Training in progress, step 1000, checkpoint
Browse files- last-checkpoint/config.json +30 -0
- last-checkpoint/generation_config.json +8 -0
- last-checkpoint/model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state_0.pth +3 -0
- last-checkpoint/rng_state_1.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/trainer_state.json +322 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 31989,
|
| 8 |
+
"eos_token_id": 31989,
|
| 9 |
+
"head_dim": 64,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.036084391824351615,
|
| 13 |
+
"intermediate_size": 1920,
|
| 14 |
+
"max_position_embeddings": 8192,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 27,
|
| 19 |
+
"num_key_value_heads": 4,
|
| 20 |
+
"pad_token_id": 31989,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"rms_norm_eps": 1e-06,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 1000000.0,
|
| 25 |
+
"tie_word_embeddings": true,
|
| 26 |
+
"torch_dtype": "bfloat16",
|
| 27 |
+
"transformers_version": "4.54.1",
|
| 28 |
+
"use_cache": false,
|
| 29 |
+
"vocab_size": 32000
|
| 30 |
+
}
|
last-checkpoint/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 31989,
|
| 4 |
+
"eos_token_id": 31989,
|
| 5 |
+
"pad_token_id": 31989,
|
| 6 |
+
"transformers_version": "4.54.1",
|
| 7 |
+
"use_cache": false
|
| 8 |
+
}
|
last-checkpoint/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:013c7fc72260d69c7b4bd7e22c5a1b3d0154c7dc1b872fdafec73a570e539692
|
| 3 |
+
size 373077376
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f75bd419b54bf437d6794e0e46c0bf78cc292e651457d4d86a7a6fa804712b4c
|
| 3 |
+
size 209816139
|
last-checkpoint/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e27c30a8804a9166cb35ef95d4b96fe4a88ae8ab12f66c7df2cd80c284d9ad60
|
| 3 |
+
size 14917
|
last-checkpoint/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e56c20334ecc931a4a5e6aaf40ab675bba6da4e48dedcde541bc576d40159ecc
|
| 3 |
+
size 14917
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a08a6a4d67b84579ef3d0c3f7b82b0f64dc1e355fdee07cf30572bf265c6492
|
| 3 |
+
size 1401
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,322 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1000,
|
| 3 |
+
"best_metric": 10.227066993713379,
|
| 4 |
+
"best_model_checkpoint": "./artifacts/models/base-250725-test/checkpoint-1000",
|
| 5 |
+
"epoch": 0.003123106616613678,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 7.807766541534195e-05,
|
| 14 |
+
"grad_norm": 1.9921875,
|
| 15 |
+
"learning_rate": 1.499063085571518e-06,
|
| 16 |
+
"loss": 10.8863,
|
| 17 |
+
"step": 25
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0001561553308306839,
|
| 21 |
+
"grad_norm": 2.40625,
|
| 22 |
+
"learning_rate": 3.0605871330418487e-06,
|
| 23 |
+
"loss": 10.8814,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.00023423299624602585,
|
| 28 |
+
"grad_norm": 2.328125,
|
| 29 |
+
"learning_rate": 4.62211118051218e-06,
|
| 30 |
+
"loss": 10.883,
|
| 31 |
+
"step": 75
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0003123106616613678,
|
| 35 |
+
"grad_norm": 2.03125,
|
| 36 |
+
"learning_rate": 6.183635227982511e-06,
|
| 37 |
+
"loss": 10.8828,
|
| 38 |
+
"step": 100
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.00039038832707670977,
|
| 42 |
+
"grad_norm": 1.9765625,
|
| 43 |
+
"learning_rate": 7.745159275452842e-06,
|
| 44 |
+
"loss": 10.8834,
|
| 45 |
+
"step": 125
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0004684659924920517,
|
| 49 |
+
"grad_norm": 2.125,
|
| 50 |
+
"learning_rate": 9.306683322923173e-06,
|
| 51 |
+
"loss": 10.8796,
|
| 52 |
+
"step": 150
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0005465436579073936,
|
| 56 |
+
"grad_norm": 1.96875,
|
| 57 |
+
"learning_rate": 1.0868207370393504e-05,
|
| 58 |
+
"loss": 10.8798,
|
| 59 |
+
"step": 175
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0006246213233227356,
|
| 63 |
+
"grad_norm": 1.9765625,
|
| 64 |
+
"learning_rate": 1.2429731417863835e-05,
|
| 65 |
+
"loss": 10.8764,
