Upload folder using huggingface_hub
Browse files- checkpoint-500/config.json +17 -0
- checkpoint-500/generation_config.json +6 -0
- checkpoint-500/hybrid_tokenizer_mapping.json +0 -0
- checkpoint-500/model.safetensors +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scaler.pt +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/tokenizer_config.json +9 -0
- checkpoint-500/trainer_state.json +384 -0
- checkpoint-500/training_args.bin +3 -0
checkpoint-500/config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"FastHyperNet125mForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "float32",
|
| 6 |
+
"hidden_size": 768,
|
| 7 |
+
"hyperbolic_dim": 16,
|
| 8 |
+
"initializer_range": 0.02,
|
| 9 |
+
"intermediate_size": 2048,
|
| 10 |
+
"max_position_embeddings": 512,
|
| 11 |
+
"model_type": "fasthypernet_125m_linguistic",
|
| 12 |
+
"num_attention_heads": 12,
|
| 13 |
+
"num_hidden_layers": 16,
|
| 14 |
+
"transformers_version": "5.13.1",
|
| 15 |
+
"use_cache": false,
|
| 16 |
+
"vocab_size": 8192
|
| 17 |
+
}
|
checkpoint-500/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"output_attentions": false,
|
| 4 |
+
"output_hidden_states": false,
|
| 5 |
+
"transformers_version": "5.13.1"
|
| 6 |
+
}
|
checkpoint-500/hybrid_tokenizer_mapping.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7b79c20beea6c0c7bd3ca2e0ae7dd9feafb8e61654d9a9cfe07909a353c7a58
|
| 3 |
+
size 508157712
|
checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62eafd88213937485dfff4ea85e00924000102437fec949b4429ed75a9d81b4f
|
| 3 |
+
size 259122285
|
checkpoint-500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:089d0d2df7def8ac53b2a224e1c562048011e2c371b3412063691b9033d28057
|
| 3 |
+
size 14645
|
checkpoint-500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:552a7b680b6e6d0be83fd462b73987ddb8eec76ca2830ffb869727e81ccbe420
|
| 3 |
+
size 1383
|
checkpoint-500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec06f373f335e609a448978ddc24e2ccbbb2c2bbe272febaee6bcb35ef9d12f1
|
| 3 |
+
size 1465
|
checkpoint-500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tokenizer_class": "HFCompatibleLinguisticTokenizer",
|
| 3 |
+
"vocab_size": 8192,
|
| 4 |
+
"model_max_length": 512,
|
| 5 |
+
"bos_token": "<bos>",
|
| 6 |
+
"eos_token": "<eos>",
|
| 7 |
+
"unk_token": "<unk>",
|
| 8 |
+
"pad_token": "<pad>"
|
| 9 |
+
}
|
checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,384 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.0010346486591815585,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.00013795315455754112,
|
| 14 |
+
"grad_norm": 53.4421272277832,
|
| 15 |
+
"learning_rate": 4.1999999999999995e-07,
|
| 16 |
+
"loss": 8.6569,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.00027590630911508224,
|
| 21 |
+
"grad_norm": 57.65703582763672,
|
| 22 |
+
"learning_rate": 1.0199999999999998e-06,
|
| 23 |
+
"loss": 8.6391,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0004138594636726234,
|
| 28 |
+
"grad_norm": 93.79612731933594,
|
| 29 |
+
"learning_rate": 1.62e-06,
|
| 30 |
+
"loss": 8.6097,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0005518126182301645,
|
| 35 |
+
"grad_norm": 133.8379669189453,
|
| 36 |
+
"learning_rate": 2.22e-06,
|
| 37 |
+
"loss": 8.5995,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0006897657727877056,
|
| 42 |
+
"grad_norm": 99.24571228027344,
|
| 43 |
+
"learning_rate": 2.8199999999999997e-06,
|
| 44 |
+
"loss": 8.5699,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0008277189273452468,
|
| 49 |
+
"grad_norm": 155.49118041992188,
|
| 50 |
+
"learning_rate": 3.42e-06,
|
| 51 |
+
"loss": 8.5516,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0009656720819027878,
|
| 56 |
+
"grad_norm": 118.79692840576172,
|
| 57 |
+
"learning_rate": 4.02e-06,
|
| 58 |
+
"loss": 8.5331,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.001103625236460329,
|
| 63 |
+
"grad_norm": 88.51729583740234,
|
| 64 |
+
"learning_rate": 4.62e-06,
|
| 65 |
+
"loss": 8.5212,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0012415783910178701,
|
| 70 |
+
"grad_norm": 117.01810455322266,
|
| 71 |
+
"learning_rate": 5.219999999999999e-06,
|
| 72 |
+
"loss": 8.5007,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0013795315455754113,
|
| 77 |
+
"grad_norm": 104.06542205810547,
|
| 78 |
+
"learning_rate": 5.819999999999999e-06,
