Upload folder using huggingface_hub
Browse files- checkpoint-3032/config.json +30 -0
- checkpoint-3032/generation_config.json +7 -0
- checkpoint-3032/model.safetensors +3 -0
- checkpoint-3032/optimizer.pt +3 -0
- checkpoint-3032/rng_state.pth +3 -0
- checkpoint-3032/scheduler.pt +3 -0
- checkpoint-3032/trainer_state.json +461 -0
- checkpoint-3032/training_args.bin +3 -0
- config.json +30 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +215 -0
- training_args.bin +3 -0
checkpoint-3032/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "EleutherAI/pythia-1.4b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTNeoXForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": true,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": 0.1,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout": 0.0,
|
| 13 |
+
"hidden_size": 2048,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 8192,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 2048,
|
| 18 |
+
"model_type": "gpt_neox",
|
| 19 |
+
"num_attention_heads": 16,
|
| 20 |
+
"num_hidden_layers": 24,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rotary_emb_base": 10000,
|
| 23 |
+
"rotary_pct": 0.25,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.44.2",
|
| 27 |
+
"use_cache": false,
|
| 28 |
+
"use_parallel_residual": true,
|
| 29 |
+
"vocab_size": 50304
|
| 30 |
+
}
|
checkpoint-3032/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.44.2",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
checkpoint-3032/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d6765c17c16d90f3a85831a059ad1ae697ffe33045562286f0290aec2173121
|
| 3 |
+
size 2829330208
|
checkpoint-3032/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a1681e0810031e90b2891a9132abaf7f4e54bd1abd1c8c469d2e7871009809c
|
| 3 |
+
size 5658843371
|
checkpoint-3032/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de69a2834426ff9ef8199d077e00892579278af31d8969d77f98235b5cfc010a
|
| 3 |
+
size 14645
|
checkpoint-3032/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5bd26f9fffbe9d013e6ab7620ca0e8c604e6486f6cbb12c833fad8a4f0f0a46
|
| 3 |
+
size 1465
|
checkpoint-3032/trainer_state.json
ADDED
|
@@ -0,0 +1,461 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.9169344902038574,
|
| 3 |
+
"best_model_checkpoint": "./checkpoints/ultrafeedback_binarized/pythia-1.4b-ultrafeedback_binarized-lambda0.24-ORPO-14-2-42/checkpoint-3032",
|
| 4 |
+
"epoch": 0.9998351195383347,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3032,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.016488046166529265,
|
| 13 |
+
"grad_norm": 8.6875,
|
| 14 |
+
"learning_rate": 4.333333333333333e-06,
|
| 15 |
+
"loss": 3.6291,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03297609233305853,
|
| 20 |
+
"grad_norm": 9.875,
|
| 21 |
+
"learning_rate": 8.666666666666666e-06,
|
| 22 |
+
"loss": 3.2106,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0494641384995878,
|
| 27 |
+
"grad_norm": 8.9375,
|
| 28 |
+
"learning_rate": 1.3e-05,
|
| 29 |
+
"loss": 2.9452,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06595218466611706,
|
| 34 |
+
"grad_norm": 6.875,
|
| 35 |
+
"learning_rate": 1.299034777031323e-05,
|
| 36 |
+
"loss": 2.7278,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08244023083264633,
|
| 41 |
+
"grad_norm": 6.8125,
|
| 42 |
+
"learning_rate": 1.2961419747572287e-05,
|
| 43 |
+
"loss": 2.6466,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0989282769991756,
|
| 48 |
+
"grad_norm": 4.375,
|
| 49 |
+
"learning_rate": 1.2913301845598668e-05,
|
| 50 |
+
"loss": 2.5629,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11541632316570487,
|
| 55 |
+
"grad_norm": 4.0625,
|
| 56 |
+
"learning_rate": 1.2846136970559112e-05,
|
| 57 |
+
"loss": 2.5691,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.13190436933223412,
|
| 62 |
+
"grad_norm": 7.46875,
|
| 63 |
+
"learning_rate": 1.2760124596546162e-05,
|
| 64 |
+
"loss": 2.4819,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1483924154987634,
