Upload folder using huggingface_hub
Browse files
slots/0/checkpoint-239/config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-239/trainer_state.json
ADDED
|
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.015510642474823599,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 239,
|
| 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 |
+
"epoch": 0.005191846853497439,
|
| 42 |
+
"grad_norm": 34.96514129638672,
|
| 43 |
+
"learning_rate": 4.999948117339598e-05,
|
| 44 |
+
"loss": 305.076220703125,
|
| 45 |
+
"step": 80
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.006489808566871798,
|
| 49 |
+
"grad_norm": 37.357093811035156,
|
| 50 |
+
"learning_rate": 4.9999185225202174e-05,
|
| 51 |
+
"loss": 298.5962890625,
|
| 52 |
+
"step": 100
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.007787770280246158,
|
| 56 |
+
"grad_norm": 43.13069152832031,
|
| 57 |
+
"learning_rate": 4.999882277338722e-05,
|
| 58 |
+
"loss": 291.7892578125,
|
| 59 |
+
"step": 120
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.009085731993620519,
|
| 63 |
+
"grad_norm": 43.607086181640625,
|
| 64 |
+
"learning_rate": 4.9998393818915336e-05,
|
| 65 |
+
"loss": 283.4513671875,
|
| 66 |
+
"step": 140
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.010383693706994879,
|
| 70 |
+
"grad_norm": 45.93403625488281,
|
| 71 |
+
"learning_rate": 4.999789836292764e-05,
|
| 72 |
+
"loss": 279.384619140625,
|
| 73 |
+
"step": 160
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.011681655420369237,
|
| 77 |
+
"grad_norm": 42.242095947265625,
|
| 78 |
+
"learning_rate": 4.9997336406742147e-05,
|
| 79 |
+
"loss": 272.4620849609375,
|
| 80 |
+
"step": 180
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.012979617133743597,
|
| 84 |
+
"grad_norm": 45.98979187011719,
|
| 85 |
+
"learning_rate": 4.99967079518538e-05,
|
| 86 |
+
"loss": 273.69755859375,
|
| 87 |
+
"step": 200
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.014277578847117956,
|
| 91 |
+
"grad_norm": 43.22636413574219,
|
| 92 |
+
"learning_rate": 4.999601299993443e-05,
|
| 93 |
+
"loss": 269.176513671875,
|
| 94 |
+
"step": 220
|
| 95 |
+
}
|
| 96 |
+
],
|
| 97 |
+
"logging_steps": 20,
|
| 98 |
+
"max_steps": 38523,
|
| 99 |
+
"num_input_tokens_seen": 0,
|
| 100 |
+
"num_train_epochs": 3,
|
| 101 |
+
"save_steps": 1000000000,
|
| 102 |
+
"stateful_callbacks": {
|
| 103 |
+
"TrainerControl": {
|
| 104 |
+
"args": {
|
| 105 |
+
"should_epoch_stop": false,
|
| 106 |
+
"should_evaluate": false,
|
| 107 |
+
"should_log": false,
|
| 108 |
+
"should_save": true,
|
| 109 |
+
"should_training_stop": false
|
| 110 |
+
},
|
| 111 |
+
"attributes": {}
|
| 112 |
+
}
|
| 113 |
+
},
|
| 114 |
+
"total_flos": 247607382251520.0,
|
| 115 |
+
"train_batch_size": 1,
|
| 116 |
+
"trial_name": null,
|
| 117 |
+
"trial_params": null
|
| 118 |
+
}
|