Add files using upload-large-folder tool
Browse files- DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3080/tokenizer_config.json +31 -0
- DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3080/trainer_state.json +732 -0
- DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3465/README.md +209 -0
- DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3465/adapter_config.json +46 -0
- DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3465/chat_template.jinja +154 -0
- DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3465/tokenizer_config.json +31 -0
- DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3465/trainer_state.json +823 -0
- DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-385/README.md +209 -0
- DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-385/adapter_config.json +46 -0
- DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-385/chat_template.jinja +154 -0
- DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-385/tokenizer_config.json +31 -0
- DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-385/trainer_state.json +115 -0
- DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3850/README.md +209 -0
- DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3850/adapter_config.json +46 -0
DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3080/tokenizer_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|endoftext|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"model_max_length": 262144,
|
| 14 |
+
"model_specific_special_tokens": {
|
| 15 |
+
"audio_bos_token": "<|audio_start|>",
|
| 16 |
+
"audio_eos_token": "<|audio_end|>",
|
| 17 |
+
"audio_token": "<|audio_pad|>",
|
| 18 |
+
"image_token": "<|image_pad|>",
|
| 19 |
+
"video_token": "<|video_pad|>",
|
| 20 |
+
"vision_bos_token": "<|vision_start|>",
|
| 21 |
+
"vision_eos_token": "<|vision_end|>"
|
| 22 |
+
},
|
| 23 |
+
"pad_token": "<|endoftext|>",
|
| 24 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 25 |
+
"split_special_tokens": false,
|
| 26 |
+
"tokenizer_class": "TokenizersBackend",
|
| 27 |
+
"unk_token": null,
|
| 28 |
+
"video_token": "<|video_pad|>",
|
| 29 |
+
"vision_bos_token": "<|vision_start|>",
|
| 30 |
+
"vision_eos_token": "<|vision_end|>"
|
| 31 |
+
}
|
DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3080/trainer_state.json
ADDED
|
@@ -0,0 +1,732 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3080,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.7529579949378968,
|
| 14 |
+
"epoch": 0.12987012987012986,
|
| 15 |
+
"grad_norm": 1.0845375061035156,
|
| 16 |
+
"learning_rate": 3.759565870277177e-05,
|
| 17 |
+
"loss": 1.6464532470703126,
|
| 18 |
+
"mean_token_accuracy": 0.6610959130525589,
|
| 19 |
+
"num_tokens": 127115.0,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 0.8384856134653091,
|
| 24 |
+
"epoch": 0.2597402597402597,
|
| 25 |
+
"grad_norm": 0.787804126739502,
|
| 26 |
+
"learning_rate": 7.595857574641644e-05,
|
| 27 |
+
"loss": 0.7860373687744141,
|
| 28 |
+
"mean_token_accuracy": 0.7873306655883789,
|
| 29 |
+
"num_tokens": 251796.0,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 0.7570279932022095,
|
| 34 |
+
"epoch": 0.38961038961038963,
|
| 35 |
+
"grad_norm": 0.8686555624008179,
|
| 36 |
+
"learning_rate": 0.00011432149279006112,
|
| 37 |
+
"loss": 0.6997585296630859,
|
| 38 |
+
"mean_token_accuracy": 0.8050823694467545,
|
| 39 |
+
"num_tokens": 366505.0,
|
| 40 |
+
"step": 150
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.7074448710680008,
|
| 44 |
+
"epoch": 0.5194805194805194,
|
| 45 |
+
"grad_norm": 0.641474723815918,
|
| 46 |
+
"learning_rate": 0.00015268440983370578,
|
| 47 |
+
"loss": 0.6549726104736329,
|
| 48 |
+
"mean_token_accuracy": 0.812009590268135,
|
| 49 |
+
"num_tokens": 493150.0,
|
| 50 |
+
"step": 200
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.7119272118806839,
|
| 54 |
+
"epoch": 0.6493506493506493,
|
| 55 |
+
"grad_norm": 0.6778020858764648,
|
| 56 |
+
"learning_rate": 0.00019104732687735045,
|
| 57 |
+
"loss": 0.6522830963134766,
|
| 58 |
+
"mean_token_accuracy": 0.8144695377349853,
|
| 59 |
+
"num_tokens": 607197.0,
|
| 60 |
+
"step": 250
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.6957281070947647,
|
| 64 |
+
"epoch": 0.7792207792207793,
|
| 65 |
+
"grad_norm": 0.5819384455680847,
|
| 66 |
+
"learning_rate": 0.00022941024392099515,
|
| 67 |
+
"loss": 0.6377084732055665,
|
| 68 |
+
"mean_token_accuracy": 0.817834352850914,
|
| 69 |
+
"num_tokens": 726579.0,
|
| 70 |
+
"step": 300
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 0.6780185508728027,
|
| 74 |
+
"epoch": 0.9090909090909091,
|
| 75 |
+
"grad_norm": 0.45764321088790894,
|
| 76 |
+
"learning_rate": 0.0002677731609646398,
|
| 77 |
+
"loss": 0.6206952285766602,
|
| 78 |
+
"mean_token_accuracy": 0.8230367678403855,
|
| 79 |
+
"num_tokens": 848944.0,
|
| 80 |
+
"step": 350
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.0,
|
| 84 |
+
"eval_entropy": 0.6696528858290269,
|
| 85 |
+
"eval_loss": 0.6696833372116089,
|
| 86 |
+
"eval_mean_token_accuracy": 0.807859004690097,
|
| 87 |
+
"eval_num_tokens": 931087.0,
|
| 88 |
+
"eval_runtime": 107.6403,
|
| 89 |
+
"eval_samples_per_second": 15.394,
|
| 90 |
+
"eval_steps_per_second": 1.932,
|
| 91 |
+
"step": 385
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"entropy": 0.6597446477413178,
|
| 95 |
+
"epoch": 1.0389610389610389,
|
| 96 |
+
"grad_norm": 0.6144201159477234,
|
| 97 |
+
"learning_rate": 0.0002953825629100547,
|
| 98 |
+
"loss": 0.5949639511108399,
|
| 99 |
+
"mean_token_accuracy": 0.8268985056877136,
|
| 100 |
+
"num_tokens": 968580.0,
|
| 101 |
+
"step": 400
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"entropy": 0.6230974847078323,
|
| 105 |
+
"epoch": 1.1688311688311688,
|
| 106 |
+
"grad_norm": 0.6531808376312256,
|
| 107 |
+
"learning_rate": 0.0002951458769281706,
|
| 108 |
+
"loss": 0.5671290588378907,
|
| 109 |
+
"mean_token_accuracy": 0.8358146512508392,
|
| 110 |
+
"num_tokens": 1090002.0,
|
| 111 |
+
"step": 450
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"entropy": 0.6187548145651818,
|
| 115 |
+
"epoch": 1.2987012987012987,
|
| 116 |
+
"grad_norm": 0.5326048135757446,
|
| 117 |
+
"learning_rate": 0.00029460622090364655,
|
| 118 |
+
"loss": 0.5627620697021485,
|
| 119 |
+
"mean_token_accuracy": 0.8350429546833038,
|
| 120 |
+
"num_tokens": 1212161.0,
|
| 121 |
+
"step": 500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"entropy": 0.6244118404388428,
|
| 125 |
+
"epoch": 1.4285714285714286,
|
| 126 |
+
"grad_norm": 0.5244704484939575,
|
| 127 |
+
"learning_rate": 0.000293764703694467,
|
| 128 |
+
"loss": 0.5693208694458007,
|
| 129 |
+
"mean_token_accuracy": 0.8332419580221176,
|
| 130 |
+
"num_tokens": 1332852.0,
|
| 131 |
+
"step": 550
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"entropy": 0.6074669760465622,
|
| 135 |
+
"epoch": 1.5584415584415585,
|
| 136 |
+
"grad_norm": 0.5502334833145142,
|
| 137 |
+
"learning_rate": 0.00029262305440775585,
|
| 138 |
+
"loss": 0.5543546676635742,
|
| 139 |
+
"mean_token_accuracy": 0.8364702826738357,
|
| 140 |
+
"num_tokens": 1453569.0,
|
| 141 |
+
"step": 600
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"entropy": 0.5978778421878814,
|
| 145 |
+
"epoch": 1.6883116883116882,
|
| 146 |
+
"grad_norm": 0.5542253255844116,
|
| 147 |
+
"learning_rate": 0.00029118361884689434,
|
| 148 |
+
"loss": 0.5433733367919922,
|
| 149 |
+
"mean_token_accuracy": 0.8386943048238754,
|
| 150 |
+
"num_tokens": 1577152.0,
|
| 151 |
+
"step": 650
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"entropy": 0.6171110290288925,
|
| 155 |
+
"epoch": 1.8181818181818183,
|
| 156 |
+
"grad_norm": 0.4130888283252716,
|
| 157 |
+
"learning_rate": 0.00028944935469148256,
|
| 158 |
+
"loss": 0.5616254043579102,
|
| 159 |
+
"mean_token_accuracy": 0.8357571196556092,
|
| 160 |
+
"num_tokens": 1691926.0,
|
| 161 |
+
"step": 700
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"entropy": 0.6099183800816536,
|
| 165 |
+
"epoch": 1.948051948051948,
|
| 166 |
+
"grad_norm": 0.5726969838142395,
|
| 167 |
+
"learning_rate": 0.0002874238254200486,
|
| 168 |
+
"loss": 0.5553982543945313,
|
| 169 |
+
"mean_token_accuracy": 0.8366436153650284,
|
| 170 |
+
"num_tokens": 1816059.0,
|
| 171 |
+
"step": 750
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.0,
|
| 175 |
+
"eval_entropy": 0.6355861249164894,
|
| 176 |
+
"eval_loss": 0.6270219087600708,
|
| 177 |
+
"eval_mean_token_accuracy": 0.8184372132214216,
|
| 178 |
+
"eval_num_tokens": 1862174.0,
|
| 179 |
+
"eval_runtime": 107.2043,
|
| 180 |
+
"eval_samples_per_second": 15.456,