|
| 69 |
+
"grad_norm": 4.6875,
|
| 70 |
+
"learning_rate": 1.2655520173156702e-05,
|
| 71 |
+
"loss": 2.4503,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.16488046166529266,
|
| 76 |
+
"grad_norm": 7.34375,
|
| 77 |
+
"learning_rate": 1.2532634366827907e-05,
|
| 78 |
+
"loss": 2.467,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.18136850783182193,
|
| 83 |
+
"grad_norm": 6.46875,
|
| 84 |
+
"learning_rate": 1.2391832138183752e-05,
|
| 85 |
+
"loss": 2.4131,
|
| 86 |
+
"step": 550
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1978565539983512,
|
| 90 |
+
"grad_norm": 3.578125,
|
| 91 |
+
"learning_rate": 1.2233531658132322e-05,
|
| 92 |
+
"loss": 2.3876,
|
| 93 |
+
"step": 600
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.21434460016488047,
|
| 97 |
+
"grad_norm": 11.25,
|
| 98 |
+
"learning_rate": 1.2058203065933e-05,
|
| 99 |
+
"loss": 2.3676,
|
| 100 |
+
"step": 650
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.23083264633140974,
|
| 104 |
+
"grad_norm": 4.25,
|
| 105 |
+
"learning_rate": 1.1866367072921961e-05,
|
| 106 |
+
"loss": 2.3321,
|
| 107 |
+
"step": 700
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.247320692497939,
|
| 111 |
+
"grad_norm": 8.1875,
|
| 112 |
+
"learning_rate": 1.1658593416042809e-05,
|
| 113 |
+
"loss": 2.3109,
|
| 114 |
+
"step": 750
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.26380873866446825,
|
| 118 |
+
"grad_norm": 5.0625,
|
| 119 |
+
"learning_rate": 1.143549916577526e-05,
|
| 120 |
+
"loss": 2.2684,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2802967848309975,
|
| 125 |
+
"grad_norm": 4.6875,
|
| 126 |
+
"learning_rate": 1.1197746893487121e-05,
|
| 127 |
+
"loss": 2.2505,
|
| 128 |
+
"step": 850
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.2967848309975268,
|
| 132 |
+
"grad_norm": 5.125,
|
| 133 |
+
"learning_rate": 1.0946042703652444e-05,
|
| 134 |
+
"loss": 2.2271,
|
| 135 |
+
"step": 900
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.31327287716405605,
|
| 139 |
+
"grad_norm": 4.71875,
|
| 140 |
+
"learning_rate": 1.0681134136779973e-05,
|
| 141 |
+
"loss": 2.1909,
|
| 142 |
+
"step": 950
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.3297609233305853,
|
| 146 |
+
"grad_norm": 4.84375,
|
| 147 |
+
"learning_rate": 1.0403807949279998e-05,
|
| 148 |
+
"loss": 2.2079,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3462489694971146,
|
| 153 |
+
"grad_norm": 4.40625,
|
| 154 |
+
"learning_rate": 1.0114887776863255e-05,
|
| 155 |
+
"loss": 2.1524,
|
| 156 |
+
"step": 1050
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.36273701566364386,
|
| 160 |
+
"grad_norm": 10.0,
|
| 161 |
+
"learning_rate": 9.815231688411385e-06,
|
| 162 |
+
"loss": 2.1247,
|
| 163 |
+
"step": 1100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.3792250618301731,
|
| 167 |
+
"grad_norm": 4.6875,
|
| 168 |
+
"learning_rate": 9.505729637583697e-06,
|
| 169 |
+
"loss": 2.1355,
|
| 170 |
+
"step": 1150
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3957131079967024,
|
| 174 |
+
"grad_norm": 4.84375,
|
| 175 |
+
"learning_rate": 9.187300819728845e-06,
|
| 176 |
+
"loss": 2.0472,
|
| 177 |
+
"step": 1200
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.41220115416323166,
|
| 181 |
+
"grad_norm": 8.5,
|
| 182 |
+
"learning_rate": 8.86089094195108e-06,
|
| 183 |
+
"loss": 2.1215,
|
| 184 |
+
"step": 1250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.42868920032976093,
|
| 188 |
+
"grad_norm": 7.90625,
|
| 189 |
+
"learning_rate": 8.527469414438818e-06,
|
| 190 |
+
"loss": 2.0956,
|
| 191 |
+
"step": 1300
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.4451772464962902,
|
| 195 |
+
"grad_norm": 6.59375,
|
| 196 |
+
"learning_rate": 8.188026471396994e-06,
|
| 197 |
+
"loss": 2.079,
|
| 198 |
+
"step": 1350
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.46166529266281947,
|
| 202 |
+
"grad_norm": 9.0625,
|
| 203 |
+
"learning_rate": 7.843570230133861e-06,
|
| 204 |
+
"loss": 2.0604,
|
| 205 |
+
"step": 1400
