prune 1 old checkpoints
Browse files
slots/0/checkpoint-67/config.json
DELETED
|
@@ -1,24 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"MinixForCausalLM"
|
| 4 |
-
],
|
| 5 |
-
"attention_dropout": 0.0,
|
| 6 |
-
"dtype": "float32",
|
| 7 |
-
"hidden_dropout": 0.0,
|
| 8 |
-
"hidden_size": 768,
|
| 9 |
-
"initializer_range": 0.02,
|
| 10 |
-
"intermediate_size": 3072,
|
| 11 |
-
"max_position_embeddings": 128,
|
| 12 |
-
"model_type": "minix",
|
| 13 |
-
"neftune_alpha": 0.0,
|
| 14 |
-
"num_attention_heads": 12,
|
| 15 |
-
"num_hidden_layers": 1,
|
| 16 |
-
"num_key_value_heads": 3,
|
| 17 |
-
"qk_norm": true,
|
| 18 |
-
"rezero_init": 1.0,
|
| 19 |
-
"rms_norm_eps": 1e-06,
|
| 20 |
-
"rope_theta": 10000.0,
|
| 21 |
-
"transformers_version": "5.0.0",
|
| 22 |
-
"use_cache": false,
|
| 23 |
-
"vocab_size": 32000
|
| 24 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
slots/0/checkpoint-67/trainer_state.json
DELETED
|
@@ -1,62 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": null,
|
| 3 |
-
"best_metric": null,
|
| 4 |
-
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.004348171739804105,
|
| 6 |
-
"eval_steps": 500,
|
| 7 |
-
"global_step": 67,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 6.489808566871798e-05,
|
| 14 |
-
"grad_norm": 109.46859741210938,
|
| 15 |
-
"learning_rate": 5e-05,
|
| 16 |
-
"loss": 421.4660949707031,
|
| 17 |
-
"step": 1
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 0.0012979617133743598,
|
| 21 |
-
"grad_norm": 88.54906463623047,
|
| 22 |
-
"learning_rate": 4.999996998926224e-05,
|
| 23 |
-
"loss": 390.39101048519734,
|
| 24 |
-
"step": 20
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 0.0025959234267487197,
|
| 28 |
-
"grad_norm": 60.599815368652344,
|
| 29 |
-
"learning_rate": 4.999987355594792e-05,
|
| 30 |
-
"loss": 341.1005126953125,
|
| 31 |
-
"step": 40
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 0.003893885140123079,
|
| 35 |
-
"grad_norm": 42.03083419799805,
|
| 36 |
-
"learning_rate": 4.999971061718136e-05,
|
| 37 |
-
"loss": 318.29091796875,
|
| 38 |
-
"step": 60
|
| 39 |
-
}
|
| 40 |
-
],
|
| 41 |
-
"logging_steps": 20,
|
| 42 |
-
"max_steps": 38523,
|
| 43 |
-
"num_input_tokens_seen": 0,
|
| 44 |
-
"num_train_epochs": 3,
|
| 45 |
-
"save_steps": 1000000000,
|
| 46 |
-
"stateful_callbacks": {
|
| 47 |
-
"TrainerControl": {
|
| 48 |
-
"args": {
|
| 49 |
-
"should_epoch_stop": false,
|
| 50 |
-
"should_evaluate": false,
|
| 51 |
-
"should_log": false,
|
| 52 |
-
"should_save": true,
|
| 53 |
-
"should_training_stop": false
|
| 54 |
-
},
|
| 55 |
-
"attributes": {}
|
| 56 |
-
}
|
| 57 |
-
},
|
| 58 |
-
"total_flos": 69412948162560.0,
|
| 59 |
-
"train_batch_size": 1,
|
| 60 |
-
"trial_name": null,
|
| 61 |
-
"trial_params": null
|
| 62 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|