Commit
•
1a7b079
1
Parent(s):
55863a4
Upload 6 files
Browse files- config.json +28 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- rng_state.pth +3 -0
- trainer_state.json +385 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Qwen/Qwen1.5-0.5B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 2816,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 21,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 18 |
+
"num_key_value_heads": 16,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_theta": 1000000.0,
|
| 21 |
+
"sliding_window": 32768,
|
| 22 |
+
"tie_word_embeddings": true,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.40.0.dev0",
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"use_sliding_window": false,
|
| 27 |
+
"vocab_size": 151936
|
| 28 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.40.0.dev0"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4865833cb4ef64d7c2a54295de455a150317c33576a195accd3a402682ae575
|
| 3 |
+
size 1855983640
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2e155718eaa0de9768e57816e6e6874ba931ec4489afb1c2874db91c97f7a96
|
| 3 |
+
size 14244
|
trainer_state.json
ADDED
|
@@ -0,0 +1,385 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.8930602957906713,
|
| 5 |
+
"eval_steps": 100000,
|
| 6 |
+
"global_step": 5200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"grad_norm": 8.332918167114258,
|
| 14 |
+
"learning_rate": 9.999e-07,
|
| 15 |
+
"loss": 0.256,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07,
|
| 20 |
+
"grad_norm": 6.65649938583374,
|
| 21 |
+
"learning_rate": 9.998e-07,
|
| 22 |
+
"loss": 0.174,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.11,
|
| 27 |
+
"grad_norm": 5.654027462005615,
|
| 28 |
+
"learning_rate": 9.997e-07,
|
| 29 |
+
"loss": 0.1674,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.15,
|
| 34 |
+
"grad_norm": 6.793820858001709,
|
| 35 |
+
"learning_rate": 9.996e-07,
|
| 36 |
+
"loss": 0.1538,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.18,
|
| 41 |
+
"grad_norm": 5.857839107513428,
|
| 42 |
+
"learning_rate": 9.995e-07,
|
| 43 |
+
"loss": 0.1507,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.22,
|
| 48 |
+
"grad_norm": 6.979122638702393,
|
| 49 |
+
"learning_rate": 9.994e-07,
|
| 50 |
+
"loss": 0.1413,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.25,
|
| 55 |
+
"grad_norm": 3.4787421226501465,
|
| 56 |
+
"learning_rate": 9.993e-07,
|
| 57 |
+
"loss": 0.1426,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.29,
|
| 62 |
+
"grad_norm": 5.989820957183838,
|
| 63 |
+
"learning_rate": 9.992e-07,
|
| 64 |
+
"loss": 0.139,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.33,
|
| 69 |
+
"grad_norm": 4.455531597137451,
|
| 70 |
+
"learning_rate": 9.990999999999999e-07,
|
| 71 |
+
"loss": 0.145,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.36,
|
| 76 |
+
"grad_norm": 3.2097902297973633,
|
| 77 |
+
"learning_rate": 9.989999999999999e-07,
|
| 78 |
+
"loss": 0.1349,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.4,
|
| 83 |
+
"grad_norm": 4.64670467376709,
|
| 84 |
+
"learning_rate": 9.988999999999999e-07,
|
| 85 |
+
"loss": 0.1394,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.44,
|
| 90 |
+
"grad_norm": 6.975039958953857,
|
| 91 |
+
"learning_rate": 9.988e-07,
|
| 92 |
+
"loss": 0.1346,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.47,
|
| 97 |
+
"grad_norm": 7.464960098266602,
|
| 98 |
+
"learning_rate": 9.987e-07,
|
| 99 |
+
"loss": 0.1314,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.51,
|
| 104 |
+
"grad_norm": 4.806921482086182,
|
| 105 |
+
"learning_rate": 9.986e-07,
|
| 106 |
+
"loss": 0.131,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.55,
|
| 111 |
+
"grad_norm": 6.7189531326293945,
|
| 112 |
+