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.47815333882934874,
|
| 209 |
+
"grad_norm": 7.53125,
|
| 210 |
+
"learning_rate": 7.4951236970364e-06,
|
| 211 |
+
"loss": 2.0528,
|
| 212 |
+
"step": 1450
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.494641384995878,
|
| 216 |
+
"grad_norm": 8.25,
|
| 217 |
+
"learning_rate": 7.143721729326464e-06,
|
| 218 |
+
"loss": 2.0402,
|
| 219 |
+
"step": 1500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5111294311624073,
|
| 223 |
+
"grad_norm": 8.4375,
|
| 224 |
+
"learning_rate": 6.790407961620892e-06,
|
| 225 |
+
"loss": 2.0491,
|
| 226 |
+
"step": 1550
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5276174773289365,
|
| 230 |
+
"grad_norm": 12.875,
|
| 231 |
+
"learning_rate": 6.436231706423493e-06,
|
| 232 |
+
"loss": 2.0177,
|
| 233 |
+
"step": 1600
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5441055234954658,
|
| 237 |
+
"grad_norm": 8.0,
|
| 238 |
+
"learning_rate": 6.082244837754198e-06,
|
| 239 |
+
"loss": 2.0213,
|
| 240 |
+
"step": 1650
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.560593569661995,
|
| 244 |
+
"grad_norm": 7.40625,
|
| 245 |
+
"learning_rate": 5.729498667170698e-06,
|
| 246 |
+
"loss": 2.0213,
|
| 247 |
+
"step": 1700
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.5770816158285244,
|
| 251 |
+
"grad_norm": 10.3125,
|
| 252 |
+
"learning_rate": 5.379040821460559e-06,
|
| 253 |
+
"loss": 2.0067,
|
| 254 |
+
"step": 1750
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.5935696619950536,
|
| 258 |
+
"grad_norm": 4.09375,
|
| 259 |
+
"learning_rate": 5.031912131276807e-06,
|
| 260 |
+
"loss": 2.008,
|
| 261 |
+
"step": 1800
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.6100577081615829,
|
| 265 |
+
"grad_norm": 4.9375,
|
| 266 |
+
"learning_rate": 4.689143539957446e-06,
|
| 267 |
+
"loss": 2.021,
|
| 268 |
+
"step": 1850
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6265457543281121,
|
| 272 |
+
"grad_norm": 8.9375,
|
| 273 |
+
"learning_rate": 4.351753041709503e-06,
|
| 274 |
+
"loss": 2.0262,
|
| 275 |
+
"step": 1900
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.6430338004946414,
|
| 279 |
+
"grad_norm": 4.5625,
|
| 280 |
+
"learning_rate": 4.020742658250887e-06,
|
| 281 |
+
"loss": 1.9914,
|
| 282 |
+
"step": 1950
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.6595218466611706,
|
| 286 |
+
"grad_norm": 7.15625,
|
| 287 |
+
"learning_rate": 3.697095462889249e-06,
|
| 288 |
+
"loss": 2.0001,
|
| 289 |
+
"step": 2000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.6760098928277,
|
| 293 |
+
"grad_norm": 10.4375,
|
| 294 |
+
"learning_rate": 3.381772660876002e-06,
|
| 295 |
+
"loss": 1.9848,
|
| 296 |
+
"step": 2050
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.6924979389942292,
|
| 300 |
+
"grad_norm": 3.328125,
|
| 301 |
+
"learning_rate": 3.0757107347066913e-06,
|
| 302 |
+
"loss": 2.0309,
|
| 303 |
+
"step": 2100
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.7089859851607585,
|
| 307 |
+
"grad_norm": 4.8125,
|
| 308 |
+
"learning_rate": 2.779818662845854e-06,
|
| 309 |
+
"loss": 1.9704,
|
| 310 |
+
"step": 2150
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.7254740313272877,
|
| 314 |
+
"grad_norm": 5.1875,
|
| 315 |
+
"learning_rate": 2.4949752201366016e-06,
|
| 316 |
+
"loss": 1.9733,
|
| 317 |
+
"step": 2200
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.7419620774938169,
|
| 321 |
+
"grad_norm": 6.8125,
|
| 322 |
+
"learning_rate": 2.2220263679124083e-06,
|
| 323 |
+
"loss": 1.9418,
|
| 324 |
+
"step": 2250
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.7584501236603463,
|
| 328 |
+
"grad_norm": 5.15625,
|
| 329 |
+
"learning_rate": 1.9617827415623227e-06,
|
| 330 |
+
"loss": 1.9522,
|
| 331 |
+
"step": 2300
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.7749381698268755,
|
| 335 |
+
"grad_norm": 7.0625,
|
| 336 |
+
"learning_rate": 1.7150172430112804e-06,
|
| 337 |
+
"loss": 1.975,
|
| 338 |
+
"step": 2350