|
| 79 |
+
"loss": 8.4948,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.0015174847001329524,
|
| 84 |
+
"grad_norm": 103.02165985107422,
|
| 85 |
+
"learning_rate": 6.4199999999999995e-06,
|
| 86 |
+
"loss": 8.4871,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.0016554378546904936,
|
| 91 |
+
"grad_norm": 119.96959686279297,
|
| 92 |
+
"learning_rate": 7.02e-06,
|
| 93 |
+
"loss": 8.4803,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.0017933910092480345,
|
| 98 |
+
"grad_norm": 83.34615325927734,
|
| 99 |
+
"learning_rate": 7.619999999999999e-06,
|
| 100 |
+
"loss": 8.471,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.0019313441638055756,
|
| 105 |
+
"grad_norm": 76.37083435058594,
|
| 106 |
+
"learning_rate": 8.22e-06,
|
| 107 |
+
"loss": 8.4655,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.002069297318363117,
|
| 112 |
+
"grad_norm": 82.49830627441406,
|
| 113 |
+
"learning_rate": 8.819999999999999e-06,
|
| 114 |
+
"loss": 8.4708,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.002207250472920658,
|
| 119 |
+
"grad_norm": 69.70299530029297,
|
| 120 |
+
"learning_rate": 9.419999999999998e-06,
|
| 121 |
+
"loss": 8.4659,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.0023452036274781993,
|
| 126 |
+
"grad_norm": 103.55642700195312,
|
| 127 |
+
"learning_rate": 1.0019999999999999e-05,
|
| 128 |
+
"loss": 8.4555,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.0024831567820357402,
|
| 133 |
+
"grad_norm": 112.4985122680664,
|
| 134 |
+
"learning_rate": 1.062e-05,
|
| 135 |
+
"loss": 8.4629,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.002621109936593281,
|
| 140 |
+
"grad_norm": 78.48297882080078,
|
| 141 |
+
"learning_rate": 1.122e-05,
|
| 142 |
+
"loss": 8.4562,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.0027590630911508225,
|
| 147 |
+
"grad_norm": 87.78710174560547,
|
| 148 |
+
"learning_rate": 1.1819999999999999e-05,
|
| 149 |
+
"loss": 8.451,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 3.448828863938528e-05,
|
| 154 |
+
"grad_norm": 34.83774948120117,
|
| 155 |
+
"learning_rate": 1.2419999999999998e-05,
|
| 156 |
+
"loss": 8.4432,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 6.897657727877056e-05,
|
| 161 |
+
"grad_norm": 68.05087280273438,
|
| 162 |
+
"learning_rate": 1.3019999999999999e-05,
|
| 163 |
+
"loss": 8.4542,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.00010346486591815585,
|
| 168 |
+
"grad_norm": 46.86287307739258,
|
| 169 |
+
"learning_rate": 1.362e-05,
|
| 170 |
+
"loss": 8.4622,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.00013795315455754112,
|
| 175 |
+
"grad_norm": 38.558746337890625,
|
| 176 |
+
"learning_rate": 1.4219999999999998e-05,
|
| 177 |
+
"loss": 8.4458,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.0001724414431969264,
|
| 182 |
+
"grad_norm": 38.49115753173828,
|
| 183 |
+
"learning_rate": 1.4819999999999999e-05,
|
| 184 |
+
"loss": 8.4495,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.0002069297318363117,
|
| 189 |
+
"grad_norm": 29.765907287597656,
|
| 190 |
+
"learning_rate": 1.5419999999999998e-05,
|
| 191 |
+
"loss": 8.464,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.00024141802047569696,
|
| 196 |
+
"grad_norm": 48.3050537109375,
|
| 197 |
+
"learning_rate": 1.602e-05,
|
| 198 |
+
"loss": 8.4601,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.00027590630911508224,
|
| 203 |
+
"grad_norm": 27.089998245239258,
|
| 204 |
+
"learning_rate": 1.6619999999999997e-05,
|
| 205 |
+
"loss": 8.4628,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.00031039459775446753,
|
| 210 |
+
"grad_norm": 36.98786163330078,
|
| 211 |
+
"learning_rate": 1.7219999999999998e-05,
|
| 212 |
+
"loss": 8.4364,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.0003448828863938528,
|
| 217 |
+
"grad_norm": 39.274784088134766,
|
| 218 |
+
"learning_rate": 1.782e-05,
|
| 219 |
+
"loss": 8.4314,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.0003793711750332381,
|
| 224 |
+
"grad_norm": 29.303476333618164,
|
| 225 |
+
"learning_rate": 1.842e-05,
|
| 226 |
+
"loss": 8.4153,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.0004138594636726234,
|
| 231 |
+
"grad_norm": 24.435274124145508,
|
| 232 |
+
"learning_rate": 1.9019999999999997e-05,
|
| 233 |
+
