Upload 8 files
Browse files- README.md +20 -0
- adapter_config.json +20 -0
- adapter_model.bin +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +436 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- load_in_8bit: False
|
| 9 |
+
- load_in_4bit: True
|
| 10 |
+
- llm_int8_threshold: 6.0
|
| 11 |
+
- llm_int8_skip_modules: None
|
| 12 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 13 |
+
- llm_int8_has_fp16_weight: False
|
| 14 |
+
- bnb_4bit_quant_type: nf4
|
| 15 |
+
- bnb_4bit_use_double_quant: False
|
| 16 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 17 |
+
### Framework versions
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- PEFT 0.4.0.dev0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "tiiuae/falcon-7b-instruct",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 32,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 16,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"query_key_value"
|
| 18 |
+
],
|
| 19 |
+
"task_type": "CAUSAL_LM"
|
| 20 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:544729b64865c8bdf58c498069d834b20c3460e8a270daac44f338474fa2e398
|
| 3 |
+
size 18898161
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa1d7fc8a94fab0592738e9beacbcf7ee91b1811bb7fdae0f15943ff1ab4b1c6
|
| 3 |
+
size 9539077
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76f60ddb2459b8641ae6750317d7006eb2ed3b713d68ce140bdf0a96114522a3
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:212844026f239c7567d85d5858e169db7dffce519d0343f436534ad63734d705
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,436 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.114571746384872,
|
| 5 |
+
"global_step": 700,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 5e-05,
|
| 13 |
+
"loss": 3.0439,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.09,
|
| 18 |
+
"learning_rate": 0.0001,
|
| 19 |
+
"loss": 3.1296,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.13,
|
| 24 |
+
"learning_rate": 0.00015000000000000001,
|
| 25 |
+
"loss": 2.6415,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.18,
|
| 30 |
+
"learning_rate": 0.0002,
|
| 31 |
+
"loss": 2.2394,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.22,
|
| 36 |
+
"learning_rate": 0.0001999145758387301,
|
| 37 |
+
"loss": 2.1922,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.27,
|
| 42 |
+
"learning_rate": 0.000199658449300667,
|
| 43 |
+
"loss": 2.1356,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.31,
|
| 48 |
+
"learning_rate": 0.0001992320579737045,
|
| 49 |
+
"loss": 2.1113,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.36,
|
| 54 |
+
"learning_rate": 0.00019863613034027224,
|
| 55 |
+
"loss": 2.0595,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.4,
|
| 60 |
+
"learning_rate": 0.00019787168453273544,
|
| 61 |
+
"loss": 2.176,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.44,
|
| 66 |
+
"learning_rate": 0.00019694002659393305,
|
| 67 |
+
"loss": 1.9658,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.49,
|
| 72 |
+
"learning_rate": 0.0001958427482458253,
|
| 73 |
+
"loss": 2.054,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.53,
|
| 78 |
+
"learning_rate": 0.00019458172417006347,
|
| 79 |
+
"loss": 1.9974,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.58,
|
| 84 |
+
"learning_rate": 0.0001931591088051279,
|
| 85 |
+
"loss": 2.08,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.62,
|
| 90 |
+
"learning_rate": 0.00019157733266550575,
|
| 91 |
+
"loss": 2.0511,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.67,
|
| 96 |
+
"learning_rate": 0.0001898390981891979,
|
| 97 |
+
"loss": 2.0537,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.71,
|
| 102 |
+
"learning_rate": 0.0001879473751206489,
|
| 103 |
+
"loss": 2.0272,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.76,
|
| 108 |
+
"learning_rate": 0.00018590539543698854,
|
| 109 |
+
