Upload folder using huggingface_hub
Browse files- added_tokens.json +5 -0
- checkpoint-562/config.json +32 -0
- checkpoint-562/generation_config.json +7 -0
- checkpoint-562/model.safetensors +3 -0
- checkpoint-562/optimizer.pt +3 -0
- checkpoint-562/rng_state.pth +3 -0
- checkpoint-562/scheduler.pt +3 -0
- checkpoint-562/trainer_state.json +425 -0
- checkpoint-562/training_args.bin +3 -0
- config.json +32 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +44 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +69 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[BOS]": 32001,
|
| 3 |
+
"[EOS]": 32002,
|
| 4 |
+
"[PAD]": 32000
|
| 5 |
+
}
|
checkpoint-562/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "appvoid/arco",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 96,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 1536,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"max_position_embeddings": 2048,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 8,
|
| 19 |
+
"num_hidden_layers": 8,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-05,
|
| 24 |
+
"rope_scaling": null,
|
| 25 |
+
"rope_theta": 100000,
|
| 26 |
+
"sliding_window": null,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.45.1",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 32003
|
| 32 |
+
}
|
checkpoint-562/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.45.1"
|
| 7 |
+
}
|
checkpoint-562/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34f19fda47fefb05b1addcc19c5fa1b60c74409c72856c501b576dac182dda62
|
| 3 |
+
size 997345472
|
checkpoint-562/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2b7b63c561891fa85db0514a6d9ac17d9b4566e4384eee6c088971cae73827a
|
| 3 |
+
size 1994737722
|
checkpoint-562/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
|
| 3 |
+
size 14244
|
checkpoint-562/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:307dd830f51ff9de9de2039746e6431f9119496cafc6927ff8458102d191e161
|
| 3 |
+
size 1064
|
checkpoint-562/trainer_state.json
ADDED
|
@@ -0,0 +1,425 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9991111111111111,
|
| 5 |
+
"eval_steps": 2500,
|
| 6 |
+
"global_step": 562,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.017777777777777778,
|
| 13 |
+
"grad_norm": 88.875244140625,
|
| 14 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 15 |
+
"loss": 9.7267,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.035555555555555556,
|
| 20 |
+
"grad_norm": 31.958995819091797,
|
| 21 |
+
"learning_rate": 4.000000000000001e-06,
|
| 22 |
+
"loss": 5.7955,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05333333333333334,
|
| 27 |
+
"grad_norm": 5.3343024253845215,
|
| 28 |
+
"learning_rate": 6e-06,
|
| 29 |
+
"loss": 5.0347,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.07111111111111111,
|
| 34 |
+
"grad_norm": 41.579566955566406,
|
| 35 |
+
"learning_rate": 8.000000000000001e-06,
|
| 36 |
+
"loss": 4.3218,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08888888888888889,
|
| 41 |
+
"grad_norm": 10.722373008728027,
|
| 42 |
+
"learning_rate": 1e-05,
|
| 43 |
+
"loss": 3.9744,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.10666666666666667,
|
| 48 |
+
"grad_norm": 9.662172317504883,
|
| 49 |
+
"learning_rate": 1.2e-05,
|
| 50 |
+
"loss": 3.7563,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.12444444444444444,
|
| 55 |
+
"grad_norm": 28.926959991455078,
|
| 56 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 57 |
+
"loss": 4.0642,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.14222222222222222,
|
| 62 |
+
"grad_norm": 9.562807083129883,
|
| 63 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 64 |
+
"loss": 3.5177,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.16,
|
| 69 |
+
"grad_norm": 2.2154767513275146,
|
| 70 |
+
"learning_rate": 1.8e-05,
|
| 71 |
+
"loss": 3.6273,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.17777777777777778,
|
| 76 |
+