|
| 181 |
+
"eval_steps_per_second": 1.94,
|
| 182 |
+
"step": 770
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"entropy": 0.5670756819844246,
|
| 186 |
+
"epoch": 2.0779220779220777,
|
| 187 |
+
"grad_norm": 0.6053982377052307,
|
| 188 |
+
"learning_rate": 0.0002851111929879924,
|
| 189 |
+
"loss": 0.505102653503418,
|
| 190 |
+
"mean_token_accuracy": 0.8481210070848465,
|
| 191 |
+
"num_tokens": 1931345.0,
|
| 192 |
+
"step": 800
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"entropy": 0.5276236647367477,
|
| 196 |
+
"epoch": 2.207792207792208,
|
| 197 |
+
"grad_norm": 0.5643910765647888,
|
| 198 |
+
"learning_rate": 0.0002825162092758099,
|
| 199 |
+
"loss": 0.4677161407470703,
|
| 200 |
+
"mean_token_accuracy": 0.8566789335012436,
|
| 201 |
+
"num_tokens": 2057087.0,
|
| 202 |
+
"step": 850
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"entropy": 0.5339252215623855,
|
| 206 |
+
"epoch": 2.3376623376623376,
|
| 207 |
+
"grad_norm": 0.42681995034217834,
|
| 208 |
+
"learning_rate": 0.0002796442063251685,
|
| 209 |
+
"loss": 0.47243389129638674,
|
| 210 |
+
"mean_token_accuracy": 0.8550587689876556,
|
| 211 |
+
"num_tokens": 2179801.0,
|
| 212 |
+
"step": 900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"entropy": 0.5280529841780662,
|
| 216 |
+
"epoch": 2.4675324675324677,
|
| 217 |
+
"grad_norm": 0.5158858895301819,
|
| 218 |
+
"learning_rate": 0.00027650108538289684,
|
| 219 |
+
"loss": 0.4702972412109375,
|
| 220 |
+
"mean_token_accuracy": 0.8564158076047897,
|
| 221 |
+
"num_tokens": 2300775.0,
|
| 222 |
+
"step": 950
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"entropy": 0.5310711139440536,
|
| 226 |
+
"epoch": 2.5974025974025974,
|
| 227 |
+
"grad_norm": 0.5546005368232727,
|
| 228 |
+
"learning_rate": 0.0002730933047754003,
|
| 229 |
+
"loss": 0.47338516235351563,
|
| 230 |
+
"mean_token_accuracy": 0.8548757725954056,
|
| 231 |
+
"num_tokens": 2425909.0,
|
| 232 |
+
"step": 1000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"entropy": 0.5326914456486702,
|
| 236 |
+
"epoch": 2.7272727272727275,
|
| 237 |
+
"grad_norm": 0.573678195476532,
|
| 238 |
+
"learning_rate": 0.0002694278666384176,
|
| 239 |
+
"loss": 0.47013877868652343,
|
| 240 |
+
"mean_token_accuracy": 0.8559313827753067,
|
| 241 |
+
"num_tokens": 2542506.0,
|
| 242 |
+
"step": 1050
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"entropy": 0.5230106875300408,
|
| 246 |
+
"epoch": 2.857142857142857,
|
| 247 |
+
"grad_norm": 0.43543529510498047,
|
| 248 |
+
"learning_rate": 0.0002655123025293855,
|
| 249 |
+
"loss": 0.47225719451904297,
|
| 250 |
+
"mean_token_accuracy": 0.856199751496315,
|
| 251 |
+
"num_tokens": 2666261.0,
|
| 252 |
+
"step": 1100
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"entropy": 0.5375474086403846,
|
| 256 |
+
"epoch": 2.987012987012987,
|
| 257 |
+
"grad_norm": 0.5083765387535095,
|
| 258 |
+
"learning_rate": 0.0002613546579519744,
|
| 259 |
+
"loss": 0.4798706436157227,
|
| 260 |
+
"mean_token_accuracy": 0.8544004863500595,
|
| 261 |
+
"num_tokens": 2781874.0,
|
| 262 |
+
"step": 1150
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 3.0,
|
| 266 |
+
"eval_entropy": 0.5890935378578993,
|
| 267 |
+
"eval_loss": 0.6210407018661499,
|
| 268 |
+
"eval_mean_token_accuracy": 0.8224744538848217,
|
| 269 |
+
"eval_num_tokens": 2793261.0,
|
| 270 |
+
"eval_runtime": 107.2151,
|
| 271 |
+
"eval_samples_per_second": 15.455,
|
| 272 |
+
"eval_steps_per_second": 1.94,
|
| 273 |
+
"step": 1155
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"entropy": 0.45643474519252775,
|
| 277 |
+
"epoch": 3.116883116883117,
|
| 278 |
+
"grad_norm": 0.5114700198173523,
|
| 279 |
+
"learning_rate": 0.00025696347582459286,
|
| 280 |
+
"loss": 0.38789520263671873,
|
| 281 |
+
"mean_token_accuracy": 0.876228296160698,
|
| 282 |
+
"num_tokens": 2896983.0,
|
| 283 |
+
"step": 1200
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"entropy": 0.4473289516568184,
|
| 287 |
+
"epoch": 3.2467532467532467,
|
| 288 |
+
"grad_norm": 0.7070309519767761,
|
| 289 |
+
"learning_rate": 0.00025234777892683014,
|
| 290 |
+
"loss": 0.38309051513671877,
|
| 291 |
+
"mean_token_accuracy": 0.8787942957878113,
|
| 292 |
+
"num_tokens": 3019005.0,
|
| 293 |
+
"step": 1250
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"entropy": 0.4467442426085472,
|
| 297 |
+
"epoch": 3.3766233766233764,
|
| 298 |
+
"grad_norm": 0.6292402744293213,
|
| 299 |
+
"learning_rate": 0.00024751705135990325,
|
| 300 |
+
"loss": 0.38877143859863283,
|
| 301 |
+
"mean_token_accuracy": 0.8765716356039047,
|
| 302 |
+
"num_tokens": 3143415.0,
|
| 303 |
+
"step": 1300
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"entropy": 0.45880579262971877,
|
| 307 |
+
"epoch": 3.5064935064935066,
|
| 308 |
+
"grad_norm": 0.5440912842750549,
|
| 309 |
+
"learning_rate": 0.00024248121905920444,
|
| 310 |
+
"loss": 0.39555030822753906,
|
| 311 |
+
"mean_token_accuracy": 0.8744896292686463,
|
| 312 |
+
"num_tokens": 3263845.0,
|
| 313 |
+
"step": 1350
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"entropy": 0.4655648723244667,
|
| 317 |
+
"epoch": 3.6363636363636362,
|
| 318 |
+
"grad_norm": 0.7060829401016235,
|
| 319 |
+
"learning_rate": 0.00023725062939898927,
|
| 320 |
+
"loss": 0.40029312133789063,
|
| 321 |
+
"mean_token_accuracy": 0.8748717665672302,
|
| 322 |
+
"num_tokens": 3383117.0,
|
| 323 |
+
"step": 1400
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"entropy": 0.4440704095363617,
|
| 327 |
+
"epoch": 3.7662337662337664,
|
| 328 |
+
"grad_norm": 0.5638645887374878,
|
| 329 |
+
"learning_rate": 0.0002318360299311144,
|
| 330 |
+
"loss": 0.38907997131347655,
|
| 331 |
+
"mean_token_accuracy": 0.8759198677539826,
|
| 332 |
+
"num_tokens": 3509724.0,
|
| 333 |
+
"step": 1450
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"entropy": 0.4616069641709328,
|
| 337 |
+
"epoch": 3.896103896103896,
|
| 338 |
+
"grad_norm": 0.7910256385803223,
|
| 339 |
+
"learning_rate": 0.00022624854630150942,
|
| 340 |
+
"loss": 0.3976031494140625,
|
| 341 |
+
"mean_token_accuracy": 0.8735713469982147,
|
| 342 |
+
"num_tokens": 3631110.0,
|
| 343 |
+
"step": 1500
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 4.0,
|
| 347 |
+
"eval_entropy": 0.5386111264905105,
|
| 348 |
+
"eval_loss": 0.6525173187255859,
|
| 349 |
+
"eval_mean_token_accuracy": 0.8202141162294608,
|
| 350 |
+
"eval_num_tokens": 3724348.0,
|
| 351 |
+
"eval_runtime": 107.2294,
|
| 352 |
+
"eval_samples_per_second": 15.453,
|
| 353 |
+
"eval_steps_per_second": 1.94,
|
| 354 |
+
"step": 1540
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"entropy": 0.44891556322574616,
|
| 358 |
+
"epoch": 4.025974025974026,
|
| 359 |
+
"grad_norm": 0.7205175161361694,
|
| 360 |
+
"learning_rate": 0.00022049965938976109,
|
| 361 |
+
"loss": 0.3779668426513672,
|
| 362 |
+
"mean_token_accuracy": 0.8788793754577636,
|
| 363 |
+
"num_tokens": 3749929.0,
|
| 364 |
+
"step": 1550
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"entropy": 0.37067714661359785,
|
| 368 |
+
"epoch": 4.1558441558441555,
|
| 369 |
+
"grad_norm": 0.7673031687736511,
|
| 370 |
+
"learning_rate": 0.00021460118171878076,
|
| 371 |
+
"loss": 0.295870304107666,
|
| 372 |
+
"mean_token_accuracy": 0.9020969843864441,
|
| 373 |
+
"num_tokens": 3871403.0,
|
| 374 |
+
"step": 1600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"entropy": 0.37246827483177186,
|
| 378 |
+
"epoch": 4.285714285714286,
|
| 379 |
+
"grad_norm": 0.64629727602005,
|
| 380 |
+
"learning_rate": 0.000208565233183028,
|
| 381 |
+
"loss": 0.29844835281372073,
|
| 382 |
+
"mean_token_accuracy": 0.901744744181633,
|
| 383 |
+
"num_tokens": 3990410.0,
|
| 384 |
+
"step": 1650
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"entropy": 0.37455891370773314,
|
| 388 |
+
"epoch": 4.415584415584416,
|
| 389 |
+
"grad_norm": 0.6829578280448914,
|
| 390 |
+
"learning_rate": 0.00020240421614516274,
|
| 391 |
+
"loss": 0.30404550552368165,
|
| 392 |
+
"mean_token_accuracy": 0.9000005573034286,
|
| 393 |
+
"num_tokens": 4107377.0,
|
| 394 |
+
"step": 1700
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"entropy": 0.37828688144683836,
|
| 398 |
+
"epoch": 4.545454545454545,
|
| 399 |
+
"grad_norm": 0.6125279664993286,
|
| 400 |
+
"learning_rate": 0.0001961307899522958,
|
| 401 |
+
"loss": 0.30663524627685546,
|
| 402 |
+
"mean_token_accuracy": 0.8985623228549957,
|
| 403 |
+
"num_tokens": 4225238.0,
|
| 404 |
+
"step": 1750
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"entropy": 0.375451121032238,
|
| 408 |
+
"epoch": 4.675324675324675,
|
