System: Prune old checkpoint folder checkpoint-7 to save space
Browse files
checkpoint-7/config.json
DELETED
|
@@ -1,19 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"FastPlus125mForCausalLM"
|
| 4 |
-
],
|
| 5 |
-
"dtype": "float32",
|
| 6 |
-
"hidden_size": 768,
|
| 7 |
-
"initializer_range": 0.02,
|
| 8 |
-
"intermediate_size": 2048,
|
| 9 |
-
"kd_alpha": 0.4,
|
| 10 |
-
"kd_temperature": 2.5,
|
| 11 |
-
"max_position_embeddings": 512,
|
| 12 |
-
"model_type": "fastplus_125m",
|
| 13 |
-
"num_attention_heads": 12,
|
| 14 |
-
"num_hidden_layers": 16,
|
| 15 |
-
"tie_word_embeddings": true,
|
| 16 |
-
"transformers_version": "5.12.0",
|
| 17 |
-
"use_cache": false,
|
| 18 |
-
"vocab_size": 1792
|
| 19 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-7/generation_config.json
DELETED
|
@@ -1,6 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"output_attentions": false,
|
| 4 |
-
"output_hidden_states": false,
|
| 5 |
-
"transformers_version": "5.12.0"
|
| 6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-7/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-7/tokenizer_config.json
DELETED
|
@@ -1,13 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"backend": "tokenizers",
|
| 3 |
-
"bos_token": "<s>",
|
| 4 |
-
"eos_token": "</s>",
|
| 5 |
-
"extra_special_tokens": [
|
| 6 |
-
"<|user|>",
|
| 7 |
-
"<|assistant|>"
|
| 8 |
-
],
|
| 9 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 10 |
-
"pad_token": "<pad>",
|
| 11 |
-
"tokenizer_class": "TokenizersBackend",
|
| 12 |
-
"unk_token": "<unk>"
|
| 13 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-7/trainer_state.json
DELETED
|
@@ -1,33 +0,0 @@
|
|
| 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": 7,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [],
|
| 12 |
-
"logging_steps": 10,
|
| 13 |
-
"max_steps": 7,
|
| 14 |
-
"num_input_tokens_seen": 0,
|
| 15 |
-
"num_train_epochs": 1,
|
| 16 |
-
"save_steps": 200,
|
| 17 |
-
"stateful_callbacks": {
|
| 18 |
-
"TrainerControl": {
|
| 19 |
-
"args": {
|
| 20 |
-
"should_epoch_stop": false,
|
| 21 |
-
"should_evaluate": false,
|
| 22 |
-
"should_log": false,
|
| 23 |
-
"should_save": true,
|
| 24 |
-
"should_training_stop": true
|
| 25 |
-
},
|
| 26 |
-
"attributes": {}
|
| 27 |
-
}
|
| 28 |
-
},
|
| 29 |
-
"total_flos": 59773076241408.0,
|
| 30 |
-
"train_batch_size": 12,
|
| 31 |
-
"trial_name": null,
|
| 32 |
-
"trial_params": null
|
| 33 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|