|
| 66 |
+
"step": 200
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0007026989887380775,
|
| 70 |
+
"grad_norm": 2.203125,
|
| 71 |
+
"learning_rate": 1.3991255465334166e-05,
|
| 72 |
+
"loss": 10.8779,
|
| 73 |
+
"step": 225
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0007807766541534195,
|
| 77 |
+
"grad_norm": 2.296875,
|
| 78 |
+
"learning_rate": 1.5552779512804497e-05,
|
| 79 |
+
"loss": 10.8715,
|
| 80 |
+
"step": 250
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.0008588543195687615,
|
| 84 |
+
"grad_norm": 2.234375,
|
| 85 |
+
"learning_rate": 1.7114303560274827e-05,
|
| 86 |
+
"loss": 10.8676,
|
| 87 |
+
"step": 275
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.0009369319849841034,
|
| 91 |
+
"grad_norm": 2.3125,
|
| 92 |
+
"learning_rate": 1.867582760774516e-05,
|
| 93 |
+
"loss": 10.8621,
|
| 94 |
+
"step": 300
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.0010150096503994453,
|
| 98 |
+
"grad_norm": 2.359375,
|
| 99 |
+
"learning_rate": 2.0237351655215492e-05,
|
| 100 |
+
"loss": 10.8566,
|
| 101 |
+
"step": 325
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.0010930873158147873,
|
| 105 |
+
"grad_norm": 2.015625,
|
| 106 |
+
"learning_rate": 2.179887570268582e-05,
|
| 107 |
+
"loss": 10.8515,
|
| 108 |
+
"step": 350
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.0011711649812301292,
|
| 112 |
+
"grad_norm": 2.21875,
|
| 113 |
+
"learning_rate": 2.3360399750156154e-05,
|
| 114 |
+
"loss": 10.8445,
|
| 115 |
+
"step": 375
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.0012492426466454711,
|
| 119 |
+
"grad_norm": 2.09375,
|
| 120 |
+
"learning_rate": 2.4921923797626483e-05,
|
| 121 |
+
"loss": 10.8383,
|
| 122 |
+
"step": 400
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.001327320312060813,
|
| 126 |
+
"grad_norm": 2.0625,
|
| 127 |
+
"learning_rate": 2.6483447845096816e-05,
|
| 128 |
+
"loss": 10.8244,
|
| 129 |
+
"step": 425
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.001405397977476155,
|
| 133 |
+
"grad_norm": 1.890625,
|
| 134 |
+
"learning_rate": 2.804497189256715e-05,
|
| 135 |
+
"loss": 10.8193,
|
| 136 |
+
"step": 450
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.001483475642891497,
|
| 140 |
+
"grad_norm": 2.21875,
|
| 141 |
+
"learning_rate": 2.9606495940037475e-05,
|
| 142 |
+
"loss": 10.7992,
|
| 143 |
+
"step": 475
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.001561553308306839,
|
| 147 |
+
"grad_norm": 2.09375,
|
| 148 |
+
"learning_rate": 3.116801998750781e-05,
|
| 149 |
+
"loss": 10.7987,
|
| 150 |
+
"step": 500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.001639630973722181,
|
| 154 |
+
"grad_norm": 2.0625,
|
| 155 |
+
"learning_rate": 3.272954403497814e-05,
|
| 156 |
+
"loss": 10.7803,
|
| 157 |
+
"step": 525
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.001717708639137523,
|
| 161 |
+
"grad_norm": 2.140625,
|
| 162 |
+
"learning_rate": 3.429106808244847e-05,
|
| 163 |
+
"loss": 10.7653,
|
| 164 |
+
"step": 550
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.0017957863045528649,
|
| 168 |
+
"grad_norm": 2.578125,
|
| 169 |
+
"learning_rate": 3.58525921299188e-05,
|
| 170 |
+
"loss": 10.745,
|
| 171 |
+
"step": 575
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.0018738639699682068,
|
| 175 |
+
"grad_norm": 1.8515625,
|
| 176 |
+
"learning_rate": 3.741411617738913e-05,
|
| 177 |
+
"loss": 10.7327,
|
| 178 |
+
"step": 600
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.0019519416353835487,
|
| 182 |
+
"grad_norm": 2.15625,
|
| 183 |
+
"learning_rate": 3.897564022485946e-05,
|
| 184 |
+
"loss": 10.7159,
|
| 185 |
+
"step": 625
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.0020300193007988907,
|
| 189 |
+
"grad_norm": 2.53125,
|
| 190 |
+
"learning_rate": 4.053716427232979e-05,
|
| 191 |
+
"loss": 10.6931,
|
| 192 |
+
"step": 650
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.0021080969662142326,
|
| 196 |
+
"grad_norm": 2.078125,
|
| 197 |
+