| 409 |
+
"grad_norm": 0.6192310452461243,
|
| 410 |
+
"learning_rate": 0.00018975784492420103,
|
| 411 |
+
"loss": 0.3078347396850586,
|
| 412 |
+
"mean_token_accuracy": 0.8998477959632873,
|
| 413 |
+
"num_tokens": 4348229.0,
|
| 414 |
+
"step": 1800
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"entropy": 0.3755231860280037,
|
| 418 |
+
"epoch": 4.805194805194805,
|
| 419 |
+
"grad_norm": 0.7531238794326782,
|
| 420 |
+
"learning_rate": 0.0001832984758669361,
|
| 421 |
+
"loss": 0.3057806777954102,
|
| 422 |
+
"mean_token_accuracy": 0.8995966756343842,
|
| 423 |
+
"num_tokens": 4471337.0,
|
| 424 |
+
"step": 1850
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"entropy": 0.3791221937537193,
|
| 428 |
+
"epoch": 4.935064935064935,
|
| 429 |
+
"grad_norm": 0.7267350554466248,
|
| 430 |
+
"learning_rate": 0.00017676595516629556,
|
| 431 |
+
"loss": 0.3108745002746582,
|
| 432 |
+
"mean_token_accuracy": 0.8971030461788178,
|
| 433 |
+
"num_tokens": 4596516.0,
|
| 434 |
+
"step": 1900
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 5.0,
|
| 438 |
+
"eval_entropy": 0.47880522749171806,
|
| 439 |
+
"eval_loss": 0.6903005242347717,
|
| 440 |
+
"eval_mean_token_accuracy": 0.8205848932266235,
|
| 441 |
+
"eval_num_tokens": 4655435.0,
|
| 442 |
+
"eval_runtime": 107.2115,
|
| 443 |
+
"eval_samples_per_second": 15.455,
|
| 444 |
+
"eval_steps_per_second": 1.94,
|
| 445 |
+
"step": 1925
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"entropy": 0.325536966919899,
|
| 449 |
+
"epoch": 5.064935064935065,
|
| 450 |
+
"grad_norm": 0.5973520874977112,
|
| 451 |
+
"learning_rate": 0.00017017370551638175,
|
| 452 |
+
"loss": 0.2537745094299316,
|
| 453 |
+
"mean_token_accuracy": 0.9170269852876664,
|
| 454 |
+
"num_tokens": 4720113.0,
|
| 455 |
+
"step": 1950
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"entropy": 0.2805623610317707,
|
| 459 |
+
"epoch": 5.194805194805195,
|
| 460 |
+
"grad_norm": 0.8208709359169006,
|
| 461 |
+
"learning_rate": 0.00016353527233932972,
|
| 462 |
+
"loss": 0.20699060440063477,
|
| 463 |
+
"mean_token_accuracy": 0.9297245645523071,
|
| 464 |
+
"num_tokens": 4842234.0,
|
| 465 |
+
"step": 2000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"entropy": 0.2951572193205357,
|
| 469 |
+
"epoch": 5.324675324675325,
|
| 470 |
+
"grad_norm": 0.624740481376648,
|
| 471 |
+
"learning_rate": 0.0001568642959528572,
|
| 472 |
+
"loss": 0.21564756393432616,
|
| 473 |
+
"mean_token_accuracy": 0.9271520495414733,
|
| 474 |
+
"num_tokens": 4959991.0,
|
| 475 |
+
"step": 2050
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"entropy": 0.29860043823719024,
|
| 479 |
+
"epoch": 5.454545454545454,
|
| 480 |
+
"grad_norm": 0.8418864607810974,
|
| 481 |
+
"learning_rate": 0.00015017448354282757,
|
| 482 |
+
"loss": 0.2190338897705078,
|
| 483 |
+
"mean_token_accuracy": 0.9261587560176849,
|
| 484 |
+
"num_tokens": 5082208.0,
|
| 485 |
+
"step": 2100
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"entropy": 0.2909143240749836,
|
| 489 |
+
"epoch": 5.584415584415584,
|
| 490 |
+
"grad_norm": 0.7306669354438782,
|
| 491 |
+
"learning_rate": 0.00014347958099841522,
|
| 492 |
+
"loss": 0.21448070526123048,
|
| 493 |
+
"mean_token_accuracy": 0.926868360042572,
|
| 494 |
+
"num_tokens": 5199699.0,
|
| 495 |
+
"step": 2150
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"entropy": 0.2885631823539734,
|
| 499 |
+
"epoch": 5.714285714285714,
|
| 500 |
+
"grad_norm": 0.7255174517631531,
|
| 501 |
+
"learning_rate": 0.0001367933446677463,
|
| 502 |
+
"loss": 0.21533376693725587,
|
| 503 |
+
"mean_token_accuracy": 0.9273367804288865,
|
| 504 |
+
"num_tokens": 5320501.0,
|
| 505 |
+
"step": 2200
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"entropy": 0.28939690127968787,
|
| 509 |
+
"epoch": 5.8441558441558445,
|
| 510 |
+
"grad_norm": 0.7074116468429565,
|
| 511 |
+
"learning_rate": 0.00013012951309204776,
|
| 512 |
+
"loss": 0.21616615295410158,
|
| 513 |
+
"mean_token_accuracy": 0.9268639695644378,
|
| 514 |
+
"num_tokens": 5442291.0,
|
| 515 |
+
"step": 2250
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"entropy": 0.29287345737218856,
|
| 519 |
+
"epoch": 5.974025974025974,
|
| 520 |
+
"grad_norm": 0.8009970188140869,
|
| 521 |
+
"learning_rate": 0.00012350177877638605,
|
| 522 |
+
"loss": 0.21827854156494142,
|
| 523 |
+
"mean_token_accuracy": 0.926282970905304,
|
| 524 |
+
"num_tokens": 5560531.0,
|
| 525 |
+
"step": 2300
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 6.0,
|
| 529 |
+
"eval_entropy": 0.42221833765506744,
|
| 530 |
+
"eval_loss": 0.7726835608482361,
|
| 531 |
+
"eval_mean_token_accuracy": 0.814933180809021,
|
| 532 |
+
"eval_num_tokens": 5586522.0,
|
| 533 |
+
"eval_runtime": 106.3715,
|
| 534 |
+
"eval_samples_per_second": 15.577,
|
| 535 |
+
"eval_steps_per_second": 1.955,
|
| 536 |
+
"step": 2310
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"entropy": 0.23905221119523049,
|
| 540 |
+
"epoch": 6.103896103896104,
|
| 541 |
+
"grad_norm": 0.7689157128334045,
|
| 542 |
+
"learning_rate": 0.0001169237600549981,
|
| 543 |
+
"loss": 0.15075304985046387,
|
| 544 |
+
"mean_token_accuracy": 0.9464442139863968,
|
| 545 |
+
"num_tokens": 5682578.0,
|
| 546 |
+
"step": 2350
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"entropy": 0.2028607265651226,
|
| 550 |
+
"epoch": 6.233766233766234,
|
| 551 |
+
"grad_norm": 0.5387632250785828,
|
| 552 |
+
"learning_rate": 0.00011040897310902461,
|
| 553 |
+
"loss": 0.13421324729919434,
|
| 554 |
+
"mean_token_accuracy": 0.9551875954866409,
|
| 555 |
+
"num_tokens": 5803409.0,
|
| 556 |
+
"step": 2400
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"entropy": 0.20566919729113578,
|
| 560 |
+
"epoch": 6.363636363636363,
|
| 561 |
+
"grad_norm": 0.6590266227722168,
|
| 562 |
+
"learning_rate": 0.00010397080419414323,
|
| 563 |
+
"loss": 0.1351051139831543,
|
| 564 |
+
"mean_token_accuracy": 0.9552580755949021,
|
| 565 |
+
"num_tokens": 5927439.0,
|
| 566 |
+
"step": 2450
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"entropy": 0.20123363941907882,
|
| 570 |
+
"epoch": 6.4935064935064934,
|
| 571 |
+
"grad_norm": 0.7304044961929321,
|
| 572 |
+
"learning_rate": 9.762248213516496e-05,
|
| 573 |
+
"loss": 0.1317083740234375,
|
| 574 |
+
"mean_token_accuracy": 0.9555035126209259,
|
| 575 |
+
"num_tokens": 6052633.0,
|
| 576 |
+
"step": 2500
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"entropy": 0.2167628873884678,
|
| 580 |
+
"epoch": 6.623376623376624,
|
| 581 |
+
"grad_norm": 0.9369059801101685,
|
| 582 |
+
"learning_rate": 9.137705114411241e-05,
|
| 583 |
+
"loss": 0.1422165298461914,
|
| 584 |
+
"mean_token_accuracy": 0.9518895560503006,
|
| 585 |
+
"num_tokens": 6167503.0,
|
| 586 |
+
"step": 2550
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"entropy": 0.2181946974992752,
|
| 590 |
+
"epoch": 6.753246753246753,
|
| 591 |
+
"grad_norm": 0.8891282081604004,
|
| 592 |
+
"learning_rate": 8.524734401763032e-05,
|
| 593 |
+
"loss": 0.14409255027770995,
|
| 594 |
+
"mean_token_accuracy": 0.9519028991460801,
|
| 595 |
+
"num_tokens": 6284023.0,
|
| 596 |
+
"step": 2600
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"entropy": 0.21032980993390082,
|
| 600 |
+
"epoch": 6.883116883116883,
|
| 601 |
+
"grad_norm": 0.6714637875556946,
|
| 602 |
+
"learning_rate": 7.924595576880276e-05,
|
| 603 |
+
"loss": 0.1382604694366455,
|
| 604 |
+
"mean_token_accuracy": 0.95325155377388,
|
| 605 |
+
"num_tokens": 6408327.0,
|
| 606 |
+
"step": 2650
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 7.0,
|
| 610 |
+
"eval_entropy": 0.36334023767938983,
|
| 611 |
+
"eval_loss": 0.8811500668525696,
|
| 612 |
+
"eval_mean_token_accuracy": 0.8139389048402126,
|
| 613 |
+
"eval_num_tokens": 6517609.0,
|
| 614 |
+
"eval_runtime": 107.2218,
|
| 615 |
+
"eval_samples_per_second": 15.454,
|
| 616 |
+
"eval_steps_per_second": 1.94,
|
| 617 |
+
"step": 2695
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"entropy": 0.19888876721262932,
|
| 621 |
+
"epoch": 7.012987012987013,
|
| 622 |
+
"grad_norm": 0.5274959206581116,
|
| 623 |
+
"learning_rate": 7.338521774755479e-05,
|
| 624 |
+
"loss": 0.12947993278503417,
|
| 625 |
+
"mean_token_accuracy": 0.9572676807641983,
|
| 626 |
+
"num_tokens": 6530430.0,
|
| 627 |
+
"step": 2700
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"entropy": 0.1597208461165428,
|
| 631 |
+
"epoch": 7.142857142857143,
|
| 632 |
+
"grad_norm": 0.4715121388435364,
|
| 633 |
+
"learning_rate": 6.767717230281708e-05,
|
| 634 |
+
"loss": 0.08882388114929199,
|
| 635 |
+
"mean_token_accuracy": 0.9716670286655426,