"loss": 1.814,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.8,
|
| 114 |
+
"learning_rate": 0.00018371664782625287,
|
| 115 |
+
"loss": 1.9998,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.85,
|
| 120 |
+
"learning_rate": 0.0001813848717270195,
|
| 121 |
+
"loss": 2.0532,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.89,
|
| 126 |
+
"learning_rate": 0.00017891405093963938,
|
| 127 |
+
"loss": 1.9846,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.93,
|
| 132 |
+
"learning_rate": 0.00017630840681998066,
|
| 133 |
+
"loss": 2.0036,
|
| 134 |
+
"step": 210
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.98,
|
| 138 |
+
"learning_rate": 0.00017357239106731317,
|
| 139 |
+
"loss": 1.9404,
|
| 140 |
+
"step": 220
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.02,
|
| 144 |
+
"learning_rate": 0.00017071067811865476,
|
| 145 |
+
"loss": 2.0365,
|
| 146 |
+
"step": 230
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.07,
|
| 150 |
+
"learning_rate": 0.00016772815716257412,
|
| 151 |
+
"loss": 1.899,
|
| 152 |
+
"step": 240
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.11,
|
| 156 |
+
"learning_rate": 0.00016462992378609407,
|
| 157 |
+
"loss": 1.8882,
|
| 158 |
+
"step": 250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.16,
|
| 162 |
+
"learning_rate": 0.0001614212712689668,
|
| 163 |
+
"loss": 1.8806,
|
| 164 |
+
"step": 260
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.2,
|
| 168 |
+
"learning_rate": 0.00015810768154019385,
|
| 169 |
+
"loss": 1.8318,
|
| 170 |
+
"step": 270
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.25,
|
| 174 |
+
"learning_rate": 0.00015469481581224272,
|
| 175 |
+
"loss": 1.8892,
|
| 176 |
+
"step": 280
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.29,
|
| 180 |
+
"learning_rate": 0.00015118850490896012,
|
| 181 |
+
"loss": 1.8362,
|
| 182 |
+
"step": 290
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.33,
|
| 186 |
+
"learning_rate": 0.00014759473930370736,
|
| 187 |
+
"loss": 1.9268,
|
| 188 |
+
"step": 300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.38,
|
| 192 |
+
"learning_rate": 0.00014391965888473703,
|
| 193 |
+
"loss": 1.8581,
|
| 194 |
+
"step": 310
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.42,
|
| 198 |
+
"learning_rate": 0.00014016954246529696,
|
| 199 |
+
"loss": 1.928,
|
| 200 |
+
"step": 320
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.47,
|
| 204 |
+
"learning_rate": 0.00013635079705638298,
|
| 205 |
+
"loss": 1.8851,
|
| 206 |
+
"step": 330
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.51,
|
| 210 |
+
"learning_rate": 0.00013246994692046836,
|
| 211 |
+
"loss": 1.8826,
|
| 212 |
+
"step": 340
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.56,
|
| 216 |
+
"learning_rate": 0.00012853362242491053,
|
| 217 |
+
"loss": 1.9504,
|
| 218 |
+
"step": 350
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.6,
|
| 222 |
+
"learning_rate": 0.00012454854871407994,
|
| 223 |
+
"loss": 1.93,
|
| 224 |
+
"step": 360
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.65,
|
| 228 |
+
"learning_rate": 0.00012052153421956342,
|
| 229 |
+
"loss": 1.8744,
|
| 230 |
+
"step": 370
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.69,
|
| 234 |
+
"learning_rate": 0.00011645945902807341,
|
| 235 |
+
"loss": 1.9418,
|
| 236 |
+
"step": 380
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.74,
|
| 240 |
+
"learning_rate": 0.00011236926312693479,
|
| 241 |
+
"loss": 1.9751,
|
| 242 |
+
"step": 390
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.78,
|
| 246 |
+
"learning_rate": 0.00010825793454723325,
|
| 247 |
+
"loss": 1.7895,
|
| 248 |
+
"step": 400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.82,
|
| 252 |
+
"learning_rate": 0.00010413249742488131,
|
| 253 |
+
"loss": 2.0188,
|
| 254 |
+
"step": 410
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.87,
|
| 258 |
+
"learning_rate": 0.0001,