"learning_rate": 9.985e-07,
|
| 113 |
+
"loss": 0.1262,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.58,
|
| 118 |
+
"grad_norm": 5.656557559967041,
|
| 119 |
+
"learning_rate": 9.983999999999998e-07,
|
| 120 |
+
"loss": 0.1223,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.62,
|
| 125 |
+
"grad_norm": 4.686679363250732,
|
| 126 |
+
"learning_rate": 9.982999999999998e-07,
|
| 127 |
+
"loss": 0.1247,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.66,
|
| 132 |
+
"grad_norm": 5.541558265686035,
|
| 133 |
+
"learning_rate": 9.982e-07,
|
| 134 |
+
"loss": 0.1269,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.69,
|
| 139 |
+
"grad_norm": 6.699037551879883,
|
| 140 |
+
"learning_rate": 9.981e-07,
|
| 141 |
+
"loss": 0.1212,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.73,
|
| 146 |
+
"grad_norm": 7.294734001159668,
|
| 147 |
+
"learning_rate": 9.98e-07,
|
| 148 |
+
"loss": 0.1288,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.76,
|
| 153 |
+
"grad_norm": 6.782406806945801,
|
| 154 |
+
"learning_rate": 9.979e-07,
|
| 155 |
+
"loss": 0.1282,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8,
|
| 160 |
+
"grad_norm": 7.686770439147949,
|
| 161 |
+
"learning_rate": 9.978e-07,
|
| 162 |
+
"loss": 0.1252,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.84,
|
| 167 |
+
"grad_norm": 5.651573181152344,
|
| 168 |
+
"learning_rate": 9.977e-07,
|
| 169 |
+
"loss": 0.128,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.87,
|
| 174 |
+
"grad_norm": 3.8114349842071533,
|
| 175 |
+
"learning_rate": 9.976e-07,
|
| 176 |
+
"loss": 0.1189,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.91,
|
| 181 |
+
"grad_norm": 4.4628777503967285,
|
| 182 |
+
"learning_rate": 9.975e-07,
|
| 183 |
+
"loss": 0.1227,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.95,
|
| 188 |
+
"grad_norm": 3.973808526992798,
|
| 189 |
+
"learning_rate": 9.974e-07,
|
| 190 |
+
"loss": 0.1225,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.98,
|
| 195 |
+
"grad_norm": 7.216485977172852,
|
| 196 |
+
"learning_rate": 9.973e-07,
|
| 197 |
+
"loss": 0.1171,
|
| 198 |
+
"step": 2700
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.02,
|
| 202 |
+
"grad_norm": 4.588983058929443,
|
| 203 |
+
"learning_rate": 9.972e-07,
|
| 204 |
+
"loss": 0.1152,
|
| 205 |
+
"step": 2800
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.06,
|
| 209 |
+
"grad_norm": 2.4740259647369385,
|
| 210 |
+
"learning_rate": 9.971e-07,
|
| 211 |
+
"loss": 0.096,
|
| 212 |
+
"step": 2900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.09,
|
| 216 |
+
"grad_norm": 4.7505903244018555,
|
| 217 |
+
"learning_rate": 9.97e-07,
|
| 218 |
+
"loss": 0.0986,
|
| 219 |
+
"step": 3000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.13,
|
| 223 |
+
"grad_norm": 5.158182621002197,
|
| 224 |
+
"learning_rate": 9.969e-07,
|
| 225 |
+
"loss": 0.1006,
|
| 226 |
+
"step": 3100
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.16,
|
| 230 |
+
"grad_norm": 6.2976202964782715,
|
| 231 |
+
"learning_rate": 9.968e-07,
|
| 232 |
+
"loss": 0.0979,
|
| 233 |
+
"step": 3200
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.2,
|
| 237 |
+
"grad_norm": 5.02843713760376,
|
| 238 |
+
"learning_rate": 9.967e-07,
|
| 239 |
+
"loss": 0.0923,
|
| 240 |
+
"step": 3300
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.24,
|
| 244 |
+
"grad_norm": 5.816647052764893,
|
| 245 |
+
"learning_rate": 9.966e-07,
|
| 246 |
+
"loss": 0.1005,
|
| 247 |
+
"step": 3400
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.27,
|
| 251 |
+
"grad_norm": 5.387178421020508,
|
| 252 |
+
"learning_rate": 9.965e-07,
|
| 253 |
+
"loss": 0.0992,
|
| 254 |
+
"step": 3500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.31,
|
| 258 |
+
"grad_norm": 5.27618932723999,
|