|
| 636 |
+
"num_tokens": 6648623.0,
|
| 637 |
+
"step": 2750
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"entropy": 0.15440757133066654,
|
| 641 |
+
"epoch": 7.2727272727272725,
|
| 642 |
+
"grad_norm": 0.42084604501724243,
|
| 643 |
+
"learning_rate": 6.213354803851401e-05,
|
| 644 |
+
"loss": 0.08850942611694336,
|
| 645 |
+
"mean_token_accuracy": 0.9719003230333328,
|
| 646 |
+
"num_tokens": 6768614.0,
|
| 647 |
+
"step": 2800
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"entropy": 0.1516306409984827,
|
| 651 |
+
"epoch": 7.402597402597403,
|
| 652 |
+
"grad_norm": 0.5749953985214233,
|
| 653 |
+
"learning_rate": 5.6765735714220424e-05,
|
| 654 |
+
"loss": 0.08566269874572754,
|
| 655 |
+
"mean_token_accuracy": 0.9719378662109375,
|
| 656 |
+
"num_tokens": 6892420.0,
|
| 657 |
+
"step": 2850
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"entropy": 0.1592805414646864,
|
| 661 |
+
"epoch": 7.532467532467533,
|
| 662 |
+
"grad_norm": 0.7836453318595886,
|
| 663 |
+
"learning_rate": 5.158476484000283e-05,
|
| 664 |
+
"loss": 0.09052552223205566,
|
| 665 |
+
"mean_token_accuracy": 0.9701271635293961,
|
| 666 |
+
"num_tokens": 7009857.0,
|
| 667 |
+
"step": 2900
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"entropy": 0.15554923228919507,
|
| 671 |
+
"epoch": 7.662337662337662,
|
| 672 |
+
"grad_norm": 0.5220458507537842,
|
| 673 |
+
"learning_rate": 4.6601281013538485e-05,
|
| 674 |
+
"loss": 0.08924313545227051,
|
| 675 |
+
"mean_token_accuracy": 0.9713792878389359,
|
| 676 |
+
"num_tokens": 7132184.0,
|
| 677 |
+
"step": 2950
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"entropy": 0.15688340798020362,
|
| 681 |
+
"epoch": 7.792207792207792,
|
| 682 |
+
"grad_norm": 0.5455254316329956,
|
| 683 |
+
"learning_rate": 4.182552404607813e-05,
|
| 684 |
+
"loss": 0.08741535186767578,
|
| 685 |
+
"mean_token_accuracy": 0.9710536366701126,
|
| 686 |
+
"num_tokens": 7250668.0,
|
| 687 |
+
"step": 3000
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"entropy": 0.15722099043428897,
|
| 691 |
+
"epoch": 7.922077922077922,
|
| 692 |
+
"grad_norm": 0.7133240699768066,
|
| 693 |
+
"learning_rate": 3.7267306922198405e-05,
|
| 694 |
+
"loss": 0.08726611137390136,
|
| 695 |
+
"mean_token_accuracy": 0.9708961689472199,
|
| 696 |
+
"num_tokens": 7373911.0,
|
| 697 |
+
"step": 3050
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 8.0,
|
| 701 |
+
"eval_entropy": 0.3186919501481148,
|
| 702 |
+
"eval_loss": 1.0071876049041748,
|
| 703 |
+
"eval_mean_token_accuracy": 0.8123214006997072,
|
| 704 |
+
"eval_num_tokens": 7448696.0,
|
| 705 |
+
"eval_runtime": 107.0969,
|
| 706 |
+
"eval_samples_per_second": 15.472,
|
| 707 |
+
"eval_steps_per_second": 1.942,
|
| 708 |
+
"step": 3080
|
| 709 |
+
}
|
| 710 |
+
],
|
| 711 |
+
"logging_steps": 50,
|
| 712 |
+
"max_steps": 3850,
|
| 713 |
+
"num_input_tokens_seen": 0,
|
| 714 |
+
"num_train_epochs": 10,
|
| 715 |
+
"save_steps": 500,
|
| 716 |
+
"stateful_callbacks": {
|
| 717 |
+
"TrainerControl": {
|
| 718 |
+
"args": {
|
| 719 |
+
"should_epoch_stop": false,
|
| 720 |
+
"should_evaluate": false,
|
| 721 |
+
"should_log": false,
|
| 722 |
+
"should_save": true,
|
| 723 |
+
"should_training_stop": false
|
| 724 |
+
},
|
| 725 |
+
"attributes": {}
|
| 726 |
+
}
|
| 727 |
+
},
|
| 728 |
+
"total_flos": 8.735229484825283e+17,
|
| 729 |
+
"train_batch_size": 8,
|
| 730 |
+
"trial_name": null,
|
| 731 |
+
"trial_params": null
|
| 732 |
+
}
|
DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3465/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3.5-9B-Base
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen3.5-9B-Base
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.18.1
|
DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3465/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3.5-9B-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 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 32,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.06320962833718659,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.1",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 16,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"q_proj",
|
| 33 |
+
"k_proj",
|
| 34 |
+
"v_proj",
|
| 35 |
+
"gate_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
+
"o_proj",
|
| 38 |
+
"up_proj"
|
| 39 |
+
],
|
| 40 |
+
"target_parameters": null,
|
| 41 |
+
"task_type": "CAUSAL_LM",
|
| 42 |
+
"trainable_token_indices": null,
|
| 43 |
+
"use_dora": false,
|
| 44 |
+
"use_qalora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3465/chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3465/tokenizer_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|endoftext|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"model_max_length": 262144,
|
| 14 |
+
"model_specific_special_tokens": {
|
| 15 |
+
"audio_bos_token": "<|audio_start|>",
|
| 16 |
+
"audio_eos_token": "<|audio_end|>",
|
| 17 |
+
"audio_token": "<|audio_pad|>",
|
| 18 |
+
"image_token": "<|image_pad|>",
|
| 19 |
+
"video_token": "<|video_pad|>",
|
| 20 |
+
"vision_bos_token": "<|vision_start|>",
|
| 21 |
+
"vision_eos_token": "<|vision_end|>"
|
| 22 |
+
},
|
| 23 |
+
"pad_token": "<|endoftext|>",
|
| 24 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 25 |
+
"split_special_tokens": false,
|
| 26 |
+
"tokenizer_class": "TokenizersBackend",
|
| 27 |
+
"unk_token": null,
|
| 28 |
+
"video_token": "<|video_pad|>",
|
| 29 |
+
"vision_bos_token": "<|vision_start|>",
|
| 30 |
+
"vision_eos_token": "<|vision_end|>"
|
| 31 |
+
}
|
DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3465/trainer_state.json
ADDED
|
@@ -0,0 +1,823 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3465,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.7529579949378968,
|
| 14 |
+
"epoch": 0.12987012987012986,
|
| 15 |
+
"grad_norm": 1.0845375061035156,
|
| 16 |
+
"learning_rate": 3.759565870277177e-05,
|
| 17 |
+
"loss": 1.6464532470703126,
|
| 18 |
+
"mean_token_accuracy": 0.6610959130525589,
|
| 19 |
+
"num_tokens": 127115.0,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 0.8384856134653091,
|
| 24 |
+
"epoch": 0.2597402597402597,
|
| 25 |
+
"grad_norm": 0.787804126739502,
|
| 26 |
+
"learning_rate": 7.595857574641644e-05,
|
| 27 |
+
"loss": 0.7860373687744141,
|
| 28 |
+
"mean_token_accuracy": 0.7873306655883789,
|
| 29 |
+
"num_tokens": 251796.0,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 0.7570279932022095,
|
| 34 |
+
"epoch": 0.38961038961038963,
|
| 35 |
+
"grad_norm": 0.8686555624008179,
|
| 36 |
+
"learning_rate": 0.00011432149279006112,
|
| 37 |
+
"loss": 0.6997585296630859,
|
| 38 |
+
"mean_token_accuracy": 0.8050823694467545,
|
| 39 |
+
"num_tokens": 366505.0,
|
| 40 |
+
"step": 150
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.7074448710680008,
|
| 44 |
+
"epoch": 0.5194805194805194,
|
| 45 |
+
"grad_norm": 0.641474723815918,
|
| 46 |
+
"learning_rate": 0.00015268440983370578,
|
| 47 |
+
"loss": 0.6549726104736329,
|
| 48 |
+
"mean_token_accuracy": 0.812009590268135,
|
| 49 |
+
"num_tokens": 493150.0,
|
| 50 |
+
"step": 200
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.7119272118806839,
|
| 54 |
+
"epoch": 0.6493506493506493,
|
| 55 |
+
"grad_norm": 0.6778020858764648,
|
| 56 |
+
"learning_rate": 0.00019104732687735045,
|
| 57 |
+
"loss": 0.6522830963134766,
|
| 58 |
+
"mean_token_accuracy": 0.8144695377349853,
|
| 59 |
+
"num_tokens": 607197.0,
|
| 60 |
+
"step": 250
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.6957281070947647,
|
| 64 |
+
"epoch": 0.7792207792207793,
|
| 65 |
+
"grad_norm": 0.5819384455680847,
|
| 66 |
+
"learning_rate": 0.00022941024392099515,
|
| 67 |
+
"loss": 0.6377084732055665,
|
| 68 |
+
"mean_token_accuracy": 0.817834352850914,
|
| 69 |
+
"num_tokens": 726579.0,
|
| 70 |
+
"step": 300
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 0.6780185508728027,
|
| 74 |
+
"epoch": 0.9090909090909091,
|
| 75 |
+
"grad_norm": 0.45764321088790894,
|
| 76 |
+
"learning_rate": 0.0002677731609646398,
|
| 77 |
+
"loss": 0.6206952285766602,
|
| 78 |
+
"mean_token_accuracy": 0.8230367678403855,
|
| 79 |
+
"num_tokens": 848944.0,
|
| 80 |
+
"step": 350
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.0,
|
| 84 |
+
"eval_entropy": 0.6696528858290269,
|
| 85 |
+
"eval_loss": 0.6696833372116089,
|
| 86 |
+
"eval_mean_token_accuracy": 0.807859004690097,
|
| 87 |
+
"eval_num_tokens": 931087.0,
|
| 88 |
+
"eval_runtime": 107.6403,
|
| 89 |
+
"eval_samples_per_second": 15.394,
|
| 90 |
+
"eval_steps_per_second": 1.932,
|
| 91 |
+
"step": 385