"learning_rate": 4.2098688319800126e-05,
|
| 198 |
+
"loss": 10.6688,
|
| 199 |
+
"step": 675
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.0021861746316295745,
|
| 203 |
+
"grad_norm": 2.6875,
|
| 204 |
+
"learning_rate": 4.3660212367270456e-05,
|
| 205 |
+
"loss": 10.6408,
|
| 206 |
+
"step": 700
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.0022642522970449165,
|
| 210 |
+
"grad_norm": 2.6875,
|
| 211 |
+
"learning_rate": 4.522173641474079e-05,
|
| 212 |
+
"loss": 10.63,
|
| 213 |
+
"step": 725
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.0023423299624602584,
|
| 217 |
+
"grad_norm": 2.8125,
|
| 218 |
+
"learning_rate": 4.678326046221112e-05,
|
| 219 |
+
"loss": 10.6057,
|
| 220 |
+
"step": 750
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.0024204076278756003,
|
| 224 |
+
"grad_norm": 2.796875,
|
| 225 |
+
"learning_rate": 4.834478450968145e-05,
|
| 226 |
+
"loss": 10.5781,
|
| 227 |
+
"step": 775
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.0024984852932909423,
|
| 231 |
+
"grad_norm": 2.484375,
|
| 232 |
+
"learning_rate": 4.990630855715178e-05,
|
| 233 |
+
"loss": 10.5501,
|
| 234 |
+
"step": 800
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.002576562958706284,
|
| 238 |
+
"grad_norm": 3.171875,
|
| 239 |
+
"learning_rate": 5.1467832604622116e-05,
|
| 240 |
+
"loss": 10.5076,
|
| 241 |
+
"step": 825
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.002654640624121626,
|
| 245 |
+
"grad_norm": 3.078125,
|
| 246 |
+
"learning_rate": 5.3029356652092445e-05,
|
| 247 |
+
"loss": 10.477,
|
| 248 |
+
"step": 850
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.002732718289536968,
|
| 252 |
+
"grad_norm": 2.53125,
|
| 253 |
+
"learning_rate": 5.4590880699562774e-05,
|
| 254 |
+
"loss": 10.4528,
|
| 255 |
+
"step": 875
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.00281079595495231,
|
| 259 |
+
"grad_norm": 2.90625,
|
| 260 |
+
"learning_rate": 5.6152404747033104e-05,
|
| 261 |
+
"loss": 10.4192,
|
| 262 |
+
"step": 900
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.002888873620367652,
|
| 266 |
+
"grad_norm": 2.859375,
|
| 267 |
+
"learning_rate": 5.771392879450343e-05,
|
| 268 |
+
"loss": 10.3672,
|
| 269 |
+
"step": 925
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.002966951285782994,
|
| 273 |
+
"grad_norm": 3.078125,
|
| 274 |
+
"learning_rate": 5.927545284197377e-05,
|
| 275 |
+
"loss": 10.3219,
|
| 276 |
+
"step": 950
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.003045028951198336,
|
| 280 |
+
"grad_norm": 2.890625,
|
| 281 |
+
"learning_rate": 6.08369768894441e-05,
|
| 282 |
+
"loss": 10.3154,
|
| 283 |
+
"step": 975
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.003123106616613678,
|
| 287 |
+
"grad_norm": 3.125,
|
| 288 |
+
"learning_rate": 6.239850093691443e-05,
|
| 289 |
+
"loss": 10.2594,
|
| 290 |
+
"step": 1000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.003123106616613678,
|
| 294 |
+
"eval_loss": 10.227066993713379,
|
| 295 |
+
"eval_runtime": 102.2402,
|
| 296 |
+
"eval_samples_per_second": 50.89,
|
| 297 |
+
"eval_steps_per_second": 3.189,
|
| 298 |
+
"step": 1000
|
| 299 |
+
}
|
| 300 |
+
],
|
| 301 |
+
"logging_steps": 25,
|
| 302 |
+
"max_steps": 320194,
|
| 303 |
+
"num_input_tokens_seen": 0,
|
| 304 |
+
"num_train_epochs": 1,
|
| 305 |
+
"save_steps": 1000,
|
| 306 |
+
"stateful_callbacks": {
|
| 307 |
+
"TrainerControl": {
|
| 308 |
+
"args": {
|
| 309 |
+
"should_epoch_stop": false,
|
| 310 |
+
"should_evaluate": false,
|
| 311 |
+
"should_log": false,
|
| 312 |
+
"should_save": true,
|
| 313 |
+
"should_training_stop": false
|
| 314 |
+
},
|
| 315 |
+
"attributes": {}
|
| 316 |
+
}
|
| 317 |
+
},
|
| 318 |
+
"total_flos": 1.2682383335201178e+17,
|
| 319 |
+
"train_batch_size": 8,
|
| 320 |
+
"trial_name": null,
|
| 321 |
+
"trial_params": null
|
| 322 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:506dbfc2d414a423d9f6f7b5da859fa434e5990d545a7361ca3bc06e672d8c42
|
| 3 |
+
size 5777
|