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.7914262159934048,
|
| 342 |
+
"grad_norm": 9.5625,
|
| 343 |
+
"learning_rate": 1.4824627452656817e-06,
|
| 344 |
+
"loss": 1.9649,
|
| 345 |
+
"step": 2400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.807914262159934,
|
| 349 |
+
"grad_norm": 3.78125,
|
| 350 |
+
"learning_rate": 1.264809915841502e-06,
|
| 351 |
+
"loss": 1.9855,
|
| 352 |
+
"step": 2450
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.8244023083264633,
|
| 356 |
+
"grad_norm": 6.21875,
|
| 357 |
+
"learning_rate": 1.062705165539226e-06,
|
| 358 |
+
"loss": 1.9435,
|
| 359 |
+
"step": 2500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.8408903544929925,
|
| 363 |
+
"grad_norm": 4.21875,
|
| 364 |
+
"learning_rate": 8.767487286575354e-07,
|
| 365 |
+
"loss": 1.9703,
|
| 366 |
+
"step": 2550
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.8573784006595219,
|
| 370 |
+
"grad_norm": 3.625,
|
| 371 |
+
"learning_rate": 7.074928803473566e-07,
|
| 372 |
+
"loss": 2.019,
|
| 373 |
+
"step": 2600
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.8738664468260511,
|
| 377 |
+
"grad_norm": 8.3125,
|
| 378 |
+
"learning_rate": 5.55440296400602e-07,
|
| 379 |
+
"loss": 1.9383,
|
| 380 |
+
"step": 2650
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.8903544929925804,
|
| 384 |
+
"grad_norm": 5.5625,
|
| 385 |
+
"learning_rate": 4.2104256034487713e-07,
|
| 386 |
+
"loss": 1.928,
|
| 387 |
+
"step": 2700
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.9068425391591096,
|
| 391 |
+
"grad_norm": 6.5,
|
| 392 |
+
"learning_rate": 3.046988222779669e-07,
|
| 393 |
+
"loss": 1.9765,
|
| 394 |
+
"step": 2750
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.9233305853256389,
|
| 398 |
+
"grad_norm": 5.46875,
|
| 399 |
+
"learning_rate": 2.0675461342523516e-07,
|
| 400 |
+
"loss": 1.9639,
|
| 401 |
+
"step": 2800
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.9398186314921682,
|
| 405 |
+
"grad_norm": 7.40625,
|
| 406 |
+
"learning_rate": 1.275008199406322e-07,
|
| 407 |
+
"loss": 1.9248,
|
| 408 |
+
"step": 2850
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.9563066776586975,
|
| 412 |
+
"grad_norm": 8.0,
|
| 413 |
+
"learning_rate": 6.717281899900718e-08,
|
| 414 |
+
"loss": 1.957,
|
| 415 |
+
"step": 2900
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.9727947238252267,
|
| 419 |
+
"grad_norm": 6.0625,
|
| 420 |
+
"learning_rate": 2.594977974547735e-08,
|
| 421 |
+
"loss": 1.9263,
|
| 422 |
+
"step": 2950
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.989282769991756,
|
| 426 |
+
"grad_norm": 5.53125,
|
| 427 |
+
"learning_rate": 3.954131177969833e-09,
|
| 428 |
+
"loss": 1.9255,
|
| 429 |
+
"step": 3000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.9998351195383347,
|
| 433 |
+
"eval_loss": 1.9169344902038574,
|
| 434 |
+
"eval_runtime": 110.027,
|
| 435 |
+
"eval_samples_per_second": 14.805,
|
| 436 |
+
"eval_steps_per_second": 1.854,
|
| 437 |
+
"step": 3032
|
| 438 |
+
}
|
| 439 |
+
],
|
| 440 |
+
"logging_steps": 50,
|
| 441 |
+
"max_steps": 3032,
|
| 442 |
+
"num_input_tokens_seen": 0,
|
| 443 |
+
"num_train_epochs": 1,
|
| 444 |
+
"save_steps": 500,
|
| 445 |
+
"stateful_callbacks": {
|
| 446 |
+
"TrainerControl": {
|
| 447 |
+
"args": {
|
| 448 |
+
"should_epoch_stop": false,
|
| 449 |
+
"should_evaluate": false,
|
| 450 |
+
"should_log": false,
|
| 451 |
+
"should_save": true,
|
| 452 |
+
"should_training_stop": true
|
| 453 |
+
},
|
| 454 |
+
"attributes": {}
|
| 455 |
+
}
|
| 456 |
+
},
|
| 457 |
+
"total_flos": 3.9094003186846925e+17,
|
| 458 |
+
"train_batch_size": 8,
|
| 459 |
+
"trial_name": null,
|
| 460 |
+
"trial_params": null
|
| 461 |
+
}
|
checkpoint-3032/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7febae4f1cc581928d4f4651e47426d84b9354b60e9a3d632a6b34e6b6a8cbab
|
| 3 |
+
size 5841
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "EleutherAI/pythia-1.4b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTNeoXForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": true,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": 0.1,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout": 0.0,