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"entropy": 0.6597446477413178,
|
| 95 |
+
"epoch": 1.0389610389610389,
|
| 96 |
+
"grad_norm": 0.6144201159477234,
|
| 97 |
+
"learning_rate": 0.0002953825629100547,
|
| 98 |
+
"loss": 0.5949639511108399,
|
| 99 |
+
"mean_token_accuracy": 0.8268985056877136,
|
| 100 |
+
"num_tokens": 968580.0,
|
| 101 |
+
"step": 400
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"entropy": 0.6230974847078323,
|
| 105 |
+
"epoch": 1.1688311688311688,
|
| 106 |
+
"grad_norm": 0.6531808376312256,
|
| 107 |
+
"learning_rate": 0.0002951458769281706,
|
| 108 |
+
"loss": 0.5671290588378907,
|
| 109 |
+
"mean_token_accuracy": 0.8358146512508392,
|
| 110 |
+
"num_tokens": 1090002.0,
|
| 111 |
+
"step": 450
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"entropy": 0.6187548145651818,
|
| 115 |
+
"epoch": 1.2987012987012987,
|
| 116 |
+
"grad_norm": 0.5326048135757446,
|
| 117 |
+
"learning_rate": 0.00029460622090364655,
|
| 118 |
+
"loss": 0.5627620697021485,
|
| 119 |
+
"mean_token_accuracy": 0.8350429546833038,
|
| 120 |
+
"num_tokens": 1212161.0,
|
| 121 |
+
"step": 500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"entropy": 0.6244118404388428,
|
| 125 |
+
"epoch": 1.4285714285714286,
|
| 126 |
+
"grad_norm": 0.5244704484939575,
|
| 127 |
+
"learning_rate": 0.000293764703694467,
|
| 128 |
+
"loss": 0.5693208694458007,
|
| 129 |
+
"mean_token_accuracy": 0.8332419580221176,
|
| 130 |
+
"num_tokens": 1332852.0,
|
| 131 |
+
"step": 550
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"entropy": 0.6074669760465622,
|
| 135 |
+
"epoch": 1.5584415584415585,
|
| 136 |
+
"grad_norm": 0.5502334833145142,
|
| 137 |
+
"learning_rate": 0.00029262305440775585,
|
| 138 |
+
"loss": 0.5543546676635742,
|
| 139 |
+
"mean_token_accuracy": 0.8364702826738357,
|
| 140 |
+
"num_tokens": 1453569.0,
|
| 141 |
+
"step": 600
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"entropy": 0.5978778421878814,
|
| 145 |
+
"epoch": 1.6883116883116882,
|
| 146 |
+
"grad_norm": 0.5542253255844116,
|
| 147 |
+
"learning_rate": 0.00029118361884689434,
|
| 148 |
+
"loss": 0.5433733367919922,
|
| 149 |
+
"mean_token_accuracy": 0.8386943048238754,
|
| 150 |
+
"num_tokens": 1577152.0,
|
| 151 |
+
"step": 650
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"entropy": 0.6171110290288925,
|
| 155 |
+
"epoch": 1.8181818181818183,
|
| 156 |
+
"grad_norm": 0.4130888283252716,
|
| 157 |
+
"learning_rate": 0.00028944935469148256,
|
| 158 |
+
"loss": 0.5616254043579102,
|
| 159 |
+
"mean_token_accuracy": 0.8357571196556092,
|
| 160 |
+
"num_tokens": 1691926.0,
|
| 161 |
+
"step": 700
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"entropy": 0.6099183800816536,
|
| 165 |
+
"epoch": 1.948051948051948,
|
| 166 |
+
"grad_norm": 0.5726969838142395,
|
| 167 |
+
"learning_rate": 0.0002874238254200486,
|
| 168 |
+
"loss": 0.5553982543945313,
|
| 169 |
+
"mean_token_accuracy": 0.8366436153650284,
|
| 170 |
+
"num_tokens": 1816059.0,
|
| 171 |
+
"step": 750
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.0,
|
| 175 |
+
"eval_entropy": 0.6355861249164894,
|
| 176 |
+
"eval_loss": 0.6270219087600708,
|
| 177 |
+
"eval_mean_token_accuracy": 0.8184372132214216,
|
| 178 |
+
"eval_num_tokens": 1862174.0,
|
| 179 |
+
"eval_runtime": 107.2043,
|
| 180 |
+
"eval_samples_per_second": 15.456,
|
| 181 |
+
"eval_steps_per_second": 1.94,
|
| 182 |
+
"step": 770
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"entropy": 0.5670756819844246,
|
| 186 |
+
"epoch": 2.0779220779220777,
|
| 187 |
+
"grad_norm": 0.6053982377052307,
|
| 188 |
+
"learning_rate": 0.0002851111929879924,
|
| 189 |
+
"loss": 0.505102653503418,
|
| 190 |
+
"mean_token_accuracy": 0.8481210070848465,
|
| 191 |
+
"num_tokens": 1931345.0,
|
| 192 |
+
"step": 800
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"entropy": 0.5276236647367477,
|
| 196 |
+
"epoch": 2.207792207792208,
|
| 197 |
+
"grad_norm": 0.5643910765647888,
|
| 198 |
+
"learning_rate": 0.0002825162092758099,
|
| 199 |
+
"loss": 0.4677161407470703,
|
| 200 |
+
"mean_token_accuracy": 0.8566789335012436,
|
| 201 |
+
"num_tokens": 2057087.0,
|
| 202 |
+
"step": 850
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"entropy": 0.5339252215623855,
|
| 206 |
+
"epoch": 2.3376623376623376,
|
| 207 |
+
"grad_norm": 0.42681995034217834,
|
| 208 |
+
"learning_rate": 0.0002796442063251685,
|
| 209 |
+
"loss": 0.47243389129638674,
|
| 210 |
+
"mean_token_accuracy": 0.8550587689876556,
|
| 211 |
+
"num_tokens": 2179801.0,
|
| 212 |
+
"step": 900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"entropy": 0.5280529841780662,
|
| 216 |
+
"epoch": 2.4675324675324677,
|
| 217 |
+
"grad_norm": 0.5158858895301819,
|
| 218 |
+
"learning_rate": 0.00027650108538289684,
|
| 219 |
+
"loss": 0.4702972412109375,
|
| 220 |
+
"mean_token_accuracy": 0.8564158076047897,
|
| 221 |
+
"num_tokens": 2300775.0,
|
| 222 |
+
"step": 950
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"entropy": 0.5310711139440536,
|
| 226 |
+
"epoch": 2.5974025974025974,
|
| 227 |
+
"grad_norm": 0.5546005368232727,
|
| 228 |
+
"learning_rate": 0.0002730933047754003,
|
| 229 |
+
"loss": 0.47338516235351563,
|
| 230 |
+
"mean_token_accuracy": 0.8548757725954056,
|
| 231 |
+
"num_tokens": 2425909.0,
|
| 232 |
+
"step": 1000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"entropy": 0.5326914456486702,
|
| 236 |
+
"epoch": 2.7272727272727275,
|
| 237 |
+
"grad_norm": 0.573678195476532,
|
| 238 |
+
"learning_rate": 0.0002694278666384176,
|
| 239 |
+
"loss": 0.47013877868652343,
|
| 240 |
+
"mean_token_accuracy": 0.8559313827753067,
|
| 241 |
+
"num_tokens": 2542506.0,
|
| 242 |
+
"step": 1050
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"entropy": 0.5230106875300408,
|
| 246 |
+
"epoch": 2.857142857142857,
|
| 247 |
+
"grad_norm": 0.43543529510498047,
|
| 248 |
+
"learning_rate": 0.0002655123025293855,
|
| 249 |
+
"loss": 0.47225719451904297,
|
| 250 |
+
"mean_token_accuracy": 0.856199751496315,
|
| 251 |
+
"num_tokens": 2666261.0,
|
| 252 |
+
"step": 1100
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"entropy": 0.5375474086403846,
|
| 256 |
+
"epoch": 2.987012987012987,
|
| 257 |
+
"grad_norm": 0.5083765387535095,
|
| 258 |
+
"learning_rate": 0.0002613546579519744,
|
| 259 |
+
"loss": 0.4798706436157227,
|
| 260 |
+
"mean_token_accuracy": 0.8544004863500595,
|
| 261 |
+
"num_tokens": 2781874.0,
|
| 262 |
+
"step": 1150
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 3.0,
|
| 266 |
+
"eval_entropy": 0.5890935378578993,
|
| 267 |
+
"eval_loss": 0.6210407018661499,
|
| 268 |
+
"eval_mean_token_accuracy": 0.8224744538848217,
|
| 269 |
+
"eval_num_tokens": 2793261.0,
|
| 270 |
+
"eval_runtime": 107.2151,
|
| 271 |
+
"eval_samples_per_second": 15.455,
|
| 272 |
+
"eval_steps_per_second": 1.94,
|
| 273 |
+
"step": 1155
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"entropy": 0.45643474519252775,
|
| 277 |
+
"epoch": 3.116883116883117,
|
| 278 |
+
"grad_norm": 0.5114700198173523,
|
| 279 |
+
"learning_rate": 0.00025696347582459286,
|
| 280 |
+
"loss": 0.38789520263671873,
|
| 281 |
+
"mean_token_accuracy": 0.876228296160698,
|
| 282 |
+
"num_tokens": 2896983.0,
|
| 283 |
+
"step": 1200
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"entropy": 0.4473289516568184,
|
| 287 |
+
"epoch": 3.2467532467532467,
|
| 288 |
+
"grad_norm": 0.7070309519767761,
|
| 289 |
+
"learning_rate": 0.00025234777892683014,
|
| 290 |
+
"loss": 0.38309051513671877,
|
| 291 |
+
"mean_token_accuracy": 0.8787942957878113,
|
| 292 |
+
"num_tokens": 3019005.0,
|
| 293 |
+
"step": 1250
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"entropy": 0.4467442426085472,
|
| 297 |
+
"epoch": 3.3766233766233764,
|
| 298 |
+
"grad_norm": 0.6292402744293213,
|
| 299 |
+
"learning_rate": 0.00024751705135990325,
|
| 300 |
+
"loss": 0.38877143859863283,
|
| 301 |
+
"mean_token_accuracy": 0.8765716356039047,
|
| 302 |
+
"num_tokens": 3143415.0,
|
| 303 |
+
"step": 1300
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"entropy": 0.45880579262971877,
|
| 307 |
+
"epoch": 3.5064935064935066,
|
| 308 |
+
"grad_norm": 0.5440912842750549,
|
| 309 |
+
"learning_rate": 0.00024248121905920444,
|
| 310 |
+
"loss": 0.39555030822753906,
|
| 311 |
+
"mean_token_accuracy": 0.8744896292686463,
|
| 312 |
+
"num_tokens": 3263845.0,
|
| 313 |
+
"step": 1350
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"entropy": 0.4655648723244667,
|
| 317 |
+
"epoch": 3.6363636363636362,
|
| 318 |
+
"grad_norm": 0.7060829401016235,
|
| 319 |
+
"learning_rate": 0.00023725062939898927,
|
| 320 |
+