"grad_norm": 2.5517711639404297,
|
| 77 |
+
"learning_rate": 2e-05,
|
| 78 |
+
"loss": 3.4112,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.19555555555555557,
|
| 83 |
+
"grad_norm": 2.0355427265167236,
|
| 84 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 85 |
+
"loss": 3.5074,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.21333333333333335,
|
| 90 |
+
"grad_norm": 1.1960408687591553,
|
| 91 |
+
"learning_rate": 2.4e-05,
|
| 92 |
+
"loss": 3.3326,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2311111111111111,
|
| 97 |
+
"grad_norm": 1.1277498006820679,
|
| 98 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 99 |
+
"loss": 3.3374,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.24888888888888888,
|
| 104 |
+
"grad_norm": 0.8815209269523621,
|
| 105 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 106 |
+
"loss": 3.175,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.26666666666666666,
|
| 111 |
+
"grad_norm": 1.3479467630386353,
|
| 112 |
+
"learning_rate": 3e-05,
|
| 113 |
+
"loss": 2.9577,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.28444444444444444,
|
| 118 |
+
"grad_norm": 1.0421769618988037,
|
| 119 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 120 |
+
"loss": 2.9646,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.3022222222222222,
|
| 125 |
+
"grad_norm": 1.652000069618225,
|
| 126 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 127 |
+
"loss": 2.894,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.32,
|
| 132 |
+
"grad_norm": 0.7623746395111084,
|
| 133 |
+
"learning_rate": 3.6e-05,
|
| 134 |
+
"loss": 2.9097,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.3377777777777778,
|
| 139 |
+
"grad_norm": 0.8431053161621094,
|
| 140 |
+
"learning_rate": 3.8e-05,
|
| 141 |
+
"loss": 2.9105,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.35555555555555557,
|
| 146 |
+
"grad_norm": 0.5971846580505371,
|
| 147 |
+
"learning_rate": 4e-05,
|
| 148 |
+
"loss": 2.9479,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.37333333333333335,
|
| 153 |
+
"grad_norm": 1.0084749460220337,
|
| 154 |
+
"learning_rate": 4.2e-05,
|
| 155 |
+
"loss": 2.5436,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.39111111111111113,
|
| 160 |
+
"grad_norm": 0.5868157744407654,
|
| 161 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 162 |
+
"loss": 3.0776,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.4088888888888889,
|
| 167 |
+
"grad_norm": 0.6858065128326416,
|
| 168 |
+
"learning_rate": 4.600000000000001e-05,
|
| 169 |
+
"loss": 2.7455,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.4266666666666667,
|
| 174 |
+
"grad_norm": 0.6754482984542847,
|
| 175 |
+
"learning_rate": 4.8e-05,
|
| 176 |
+
"loss": 2.5998,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4444444444444444,
|
| 181 |
+
"grad_norm": 0.6398811936378479,
|
| 182 |
+
"learning_rate": 5e-05,
|
| 183 |
+
"loss": 2.9621,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.4622222222222222,
|
| 188 |
+
"grad_norm": 0.6974557638168335,
|
| 189 |
+
"learning_rate": 5.2000000000000004e-05,
|
| 190 |
+
"loss": 2.9351,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.48,
|
| 195 |
+
"grad_norm": 0.6130190491676331,
|
| 196 |
+
"learning_rate": 5.4000000000000005e-05,
|
| 197 |
+
"loss": 2.7571,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.49777777777777776,
|
| 202 |
+
"grad_norm": 0.8174580931663513,
|
| 203 |
+
"learning_rate": 5.6000000000000006e-05,
|
| 204 |
+
"loss": 2.8401,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5155555555555555,
|
| 209 |
+
"grad_norm": 0.7033889889717102,
|
| 210 |
+
"learning_rate": 5.8e-05,
|
| 211 |
+
"loss": 2.8515,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5333333333333333,
|
| 216 |
+
"grad_norm": 1.089599847793579,
|
| 217 |
+
"learning_rate": 6e-05,
|
| 218 |
+
"loss": 2.8022,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5511111111111111,