"loss": 8.4489,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.0004483477523120086,
|
| 238 |
+
"grad_norm": 25.8426456451416,
|
| 239 |
+
"learning_rate": 1.962e-05,
|
| 240 |
+
"loss": 8.4297,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.0004828360409513939,
|
| 245 |
+
"grad_norm": 24.164419174194336,
|
| 246 |
+
"learning_rate": 2.022e-05,
|
| 247 |
+
"loss": 8.4398,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.0005173243295907793,
|
| 252 |
+
"grad_norm": 17.73716163635254,
|
| 253 |
+
"learning_rate": 2.082e-05,
|
| 254 |
+
"loss": 8.4333,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.0005518126182301645,
|
| 259 |
+
"grad_norm": 34.02337646484375,
|
| 260 |
+
"learning_rate": 2.1419999999999998e-05,
|
| 261 |
+
"loss": 8.4488,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.0005863009068695498,
|
| 266 |
+
"grad_norm": 26.535123825073242,
|
| 267 |
+
"learning_rate": 2.202e-05,
|
| 268 |
+
"loss": 8.4361,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.0006207891955089351,
|
| 273 |
+
"grad_norm": 32.27824783325195,
|
| 274 |
+
"learning_rate": 2.2619999999999997e-05,
|
| 275 |
+
"loss": 8.4116,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.0006552774841483203,
|
| 280 |
+
"grad_norm": 20.55720329284668,
|
| 281 |
+
"learning_rate": 2.3219999999999998e-05,
|
| 282 |
+
"loss": 8.4151,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.0006897657727877056,
|
| 287 |
+
"grad_norm": 30.87930679321289,
|
| 288 |
+
"learning_rate": 2.382e-05,
|
| 289 |
+
"loss": 8.43,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.0007242540614270909,
|
| 294 |
+
"grad_norm": 19.80055046081543,
|
| 295 |
+
"learning_rate": 2.4419999999999997e-05,
|
| 296 |
+
"loss": 8.4345,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.0007587423500664762,
|
| 301 |
+
"grad_norm": 23.822568893432617,
|
| 302 |
+
"learning_rate": 2.5019999999999998e-05,
|
| 303 |
+
"loss": 8.413,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.0007932306387058614,
|
| 308 |
+
"grad_norm": 24.005403518676758,
|
| 309 |
+
"learning_rate": 2.562e-05,
|
| 310 |
+
"loss": 8.419,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.0008277189273452468,
|
| 315 |
+
"grad_norm": 30.060989379882812,
|
| 316 |
+
"learning_rate": 2.622e-05,
|
| 317 |
+
"loss": 8.4314,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.000862207215984632,
|
| 322 |
+
"grad_norm": 22.84067153930664,
|
| 323 |
+
"learning_rate": 2.6759999999999998e-05,
|
| 324 |
+
"loss": 8.4154,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.0008966955046240172,
|
| 329 |
+
"grad_norm": 22.259994506835938,
|
| 330 |
+
"learning_rate": 2.7299999999999996e-05,
|
| 331 |
+
"loss": 8.4086,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.0009311837932634026,
|
| 336 |
+
"grad_norm": 11.726574897766113,
|
| 337 |
+
"learning_rate": 2.7899999999999997e-05,
|
| 338 |
+
"loss": 8.4284,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.0009656720819027878,
|
| 343 |
+
"grad_norm": 27.165864944458008,
|
| 344 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 345 |
+
"loss": 8.4169,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.001000160370542173,
|
| 350 |
+
"grad_norm": 24.19461441040039,
|
| 351 |
+
"learning_rate": 2.91e-05,
|
| 352 |
+
"loss": 8.4343,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.0010346486591815585,
|
| 357 |
+
"grad_norm": 10.8844633102417,
|
| 358 |
+
"learning_rate": 2.97e-05,
|
| 359 |
+
"loss": 8.4233,
|
| 360 |
+
"step": 500
|
| 361 |
+
}
|
| 362 |
+
],
|
| 363 |
+
"logging_steps": 10,
|
| 364 |
+
"max_steps": 10000000,
|
| 365 |
+
"num_input_tokens_seen": 0,
|
| 366 |
+
"num_train_epochs": 35,
|
| 367 |
+
"save_steps": 100,
|
| 368 |
+
"stateful_callbacks": {
|
| 369 |
+
"TrainerControl": {
|
| 370 |
+
"args": {
|
| 371 |
+
"should_epoch_stop": false,
|
| 372 |
+
"should_evaluate": false,
|
| 373 |
+
"should_log": false,
|
| 374 |
+
"should_save": true,
|
| 375 |
+
"should_training_stop": false
|
| 376 |
+
},
|
| 377 |
+
"attributes": {}
|
| 378 |
+
}
|
| 379 |
+
},
|
| 380 |
+
"total_flos": 4236220120743936.0,
|
| 381 |
+
"train_batch_size": 8,
|
| 382 |
+
"trial_name": null,
|
| 383 |
+
"trial_params": null
|
| 384 |
+
}
|
checkpoint-500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a51182451ce226f524b4245bb98c4f2eb82c17aaf6895f5b914588d78fefda14
|
| 3 |
+
size 5201
|