"loss": 0.40029312133789063,
|
| 321 |
+
"mean_token_accuracy": 0.8748717665672302,
|
| 322 |
+
"num_tokens": 3383117.0,
|
| 323 |
+
"step": 1400
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"entropy": 0.4440704095363617,
|
| 327 |
+
"epoch": 3.7662337662337664,
|
| 328 |
+
"grad_norm": 0.5638645887374878,
|
| 329 |
+
"learning_rate": 0.0002318360299311144,
|
| 330 |
+
"loss": 0.38907997131347655,
|
| 331 |
+
"mean_token_accuracy": 0.8759198677539826,
|
| 332 |
+
"num_tokens": 3509724.0,
|
| 333 |
+
"step": 1450
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"entropy": 0.4616069641709328,
|
| 337 |
+
"epoch": 3.896103896103896,
|
| 338 |
+
"grad_norm": 0.7910256385803223,
|
| 339 |
+
"learning_rate": 0.00022624854630150942,
|
| 340 |
+
"loss": 0.3976031494140625,
|
| 341 |
+
"mean_token_accuracy": 0.8735713469982147,
|
| 342 |
+
"num_tokens": 3631110.0,
|
| 343 |
+
"step": 1500
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 4.0,
|
| 347 |
+
"eval_entropy": 0.5386111264905105,
|
| 348 |
+
"eval_loss": 0.6525173187255859,
|
| 349 |
+
"eval_mean_token_accuracy": 0.8202141162294608,
|
| 350 |
+
"eval_num_tokens": 3724348.0,
|
| 351 |
+
"eval_runtime": 107.2294,
|
| 352 |
+
"eval_samples_per_second": 15.453,
|
| 353 |
+
"eval_steps_per_second": 1.94,
|
| 354 |
+
"step": 1540
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"entropy": 0.44891556322574616,
|
| 358 |
+
"epoch": 4.025974025974026,
|
| 359 |
+
"grad_norm": 0.7205175161361694,
|
| 360 |
+
"learning_rate": 0.00022049965938976109,
|
| 361 |
+
"loss": 0.3779668426513672,
|
| 362 |
+
"mean_token_accuracy": 0.8788793754577636,
|
| 363 |
+
"num_tokens": 3749929.0,
|
| 364 |
+
"step": 1550
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"entropy": 0.37067714661359785,
|
| 368 |
+
"epoch": 4.1558441558441555,
|
| 369 |
+
"grad_norm": 0.7673031687736511,
|
| 370 |
+
"learning_rate": 0.00021460118171878076,
|
| 371 |
+
"loss": 0.295870304107666,
|
| 372 |
+
"mean_token_accuracy": 0.9020969843864441,
|
| 373 |
+
"num_tokens": 3871403.0,
|
| 374 |
+
"step": 1600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"entropy": 0.37246827483177186,
|
| 378 |
+
"epoch": 4.285714285714286,
|
| 379 |
+
"grad_norm": 0.64629727602005,
|
| 380 |
+
"learning_rate": 0.000208565233183028,
|
| 381 |
+
"loss": 0.29844835281372073,
|
| 382 |
+
"mean_token_accuracy": 0.901744744181633,
|
| 383 |
+
"num_tokens": 3990410.0,
|
| 384 |
+
"step": 1650
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"entropy": 0.37455891370773314,
|
| 388 |
+
"epoch": 4.415584415584416,
|
| 389 |
+
"grad_norm": 0.6829578280448914,
|
| 390 |
+
"learning_rate": 0.00020240421614516274,
|
| 391 |
+
"loss": 0.30404550552368165,
|
| 392 |
+
"mean_token_accuracy": 0.9000005573034286,
|
| 393 |
+
"num_tokens": 4107377.0,
|
| 394 |
+
"step": 1700
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"entropy": 0.37828688144683836,
|
| 398 |
+
"epoch": 4.545454545454545,
|
| 399 |
+
"grad_norm": 0.6125279664993286,
|
| 400 |
+
"learning_rate": 0.0001961307899522958,
|
| 401 |
+
"loss": 0.30663524627685546,
|
| 402 |
+
"mean_token_accuracy": 0.8985623228549957,
|
| 403 |
+
"num_tokens": 4225238.0,
|
| 404 |
+
"step": 1750
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"entropy": 0.375451121032238,
|
| 408 |
+
"epoch": 4.675324675324675,
|
| 409 |
+
"grad_norm": 0.6192310452461243,
|
| 410 |
+
"learning_rate": 0.00018975784492420103,
|
| 411 |
+
"loss": 0.3078347396850586,
|
| 412 |
+
"mean_token_accuracy": 0.8998477959632873,
|
| 413 |
+
"num_tokens": 4348229.0,
|
| 414 |
+
"step": 1800
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"entropy": 0.3755231860280037,
|
| 418 |
+
"epoch": 4.805194805194805,
|
| 419 |
+
"grad_norm": 0.7531238794326782,
|
| 420 |
+
"learning_rate": 0.0001832984758669361,
|
| 421 |
+
"loss": 0.3057806777954102,
|
| 422 |
+
"mean_token_accuracy": 0.8995966756343842,
|
| 423 |
+
"num_tokens": 4471337.0,
|
| 424 |
+
"step": 1850
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"entropy": 0.3791221937537193,
|
| 428 |
+
"epoch": 4.935064935064935,
|
| 429 |
+
"grad_norm": 0.7267350554466248,
|
| 430 |
+
"learning_rate": 0.00017676595516629556,
|
| 431 |
+
"loss": 0.3108745002746582,
|
| 432 |
+
"mean_token_accuracy": 0.8971030461788178,
|
| 433 |
+
"num_tokens": 4596516.0,
|
| 434 |
+
"step": 1900
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 5.0,
|
| 438 |
+
"eval_entropy": 0.47880522749171806,
|
| 439 |
+
"eval_loss": 0.6903005242347717,
|
| 440 |
+
"eval_mean_token_accuracy": 0.8205848932266235,
|
| 441 |
+
"eval_num_tokens": 4655435.0,
|
| 442 |
+
"eval_runtime": 107.2115,
|
| 443 |
+
"eval_samples_per_second": 15.455,
|
| 444 |
+
"eval_steps_per_second": 1.94,
|
| 445 |
+
"step": 1925
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"entropy": 0.325536966919899,
|
| 449 |
+
"epoch": 5.064935064935065,
|
| 450 |
+
"grad_norm": 0.5973520874977112,
|
| 451 |
+
"learning_rate": 0.00017017370551638175,
|
| 452 |
+
"loss": 0.2537745094299316,
|
| 453 |
+
"mean_token_accuracy": 0.9170269852876664,
|
| 454 |
+
"num_tokens": 4720113.0,
|
| 455 |
+
"step": 1950
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"entropy": 0.2805623610317707,
|
| 459 |
+
"epoch": 5.194805194805195,
|
| 460 |
+
"grad_norm": 0.8208709359169006,
|
| 461 |
+
"learning_rate": 0.00016353527233932972,
|
| 462 |
+
"loss": 0.20699060440063477,
|
| 463 |
+
"mean_token_accuracy": 0.9297245645523071,
|
| 464 |
+
"num_tokens": 4842234.0,
|
| 465 |
+
"step": 2000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"entropy": 0.2951572193205357,
|
| 469 |
+
"epoch": 5.324675324675325,
|
| 470 |
+
"grad_norm": 0.624740481376648,
|
| 471 |
+
"learning_rate": 0.0001568642959528572,
|
| 472 |
+
"loss": 0.21564756393432616,
|
| 473 |
+
"mean_token_accuracy": 0.9271520495414733,
|
| 474 |
+
"num_tokens": 4959991.0,
|
| 475 |
+
"step": 2050
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"entropy": 0.29860043823719024,
|
| 479 |
+
"epoch": 5.454545454545454,
|
| 480 |
+
"grad_norm": 0.8418864607810974,
|
| 481 |
+
"learning_rate": 0.00015017448354282757,
|
| 482 |
+
"loss": 0.2190338897705078,
|
| 483 |
+
"mean_token_accuracy": 0.9261587560176849,
|
| 484 |
+
"num_tokens": 5082208.0,
|
| 485 |
+
"step": 2100
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"entropy": 0.2909143240749836,
|
| 489 |
+
"epoch": 5.584415584415584,
|
| 490 |
+
"grad_norm": 0.7306669354438782,
|
| 491 |
+
"learning_rate": 0.00014347958099841522,
|
| 492 |
+
"loss": 0.21448070526123048,
|
| 493 |
+
"mean_token_accuracy": 0.926868360042572,
|
| 494 |
+
"num_tokens": 5199699.0,
|
| 495 |
+
"step": 2150
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"entropy": 0.2885631823539734,
|
| 499 |
+
"epoch": 5.714285714285714,
|
| 500 |
+
"grad_norm": 0.7255174517631531,
|
| 501 |
+
"learning_rate": 0.0001367933446677463,
|
| 502 |
+
"loss": 0.21533376693725587,
|
| 503 |
+
"mean_token_accuracy": 0.9273367804288865,
|
| 504 |
+
"num_tokens": 5320501.0,
|
| 505 |
+
"step": 2200
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"entropy": 0.28939690127968787,
|
| 509 |
+
"epoch": 5.8441558441558445,
|
| 510 |
+
"grad_norm": 0.7074116468429565,
|
| 511 |
+
"learning_rate": 0.00013012951309204776,
|
| 512 |
+
"loss": 0.21616615295410158,
|
| 513 |
+
"mean_token_accuracy": 0.9268639695644378,
|
| 514 |
+
"num_tokens": 5442291.0,
|
| 515 |
+
"step": 2250
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"entropy": 0.29287345737218856,
|
| 519 |
+
"epoch": 5.974025974025974,
|
| 520 |
+
"grad_norm": 0.8009970188140869,
|
| 521 |
+
"learning_rate": 0.00012350177877638605,
|
| 522 |
+
"loss": 0.21827854156494142,
|
| 523 |
+
"mean_token_accuracy": 0.926282970905304,
|
| 524 |
+
"num_tokens": 5560531.0,
|
| 525 |
+
"step": 2300
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 6.0,
|
| 529 |
+
"eval_entropy": 0.42221833765506744,
|
| 530 |
+
"eval_loss": 0.7726835608482361,
|
| 531 |
+
"eval_mean_token_accuracy": 0.814933180809021,
|
| 532 |
+
"eval_num_tokens": 5586522.0,
|
| 533 |
+
"eval_runtime": 106.3715,
|
| 534 |
+
"eval_samples_per_second": 15.577,
|
| 535 |
+
"eval_steps_per_second": 1.955,
|
| 536 |
+
"step": 2310
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"entropy": 0.23905221119523049,
|
| 540 |
+
"epoch": 6.103896103896104,
|
| 541 |
+
"grad_norm": 0.7689157128334045,
|
| 542 |
+
"learning_rate": 0.0001169237600549981,
|
| 543 |
+
"loss": 0.15075304985046387,
|
| 544 |
+
"mean_token_accuracy": 0.9464442139863968,
|
| 545 |
+
"num_tokens": 5682578.0,
|
| 546 |
+
"step": 2350