|
| 223 |
+
"grad_norm": 0.8031187057495117,
|
| 224 |
+
"learning_rate": 6.2e-05,
|
| 225 |
+
"loss": 2.966,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5688888888888889,
|
| 230 |
+
"grad_norm": 0.732790470123291,
|
| 231 |
+
"learning_rate": 6.400000000000001e-05,
|
| 232 |
+
"loss": 2.6968,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5866666666666667,
|
| 237 |
+
"grad_norm": 0.7719486951828003,
|
| 238 |
+
"learning_rate": 6.6e-05,
|
| 239 |
+
"loss": 2.4432,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.6044444444444445,
|
| 244 |
+
"grad_norm": 0.7919511198997498,
|
| 245 |
+
"learning_rate": 6.800000000000001e-05,
|
| 246 |
+
"loss": 2.8117,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.6222222222222222,
|
| 251 |
+
"grad_norm": 0.7884833216667175,
|
| 252 |
+
"learning_rate": 7e-05,
|
| 253 |
+
"loss": 2.6053,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.64,
|
| 258 |
+
"grad_norm": 0.7277636528015137,
|
| 259 |
+
"learning_rate": 7.2e-05,
|
| 260 |
+
"loss": 2.4502,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.6577777777777778,
|
| 265 |
+
"grad_norm": 0.7130594253540039,
|
| 266 |
+
"learning_rate": 7.4e-05,
|
| 267 |
+
"loss": 2.796,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6755555555555556,
|
| 272 |
+
"grad_norm": 0.62201327085495,
|
| 273 |
+
"learning_rate": 7.6e-05,
|
| 274 |
+
"loss": 2.6094,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.6933333333333334,
|
| 279 |
+
"grad_norm": 0.6539739370346069,
|
| 280 |
+
"learning_rate": 7.800000000000001e-05,
|
| 281 |
+
"loss": 2.717,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.7111111111111111,
|
| 286 |
+
"grad_norm": 0.7225100994110107,
|
| 287 |
+
"learning_rate": 8e-05,
|
| 288 |
+
"loss": 2.7048,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.7288888888888889,
|
| 293 |
+
"grad_norm": 0.6137427687644958,
|
| 294 |
+
"learning_rate": 8.2e-05,
|
| 295 |
+
"loss": 2.5289,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.7466666666666667,
|
| 300 |
+
"grad_norm": 0.582849383354187,
|
| 301 |
+
"learning_rate": 8.4e-05,
|
| 302 |
+
"loss": 2.5651,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.7644444444444445,
|
| 307 |
+
"grad_norm": 0.5719377398490906,
|
| 308 |
+
"learning_rate": 8.6e-05,
|
| 309 |
+
"loss": 2.4367,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.7822222222222223,
|
| 314 |
+
"grad_norm": 0.578987181186676,
|
| 315 |
+
"learning_rate": 8.800000000000001e-05,
|
| 316 |
+
"loss": 2.5171,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.8,
|
| 321 |
+
"grad_norm": 0.6348330974578857,
|
| 322 |
+
"learning_rate": 9e-05,
|
| 323 |
+
"loss": 2.612,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8177777777777778,
|
| 328 |
+
"grad_norm": 0.6249493360519409,
|
| 329 |
+
"learning_rate": 9.200000000000001e-05,
|
| 330 |
+
"loss": 2.5857,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.8355555555555556,
|
| 335 |
+
"grad_norm": 0.5591100454330444,
|
| 336 |
+
"learning_rate": 9.4e-05,
|
| 337 |
+
"loss": 2.5947,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.8533333333333334,
|
| 342 |
+
"grad_norm": 0.7849887609481812,
|
| 343 |
+
"learning_rate": 9.6e-05,
|
| 344 |
+
"loss": 2.7158,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.8711111111111111,
|
| 349 |
+
"grad_norm": 0.6603601574897766,
|
| 350 |
+
"learning_rate": 9.8e-05,
|
| 351 |
+
"loss": 2.654,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.8888888888888888,
|
| 356 |
+
"grad_norm": 0.7159696817398071,
|
| 357 |
+
"learning_rate": 0.0001,
|
| 358 |
+
"loss": 2.3747,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.9066666666666666,
|
| 363 |
+
"grad_norm": 0.5841464996337891,
|
| 364 |
+
"learning_rate": 8.387096774193549e-05,
|
| 365 |
+
"loss": 2.3139,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.9244444444444444,
|
| 370 |
+
"grad_norm": 0.6657692193984985,
|
| 371 |
+
"learning_rate": 6.774193548387096e-05,
