,
96
+ "should_training_stop": true
97
+ },
98
+ "attributes": {}
99
+ }
100
+ },
101
+ "total_flos": 1.6013083311596544e+16,
102
+ "train_batch_size": 10,
103
+ "trial_name": null,
104
+ "trial_params": null
105
+ }
checkpoint-90/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:520a7bea9f9d3bfc63ec041133a829212380f01fdc32add517900671fb2f31c2
3
+ size 5777
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151643,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2560,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 9728,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention"
52
+ ],
53
+ "max_position_embeddings": 32768,
54
+ "max_window_layers": 36,
55
+ "model_name": "alwaysgood/qwen3-st1",
56
+ "model_type": "qwen3",
57
+ "num_attention_heads": 32,
58
+ "num_hidden_layers": 36,
59
+ "num_key_value_heads": 8,
60
+ "pad_token_id": 151669,
61
+ "rms_norm_eps": 1e-06,
62
+ "rope_parameters": {
63
+ "rope_theta": 1000000,
64
+ "rope_type": "default"
65
+ },
66
+ "sliding_window": null,
67
+ "tie_word_embeddings": true,
68
+ "transformers_version": "5.5.4",
69
+ "unsloth_fixed": true,
70
+ "unsloth_version": "2026.4.6",
71
+ "use_cache": false,
72
+ "use_sliding_window": false,
73
+ "vocab_size": 151936
74
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 1.7960469722747803,
4
+ "eval_runtime": 1.4557,
5
+ "eval_samples_per_second": 49.461,
6
+ "eval_steps_per_second": 6.183
7
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token_id": [
3
+ 151643
4
+ ],
5
+ "max_length": 32768,
6
+ "max_new_tokens": 2048,
7
+ "pad_token_id": 151669,
8
+ "transformers_version": "5.5.4"
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:483b5c930ea9fd8e915605da837bb6dc4655d36fa9129a76c5bc76d4771b425d
3
+ size 8044982080
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45c4ffda6666cf6d75d0b1f961f25964e2a52a62e78aaecb2f458e9ba9824112
3
+ size 11422840
tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45c4ffda6666cf6d75d0b1f961f25964e2a52a62e78aaecb2f458e9ba9824112
3
+ size 11422840
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "is_local": false,
9
+ "model_max_length": 32768,
10
+ "pad_token": "<|PAD_TOKEN|>",
11
+ "padding_side": "left",
12
+ "split_special_tokens": false,
13
+ "tokenizer_class": "Qwen2Tokenizer",
14
+ "unk_token": null
15
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "is_local": false,
9
+ "model_max_length": 32768,
10
+ "pad_token": "<|PAD_TOKEN|>",
11
+ "padding_side": "left",
12
+ "split_special_tokens": false,
13
+ "tokenizer_class": "Qwen2Tokenizer",
14
+ "unk_token": null
15
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 1.6013083311596544e+16,
4
+ "train_loss": 1.9456637912326389,
5
+ "train_runtime": 195.6651,
6
+ "train_samples_per_second": 18.21,
7
+ "train_steps_per_second": 0.46
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 90,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.11204481792717087,
14
+ "grad_norm": 15.3125,
15
+ "learning_rate": 1e-05,
16
+ "loss": 2.2154748916625975,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.22408963585434175,
21
+ "grad_norm": 7.40625,
22
+ "learning_rate": 9.628619846344453e-06,
23
+ "loss": 1.983123207092285,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.33613445378151263,
28
+ "grad_norm": 7.375,
29
+ "learning_rate": 8.569648672789496e-06,
30
+ "loss": 1.9408803939819337,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.4481792717086835,
35
+ "grad_norm": 7.875,
36
+ "learning_rate": 6.980398830195785e-06,
37
+ "loss": 1.9281248092651366,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.5602240896358543,
42
+ "grad_norm": 5.21875,
43
+ "learning_rate": 5.096956658859122e-06,
44
+ "loss": 1.8314035415649415,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.6722689075630253,
49
+ "grad_norm": 6.0,
50
+ "learning_rate": 3.1991113759764493e-06,
51
+ "loss": 1.8851320266723632,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.7843137254901961,
56
+ "grad_norm": 5.28125,
57
+ "learning_rate": 1.5687918106563326e-06,
58
+ "loss": 1.8772430419921875,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.896358543417367,
63
+ "grad_norm": 5.25,
64
+ "learning_rate": 4.481852951692672e-07,
65
+ "loss": 1.8912254333496095,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 1.0,
70
+ "grad_norm": 28.25,
71
+ "learning_rate": 3.760237478849793e-09,
72
+ "loss": 1.9583667755126952,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 1.0,
77
+ "eval_loss": 1.795481562614441,
78
+ "eval_runtime": 2.3084,
79
+ "eval_samples_per_second": 31.191,
80
+ "eval_steps_per_second": 3.899,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 1.0,
85
+ "step": 90,
86
+ "total_flos": 1.6013083311596544e+16,
87
+ "train_loss": 1.9456637912326389,
88
+ "train_runtime": 195.6651,
89
+ "train_samples_per_second": 18.21,
90
+ "train_steps_per_second": 0.46
91
+ }
92
+ ],
93
+ "logging_steps": 10,
94
+ "max_steps": 90,
95
+ "num_input_tokens_seen": 0,
96
+ "num_train_epochs": 1,
97
+ "save_steps": 200,
98
+ "stateful_callbacks": {
99
+ "TrainerControl": {
100
+ "args": {
101
+ "should_epoch_stop": false,
102
+ "should_evaluate": false,
103
+ "should_log": false,
104
+ "should_save": true,
105
+ "should_training_stop": true
106
+ },
107
+ "attributes": {}
108
+ }
109
+ },
110
+ "total_flos": 1.6013083311596544e+16,
111
+ "train_batch_size": 10,
112
+ "trial_name": null,
113
+ "trial_params": null
114
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:520a7bea9f9d3bfc63ec041133a829212380f01fdc32add517900671fb2f31c2
3
+ size 5777