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"entropy": 0.2028607265651226,
|
| 550 |
+
"epoch": 6.233766233766234,
|
| 551 |
+
"grad_norm": 0.5387632250785828,
|
| 552 |
+
"learning_rate": 0.00011040897310902461,
|
| 553 |
+
"loss": 0.13421324729919434,
|
| 554 |
+
"mean_token_accuracy": 0.9551875954866409,
|
| 555 |
+
"num_tokens": 5803409.0,
|
| 556 |
+
"step": 2400
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"entropy": 0.20566919729113578,
|
| 560 |
+
"epoch": 6.363636363636363,
|
| 561 |
+
"grad_norm": 0.6590266227722168,
|
| 562 |
+
"learning_rate": 0.00010397080419414323,
|
| 563 |
+
"loss": 0.1351051139831543,
|
| 564 |
+
"mean_token_accuracy": 0.9552580755949021,
|
| 565 |
+
"num_tokens": 5927439.0,
|
| 566 |
+
"step": 2450
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"entropy": 0.20123363941907882,
|
| 570 |
+
"epoch": 6.4935064935064934,
|
| 571 |
+
"grad_norm": 0.7304044961929321,
|
| 572 |
+
"learning_rate": 9.762248213516496e-05,
|
| 573 |
+
"loss": 0.1317083740234375,
|
| 574 |
+
"mean_token_accuracy": 0.9555035126209259,
|
| 575 |
+
"num_tokens": 6052633.0,
|
| 576 |
+
"step": 2500
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"entropy": 0.2167628873884678,
|
| 580 |
+
"epoch": 6.623376623376624,
|
| 581 |
+
"grad_norm": 0.9369059801101685,
|
| 582 |
+
"learning_rate": 9.137705114411241e-05,
|
| 583 |
+
"loss": 0.1422165298461914,
|
| 584 |
+
"mean_token_accuracy": 0.9518895560503006,
|
| 585 |
+
"num_tokens": 6167503.0,
|
| 586 |
+
"step": 2550
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"entropy": 0.2181946974992752,
|
| 590 |
+
"epoch": 6.753246753246753,
|
| 591 |
+
"grad_norm": 0.8891282081604004,
|
| 592 |
+
"learning_rate": 8.524734401763032e-05,
|
| 593 |
+
"loss": 0.14409255027770995,
|
| 594 |
+
"mean_token_accuracy": 0.9519028991460801,
|
| 595 |
+
"num_tokens": 6284023.0,
|
| 596 |
+
"step": 2600
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"entropy": 0.21032980993390082,
|
| 600 |
+
"epoch": 6.883116883116883,
|
| 601 |
+
"grad_norm": 0.6714637875556946,
|
| 602 |
+
"learning_rate": 7.924595576880276e-05,
|
| 603 |
+
"loss": 0.1382604694366455,
|
| 604 |
+
"mean_token_accuracy": 0.95325155377388,
|
| 605 |
+
"num_tokens": 6408327.0,
|
| 606 |
+
"step": 2650
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 7.0,
|
| 610 |
+
"eval_entropy": 0.36334023767938983,
|
| 611 |
+
"eval_loss": 0.8811500668525696,
|
| 612 |
+
"eval_mean_token_accuracy": 0.8139389048402126,
|
| 613 |
+
"eval_num_tokens": 6517609.0,
|
| 614 |
+
"eval_runtime": 107.2218,
|
| 615 |
+
"eval_samples_per_second": 15.454,
|
| 616 |
+
"eval_steps_per_second": 1.94,
|
| 617 |
+
"step": 2695
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"entropy": 0.19888876721262932,
|
| 621 |
+
"epoch": 7.012987012987013,
|
| 622 |
+
"grad_norm": 0.5274959206581116,
|
| 623 |
+
"learning_rate": 7.338521774755479e-05,
|
| 624 |
+
"loss": 0.12947993278503417,
|
| 625 |
+
"mean_token_accuracy": 0.9572676807641983,
|
| 626 |
+
"num_tokens": 6530430.0,
|
| 627 |
+
"step": 2700
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"entropy": 0.1597208461165428,
|
| 631 |
+
"epoch": 7.142857142857143,
|
| 632 |
+
"grad_norm": 0.4715121388435364,
|
| 633 |
+
"learning_rate": 6.767717230281708e-05,
|
| 634 |
+
"loss": 0.08882388114929199,
|
| 635 |
+
"mean_token_accuracy": 0.9716670286655426,
|
| 636 |
+
"num_tokens": 6648623.0,
|
| 637 |
+
"step": 2750
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"entropy": 0.15440757133066654,
|
| 641 |
+
"epoch": 7.2727272727272725,
|
| 642 |
+
"grad_norm": 0.42084604501724243,
|
| 643 |
+
"learning_rate": 6.213354803851401e-05,
|
| 644 |
+
"loss": 0.08850942611694336,
|
| 645 |
+
"mean_token_accuracy": 0.9719003230333328,
|
| 646 |
+
"num_tokens": 6768614.0,
|
| 647 |
+
"step": 2800
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"entropy": 0.1516306409984827,
|
| 651 |
+
"epoch": 7.402597402597403,
|
| 652 |
+
"grad_norm": 0.5749953985214233,
|
| 653 |
+
"learning_rate": 5.6765735714220424e-05,
|
| 654 |
+
"loss": 0.08566269874572754,
|
| 655 |
+
"mean_token_accuracy": 0.9719378662109375,
|
| 656 |
+
"num_tokens": 6892420.0,
|
| 657 |
+
"step": 2850
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"entropy": 0.1592805414646864,
|
| 661 |
+
"epoch": 7.532467532467533,
|
| 662 |
+
"grad_norm": 0.7836453318595886,
|
| 663 |
+
"learning_rate": 5.158476484000283e-05,
|
| 664 |
+
"loss": 0.09052552223205566,
|
| 665 |
+
"mean_token_accuracy": 0.9701271635293961,
|
| 666 |
+
"num_tokens": 7009857.0,
|
| 667 |
+
"step": 2900
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"entropy": 0.15554923228919507,
|
| 671 |
+
"epoch": 7.662337662337662,
|
| 672 |
+
"grad_norm": 0.5220458507537842,
|
| 673 |
+
"learning_rate": 4.6601281013538485e-05,
|
| 674 |
+
"loss": 0.08924313545227051,
|
| 675 |
+
"mean_token_accuracy": 0.9713792878389359,
|
| 676 |
+
"num_tokens": 7132184.0,
|
| 677 |
+
"step": 2950
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"entropy": 0.15688340798020362,
|
| 681 |
+
"epoch": 7.792207792207792,
|
| 682 |
+
"grad_norm": 0.5455254316329956,
|
| 683 |
+
"learning_rate": 4.182552404607813e-05,
|
| 684 |
+
"loss": 0.08741535186767578,
|
| 685 |
+
"mean_token_accuracy": 0.9710536366701126,
|
| 686 |
+
"num_tokens": 7250668.0,
|
| 687 |
+
"step": 3000
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"entropy": 0.15722099043428897,
|
| 691 |
+
"epoch": 7.922077922077922,
|
| 692 |
+
"grad_norm": 0.7133240699768066,
|
| 693 |
+
"learning_rate": 3.7267306922198405e-05,
|
| 694 |
+
"loss": 0.08726611137390136,
|
| 695 |
+
"mean_token_accuracy": 0.9708961689472199,
|
| 696 |
+
"num_tokens": 7373911.0,
|
| 697 |
+
"step": 3050
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 8.0,
|
| 701 |
+
"eval_entropy": 0.3186919501481148,
|
| 702 |
+
"eval_loss": 1.0071876049041748,
|
| 703 |
+
"eval_mean_token_accuracy": 0.8123214006997072,
|
| 704 |
+
"eval_num_tokens": 7448696.0,
|
| 705 |
+
"eval_runtime": 107.0969,
|
| 706 |
+
"eval_samples_per_second": 15.472,
|
| 707 |
+
"eval_steps_per_second": 1.942,
|
| 708 |
+
"step": 3080
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"entropy": 0.14195461072027682,
|
| 712 |
+
"epoch": 8.051948051948052,
|
| 713 |
+
"grad_norm": 0.26776430010795593,
|
| 714 |
+
"learning_rate": 3.2935995636575635e-05,
|
| 715 |
+
"loss": 0.0777656078338623,
|
| 716 |
+
"mean_token_accuracy": 0.97492840051651,
|
| 717 |
+
"num_tokens": 7497025.0,
|
| 718 |
+
"step": 3100
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"entropy": 0.13433482259511947,
|
| 722 |
+
"epoch": 8.181818181818182,
|
| 723 |
+
"grad_norm": 0.3423265516757965,
|
| 724 |
+
"learning_rate": 2.88404899492126e-05,
|
| 725 |
+
"loss": 0.06844220638275146,
|
| 726 |
+
"mean_token_accuracy": 0.9771447205543518,
|
| 727 |
+
"num_tokens": 7615828.0,
|
| 728 |
+
"step": 3150
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"entropy": 0.13602125875651835,
|
| 732 |
+
"epoch": 8.311688311688311,
|
| 733 |
+
"grad_norm": 0.3100737929344177,
|
| 734 |
+
"learning_rate": 2.498920509866034e-05,
|
| 735 |
+
"loss": 0.06934462547302246,
|
| 736 |
+
"mean_token_accuracy": 0.9767152363061905,
|
| 737 |
+
"num_tokens": 7734498.0,
|
| 738 |
+
"step": 3200
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"entropy": 0.1314435251057148,
|
| 742 |
+
"epoch": 8.441558441558442,
|
| 743 |
+
"grad_norm": 0.30841144919395447,
|
| 744 |
+
"learning_rate": 2.1390054510810508e-05,
|
| 745 |
+
"loss": 0.06751186847686767,
|
| 746 |
+
"mean_token_accuracy": 0.9776975494623185,
|
| 747 |
+
"num_tokens": 7855780.0,
|
| 748 |
+
"step": 3250
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"entropy": 0.13987424969673157,
|
| 752 |
+
"epoch": 8.571428571428571,
|
| 753 |
+
"grad_norm": 0.7126380205154419,
|
| 754 |
+
"learning_rate": 1.805043353878673e-05,
|
| 755 |
+
"loss": 0.07370821952819824,
|
| 756 |
+
"mean_token_accuracy": 0.9760742300748825,
|
| 757 |
+
"num_tokens": 7968890.0,
|
| 758 |
+
"step": 3300
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"entropy": 0.127069203928113,
|
| 762 |
+
"epoch": 8.7012987012987,
|
| 763 |
+
"grad_norm": 0.3540371358394623,
|
| 764 |
+
"learning_rate": 1.4977204267346069e-05,
|
| 765 |
+
"loss": 0.06683775424957275,
|
| 766 |
+
"mean_token_accuracy": 0.9786590534448624,
|
| 767 |
+
"num_tokens": 8094439.0,
|
| 768 |
+
"step": 3350
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"entropy": 0.12823721051216125,
|
| 772 |
+
"epoch": 8.831168831168831,
|
| 773 |
+
"grad_norm": 0.5126563906669617,
|
| 774 |
+
"learning_rate": 1.2176681413013285e-05,
|
| 775 |