|
| 372 |
+
"loss": 2.5446,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.9422222222222222,
|
| 377 |
+
"grad_norm": 0.5464931726455688,
|
| 378 |
+
"learning_rate": 5.161290322580645e-05,
|
| 379 |
+
"loss": 2.3528,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.96,
|
| 384 |
+
"grad_norm": 0.6112729907035828,
|
| 385 |
+
"learning_rate": 3.548387096774194e-05,
|
| 386 |
+
"loss": 2.2875,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.9777777777777777,
|
| 391 |
+
"grad_norm": 0.5398631691932678,
|
| 392 |
+
"learning_rate": 1.935483870967742e-05,
|
| 393 |
+
"loss": 2.3833,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.9955555555555555,
|
| 398 |
+
"grad_norm": 0.6032394766807556,
|
| 399 |
+
"learning_rate": 3.225806451612903e-06,
|
| 400 |
+
"loss": 2.353,
|
| 401 |
+
"step": 560
|
| 402 |
+
}
|
| 403 |
+
],
|
| 404 |
+
"logging_steps": 10,
|
| 405 |
+
"max_steps": 562,
|
| 406 |
+
"num_input_tokens_seen": 0,
|
| 407 |
+
"num_train_epochs": 1,
|
| 408 |
+
"save_steps": 2500,
|
| 409 |
+
"stateful_callbacks": {
|
| 410 |
+
"TrainerControl": {
|
| 411 |
+
"args": {
|
| 412 |
+
"should_epoch_stop": false,
|
| 413 |
+
"should_evaluate": false,
|
| 414 |
+
"should_log": false,
|
| 415 |
+
"should_save": true,
|
| 416 |
+
"should_training_stop": true
|
| 417 |
+
},
|
| 418 |
+
"attributes": {}
|
| 419 |
+
}
|
| 420 |
+
},
|
| 421 |
+
"total_flos": 2.2118369952006144e+16,
|
| 422 |
+
"train_batch_size": 4,
|
| 423 |
+
"trial_name": null,
|
| 424 |
+
"trial_params": null
|
| 425 |
+
}
|
checkpoint-562/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6a2b05271f7c80f5e8459b363dc27b41bbb262bcfa791304c142089f575f87e
|
| 3 |
+
size 5176
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "appvoid/arco",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 96,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 1536,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"max_position_embeddings": 2048,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 8,
|
| 19 |
+
"num_hidden_layers": 8,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-05,
|
| 24 |
+
"rope_scaling": null,
|
| 25 |
+
"rope_theta": 100000,
|
| 26 |
+
"sliding_window": null,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.45.1",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 32003
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.45.1"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34f19fda47fefb05b1addcc19c5fa1b60c74409c72856c501b576dac182dda62
|
| 3 |
+
size 997345472
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[BOS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[EOS]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"pad_token": {
|
| 24 |
+
"content": "[PAD]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"sep_token": {
|
| 31 |
+
"content": "</s>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"unk_token": {
|
| 38 |
+
"content": "<unk>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
}
|
| 44 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "[BOS]",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"32002": {
|
| 47 |
+
"content": "[EOS]",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
}
|
| 54 |
+
},
|
| 55 |
+
"additional_special_tokens": [],
|
| 56 |
+
"bos_token": "[BOS]",
|
| 57 |
+
"clean_up_tokenization_spaces": false,
|
| 58 |
+
"cls_token": "</s>",
|
| 59 |
+
"eos_token": "[EOS]",
|
| 60 |
+
"legacy": true,
|
| 61 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 62 |
+
"pad_token": "[PAD]",
|
| 63 |
+
"sep_token": "</s>",
|
| 64 |
+
"sp_model_kwargs": {},
|
| 65 |
+
"spaces_between_special_tokens": false,
|
| 66 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 67 |
+
"unk_token": "<unk>",
|
| 68 |
+
"use_default_system_prompt": false
|
| 69 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6a2b05271f7c80f5e8459b363dc27b41bbb262bcfa791304c142089f575f87e
|
| 3 |
+
size 5176
|