|
| 13 |
+
"hidden_size": 2048,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 8192,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 2048,
|
| 18 |
+
"model_type": "gpt_neox",
|
| 19 |
+
"num_attention_heads": 16,
|
| 20 |
+
"num_hidden_layers": 24,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rotary_emb_base": 10000,
|
| 23 |
+
"rotary_pct": 0.25,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.44.2",
|
| 27 |
+
"use_cache": false,
|
| 28 |
+
"use_parallel_residual": true,
|
| 29 |
+
"vocab_size": 50304
|
| 30 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.44.2",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d6765c17c16d90f3a85831a059ad1ae697ffe33045562286f0290aec2173121
|
| 3 |
+
size 2829330208
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,215 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<|padding|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"50254": {
|
| 23 |
+
"content": " ",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"50255": {
|
| 31 |
+
"content": " ",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"50256": {
|
| 39 |
+
"content": " ",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"50257": {
|
| 47 |
+
"content": " ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"50258": {
|
| 55 |
+
"content": " ",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"50259": {
|
| 63 |
+
"content": " ",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"50260": {
|
| 71 |
+
"content": " ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"50261": {
|
| 79 |
+
"content": " ",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"50262": {
|
| 87 |
+
"content": " ",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"50263": {
|
| 95 |
+
"content": " ",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"50264": {
|
| 103 |
+
"content": " ",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"50265": {
|
| 111 |
+
"content": " ",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": false
|
| 117 |
+
},
|
| 118 |
+
"50266": {
|
| 119 |
+
"content": " ",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"50267": {
|
| 127 |
+
"content": " ",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"50268": {
|
| 135 |
+
"content": " ",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"50269": {
|
| 143 |
+
"content": " ",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"50270": {
|
| 151 |
+
"content": " ",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"50271": {
|
| 159 |
+
"content": " ",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"50272": {
|
| 167 |
+
"content": " ",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"50273": {
|
| 175 |
+
"content": " ",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
"50274": {
|
| 183 |
+
"content": " ",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": true,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": false
|
| 189 |
+
},
|
| 190 |
+
"50275": {
|
| 191 |
+
"content": " ",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": true,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": false
|
| 197 |
+
},
|
| 198 |
+
"50276": {
|
| 199 |
+
"content": " ",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": true,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": false
|
| 205 |
+
}
|
| 206 |
+
},
|
| 207 |
+
"bos_token": "<|endoftext|>",
|
| 208 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 209 |
+
"clean_up_tokenization_spaces": true,
|
| 210 |
+
"eos_token": "<|endoftext|>",
|
| 211 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 212 |
+
"pad_token": "<|endoftext|>",
|
| 213 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 214 |
+
"unk_token": "<|endoftext|>"
|
| 215 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7febae4f1cc581928d4f4651e47426d84b9354b60e9a3d632a6b34e6b6a8cbab
|
| 3 |
+
size 5841
|