+
"loss": 0.06561075210571289,
|
| 776 |
+
"mean_token_accuracy": 0.9777718102931976,
|
| 777 |
+
"num_tokens": 8219578.0,
|
| 778 |
+
"step": 3400
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"entropy": 0.1255523782223463,
|
| 782 |
+
"epoch": 8.96103896103896,
|
| 783 |
+
"grad_norm": 0.44230973720550537,
|
| 784 |
+
"learning_rate": 9.654619348919862e-06,
|
| 785 |
+
"loss": 0.06667422771453857,
|
| 786 |
+
"mean_token_accuracy": 0.9777981823682785,
|
| 787 |
+
"num_tokens": 8345441.0,
|
| 788 |
+
"step": 3450
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 9.0,
|
| 792 |
+
"eval_entropy": 0.2925072068778368,
|
| 793 |
+
"eval_loss": 1.136028528213501,
|
| 794 |
+
"eval_mean_token_accuracy": 0.8110573165691816,
|
| 795 |
+
"eval_num_tokens": 8379783.0,
|
| 796 |
+
"eval_runtime": 106.7187,
|
| 797 |
+
"eval_samples_per_second": 15.527,
|
| 798 |
+
"eval_steps_per_second": 1.949,
|
| 799 |
+
"step": 3465
|
| 800 |
+
}
|
| 801 |
+
],
|
| 802 |
+
"logging_steps": 50,
|
| 803 |
+
"max_steps": 3850,
|
| 804 |
+
"num_input_tokens_seen": 0,
|
| 805 |
+
"num_train_epochs": 10,
|
| 806 |
+
"save_steps": 500,
|
| 807 |
+
"stateful_callbacks": {
|
| 808 |
+
"TrainerControl": {
|
| 809 |
+
"args": {
|
| 810 |
+
"should_epoch_stop": false,
|
| 811 |
+
"should_evaluate": false,
|
| 812 |
+
"should_log": false,
|
| 813 |
+
"should_save": true,
|
| 814 |
+
"should_training_stop": false
|
| 815 |
+
},
|
| 816 |
+
"attributes": {}
|
| 817 |
+
}
|
| 818 |
+
},
|
| 819 |
+
"total_flos": 9.825626741380116e+17,
|
| 820 |
+
"train_batch_size": 8,
|
| 821 |
+
"trial_name": null,
|
| 822 |
+
"trial_params": null
|
| 823 |
+
}
|
DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-385/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3.5-9B-Base
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen3.5-9B-Base
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.18.1
|
DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-385/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3.5-9B-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 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 32,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.06320962833718659,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.1",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 16,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"q_proj",
|
| 33 |
+
"k_proj",
|
| 34 |
+
"v_proj",
|
| 35 |
+
"gate_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
+
"o_proj",
|
| 38 |
+
"up_proj"
|
| 39 |
+
],
|
| 40 |
+
"target_parameters": null,
|
| 41 |
+
"task_type": "CAUSAL_LM",
|
| 42 |
+
"trainable_token_indices": null,
|
| 43 |
+
"use_dora": false,
|
| 44 |
+
"use_qalora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-385/chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-385/tokenizer_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|endoftext|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"model_max_length": 262144,
|
| 14 |
+
"model_specific_special_tokens": {
|
| 15 |
+
"audio_bos_token": "<|audio_start|>",
|
| 16 |
+
"audio_eos_token": "<|audio_end|>",
|
| 17 |
+
"audio_token": "<|audio_pad|>",
|
| 18 |
+
"image_token": "<|image_pad|>",
|
| 19 |
+
"video_token": "<|video_pad|>",
|
| 20 |
+
"vision_bos_token": "<|vision_start|>",
|
| 21 |
+
"vision_eos_token": "<|vision_end|>"
|
| 22 |
+
},
|
| 23 |
+
"pad_token": "<|endoftext|>",
|
| 24 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 25 |
+
"split_special_tokens": false,
|
| 26 |
+
"tokenizer_class": "TokenizersBackend",
|
| 27 |
+
"unk_token": null,
|
| 28 |
+
"video_token": "<|video_pad|>",
|
| 29 |
+
"vision_bos_token": "<|vision_start|>",
|
| 30 |
+
"vision_eos_token": "<|vision_end|>"
|
| 31 |
+
}
|
DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-385/trainer_state.json
ADDED
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 385,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.7529579949378968,
|
| 14 |
+
"epoch": 0.12987012987012986,
|
| 15 |
+
"grad_norm": 1.0845375061035156,
|
| 16 |
+
"learning_rate": 3.759565870277177e-05,
|
| 17 |
+
"loss": 1.6464532470703126,
|
| 18 |
+
"mean_token_accuracy": 0.6610959130525589,
|
| 19 |
+
"num_tokens": 127115.0,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 0.8384856134653091,
|
| 24 |
+
"epoch": 0.2597402597402597,
|
| 25 |
+
"grad_norm": 0.787804126739502,
|
| 26 |
+
"learning_rate": 7.595857574641644e-05,
|
| 27 |
+
"loss": 0.7860373687744141,
|
| 28 |
+
"mean_token_accuracy": 0.7873306655883789,
|
| 29 |
+
"num_tokens": 251796.0,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 0.7570279932022095,
|
| 34 |
+
"epoch": 0.38961038961038963,
|
| 35 |
+
"grad_norm": 0.8686555624008179,
|
| 36 |
+
"learning_rate": 0.00011432149279006112,
|
| 37 |
+
"loss": 0.6997585296630859,
|
| 38 |
+
"mean_token_accuracy": 0.8050823694467545,
|
| 39 |
+
"num_tokens": 366505.0,
|
| 40 |
+
"step": 150
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.7074448710680008,
|
| 44 |
+
"epoch": 0.5194805194805194,
|
| 45 |
+
"grad_norm": 0.641474723815918,
|
| 46 |
+
"learning_rate": 0.00015268440983370578,
|
| 47 |
+
"loss": 0.6549726104736329,
|
| 48 |
+
"mean_token_accuracy": 0.812009590268135,
|
| 49 |
+
"num_tokens": 493150.0,
|
| 50 |
+
"step": 200
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.7119272118806839,
|
| 54 |
+
"epoch": 0.6493506493506493,
|
| 55 |
+
"grad_norm": 0.6778020858764648,
|
| 56 |
+
"learning_rate": 0.00019104732687735045,
|
| 57 |
+
"loss": 0.6522830963134766,
|
| 58 |
+
"mean_token_accuracy": 0.8144695377349853,
|
| 59 |
+
"num_tokens": 607197.0,
|
| 60 |
+
"step": 250
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.6957281070947647,
|
| 64 |
+
"epoch": 0.7792207792207793,
|
| 65 |
+
"grad_norm": 0.5819384455680847,
|
| 66 |
+
"learning_rate": 0.00022941024392099515,
|
| 67 |
+
"loss": 0.6377084732055665,
|
| 68 |
+
"mean_token_accuracy": 0.817834352850914,
|
| 69 |
+
"num_tokens": 726579.0,
|
| 70 |
+
"step": 300
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 0.6780185508728027,
|
| 74 |
+
"epoch": 0.9090909090909091,
|
| 75 |
+
"grad_norm": 0.45764321088790894,
|
| 76 |
+
"learning_rate": 0.0002677731609646398,
|
| 77 |
+
"loss": 0.6206952285766602,
|
| 78 |
+
"mean_token_accuracy": 0.8230367678403855,
|
| 79 |
+
"num_tokens": 848944.0,
|
| 80 |
+
"step": 350
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.0,
|
| 84 |
+
"eval_entropy": 0.6696528858290269,
|
| 85 |
+
"eval_loss": 0.6696833372116089,
|
| 86 |
+
"eval_mean_token_accuracy": 0.807859004690097,
|
| 87 |
+
"eval_num_tokens": 931087.0,
|
| 88 |
+
"eval_runtime": 107.6403,
|
| 89 |
+
"eval_samples_per_second": 15.394,
|
| 90 |
+
"eval_steps_per_second": 1.932,
|
| 91 |
+
"step": 385
|
| 92 |
+
}
|
| 93 |
+
],
|
| 94 |
+
"logging_steps": 50,
|
| 95 |
+
"max_steps": 3850,
|
| 96 |
+
"num_input_tokens_seen": 0,
|
| 97 |
+
"num_train_epochs": 10,
|
| 98 |
+
"save_steps": 500,
|
| 99 |
+
"stateful_callbacks": {
|
| 100 |
+
"TrainerControl": {
|
| 101 |
+
"args": {
|
| 102 |
+
"should_epoch_stop": false,
|
| 103 |
+
"should_evaluate": false,
|
| 104 |
+
"should_log": false,
|
| 105 |
+
"should_save": true,
|
| 106 |
+
"should_training_stop": false
|
| 107 |
+
},
|
| 108 |
+
"attributes": {}
|
| 109 |
+
}
|
| 110 |
+
},
|
| 111 |
+
"total_flos": 1.0891861389792768e+17,
|
| 112 |
+
"train_batch_size": 8,
|
| 113 |
+
"trial_name": null,
|
| 114 |
+
"trial_params": null
|
| 115 |
+
}
|
DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3850/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3.5-9B-Base
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen3.5-9B-Base
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.18.1
|
DBCA_original_Estonian/Qwen3.5-9B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3850/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3.5-9B-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 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 32,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.06320962833718659,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.1",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 16,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"q_proj",
|
| 33 |
+
"k_proj",
|
| 34 |
+
"v_proj",
|
| 35 |
+
"gate_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
+
"o_proj",
|
| 38 |
+
"up_proj"
|
| 39 |
+
],
|
| 40 |
+
"target_parameters": null,
|
| 41 |
+
"task_type": "CAUSAL_LM",
|
| 42 |
+
"trainable_token_indices": null,
|
| 43 |
+
"use_dora": false,
|
| 44 |
+
"use_qalora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|