| 259 |
+
"learning_rate": 9.964e-07,
|
| 260 |
+
"loss": 0.0945,
|
| 261 |
+
"step": 3600
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.35,
|
| 265 |
+
"grad_norm": 2.8429291248321533,
|
| 266 |
+
"learning_rate": 9.962999999999999e-07,
|
| 267 |
+
"loss": 0.0999,
|
| 268 |
+
"step": 3700
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.38,
|
| 272 |
+
"grad_norm": 3.8993031978607178,
|
| 273 |
+
"learning_rate": 9.961999999999999e-07,
|
| 274 |
+
"loss": 0.0946,
|
| 275 |
+
"step": 3800
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.42,
|
| 279 |
+
"grad_norm": 4.275607585906982,
|
| 280 |
+
"learning_rate": 9.960999999999999e-07,
|
| 281 |
+
"loss": 0.0943,
|
| 282 |
+
"step": 3900
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.46,
|
| 286 |
+
"grad_norm": 4.941762447357178,
|
| 287 |
+
"learning_rate": 9.959999999999999e-07,
|
| 288 |
+
"loss": 0.1011,
|
| 289 |
+
"step": 4000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.49,
|
| 293 |
+
"grad_norm": 3.800781726837158,
|
| 294 |
+
"learning_rate": 9.958999999999999e-07,
|
| 295 |
+
"loss": 0.096,
|
| 296 |
+
"step": 4100
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.53,
|
| 300 |
+
"grad_norm": 3.8520452976226807,
|
| 301 |
+
"learning_rate": 9.958e-07,
|
| 302 |
+
"loss": 0.0986,
|
| 303 |
+
"step": 4200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.57,
|
| 307 |
+
"grad_norm": 8.225783348083496,
|
| 308 |
+
"learning_rate": 9.957e-07,
|
| 309 |
+
"loss": 0.0935,
|
| 310 |
+
"step": 4300
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.6,
|
| 314 |
+
"grad_norm": 3.4622890949249268,
|
| 315 |
+
"learning_rate": 9.956e-07,
|
| 316 |
+
"loss": 0.0964,
|
| 317 |
+
"step": 4400
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.64,
|
| 321 |
+
"grad_norm": 4.632036209106445,
|
| 322 |
+
"learning_rate": 9.955e-07,
|
| 323 |
+
"loss": 0.0899,
|
| 324 |
+
"step": 4500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.67,
|
| 328 |
+
"grad_norm": 4.176944732666016,
|
| 329 |
+
"learning_rate": 9.953999999999998e-07,
|
| 330 |
+
"loss": 0.0947,
|
| 331 |
+
"step": 4600
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.71,
|
| 335 |
+
"grad_norm": 4.445220947265625,
|
| 336 |
+
"learning_rate": 9.952999999999998e-07,
|
| 337 |
+
"loss": 0.0882,
|
| 338 |
+
"step": 4700
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.75,
|
| 342 |
+
"grad_norm": 4.21484375,
|
| 343 |
+
"learning_rate": 9.952e-07,
|
| 344 |
+
"loss": 0.0987,
|
| 345 |
+
"step": 4800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.78,
|
| 349 |
+
"grad_norm": 7.656230449676514,
|
| 350 |
+
"learning_rate": 9.951e-07,
|
| 351 |
+
"loss": 0.0995,
|
| 352 |
+
"step": 4900
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.82,
|
| 356 |
+
"grad_norm": 4.51482629776001,
|
| 357 |
+
"learning_rate": 9.95e-07,
|
| 358 |
+
"loss": 0.092,
|
| 359 |
+
"step": 5000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.86,
|
| 363 |
+
"grad_norm": 4.313094139099121,
|
| 364 |
+
"learning_rate": 9.949e-07,
|
| 365 |
+
"loss": 0.0935,
|
| 366 |
+
"step": 5100
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.89,
|
| 370 |
+
"grad_norm": 5.037979602813721,
|
| 371 |
+
"learning_rate": 9.948e-07,
|
| 372 |
+
"loss": 0.0998,
|
| 373 |
+
"step": 5200
|
| 374 |
+
}
|
| 375 |
+
],
|
| 376 |
+
"logging_steps": 100,
|
| 377 |
+
"max_steps": 1000000,
|
| 378 |
+
"num_input_tokens_seen": 0,
|
| 379 |
+
"num_train_epochs": 365,
|
| 380 |
+
"save_steps": 200,
|
| 381 |
+
"total_flos": 3.542617035836621e+16,
|
| 382 |
+
"train_batch_size": 1,
|
| 383 |
+
"trial_name": null,
|
| 384 |
+
"trial_params": null
|
| 385 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3823135df21828411ae08d058ef138459927ddea750b967923c9d76e089e44d
|
| 3 |
+
size 4920
|