|
| 259 |
+
"loss": 1.9481,
|
| 260 |
+
"step": 420
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.91,
|
| 264 |
+
"learning_rate": 9.586750257511867e-05,
|
| 265 |
+
"loss": 1.9162,
|
| 266 |
+
"step": 430
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.96,
|
| 270 |
+
"learning_rate": 9.174206545276677e-05,
|
| 271 |
+
"loss": 1.8781,
|
| 272 |
+
"step": 440
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.0,
|
| 276 |
+
"learning_rate": 8.763073687306524e-05,
|
| 277 |
+
"loss": 1.8272,
|
| 278 |
+
"step": 450
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.05,
|
| 282 |
+
"learning_rate": 8.35405409719266e-05,
|
| 283 |
+
"loss": 1.7678,
|
| 284 |
+
"step": 460
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.09,
|
| 288 |
+
"learning_rate": 7.947846578043659e-05,
|
| 289 |
+
"loss": 1.7603,
|
| 290 |
+
"step": 470
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.14,
|
| 294 |
+
"learning_rate": 7.54514512859201e-05,
|
| 295 |
+
"loss": 1.812,
|
| 296 |
+
"step": 480
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.18,
|
| 300 |
+
"learning_rate": 7.146637757508949e-05,
|
| 301 |
+
"loss": 1.7061,
|
| 302 |
+
"step": 490
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.22,
|
| 306 |
+
"learning_rate": 6.753005307953167e-05,
|
| 307 |
+
"loss": 1.749,
|
| 308 |
+
"step": 500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.27,
|
| 312 |
+
"learning_rate": 6.3649202943617e-05,
|
| 313 |
+
"loss": 1.8795,
|
| 314 |
+
"step": 510
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.31,
|
| 318 |
+
"learning_rate": 5.983045753470308e-05,
|
| 319 |
+
"loss": 1.7342,
|
| 320 |
+
"step": 520
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.36,
|
| 324 |
+
"learning_rate": 5.608034111526298e-05,
|
| 325 |
+
"loss": 1.8323,
|
| 326 |
+
"step": 530
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.4,
|
| 330 |
+
"learning_rate": 5.240526069629265e-05,
|
| 331 |
+
"loss": 1.7113,
|
| 332 |
+
"step": 540
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.45,
|
| 336 |
+
"learning_rate": 4.8811495091039926e-05,
|
| 337 |
+
"loss": 1.6987,
|
| 338 |
+
"step": 550
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.49,
|
| 342 |
+
"learning_rate": 4.530518418775733e-05,
|
| 343 |
+
"loss": 1.7021,
|
| 344 |
+
"step": 560
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.54,
|
| 348 |
+
"learning_rate": 4.189231845980618e-05,
|
| 349 |
+
"loss": 1.7919,
|
| 350 |
+
"step": 570
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.58,
|
| 354 |
+
"learning_rate": 3.857872873103322e-05,
|
| 355 |
+
"loss": 1.8427,
|
| 356 |
+
"step": 580
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.63,
|
| 360 |
+
"learning_rate": 3.53700762139059e-05,
|
| 361 |
+
"loss": 1.7832,
|
| 362 |
+
"step": 590
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.67,
|
| 366 |
+
"learning_rate": 3.227184283742591e-05,
|
| 367 |
+
"loss": 1.5746,
|
| 368 |
+
"step": 600
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.71,
|
| 372 |
+
"learning_rate": 2.9289321881345254e-05,
|
| 373 |
+
"loss": 1.7318,
|
| 374 |
+
"step": 610
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.76,
|
| 378 |
+
"learning_rate": 2.6427608932686843e-05,
|
| 379 |
+
"loss": 1.7361,
|
| 380 |
+
"step": 620
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.8,
|
| 384 |
+
"learning_rate": 2.3691593180019366e-05,
|
| 385 |
+
"loss": 1.7565,
|
| 386 |
+
"step": 630
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.85,
|
| 390 |
+
"learning_rate": 2.1085949060360654e-05,
|
| 391 |
+
"loss": 1.6935,
|
| 392 |
+
"step": 640
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.89,
|
| 396 |
+
"learning_rate": 1.861512827298051e-05,
|
| 397 |
+
"loss": 1.6684,
|
| 398 |
+
"step": 650
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.94,
|
| 402 |
+
"learning_rate": 1.6283352173747145e-05,
|
| 403 |
+
"loss": 1.665,
|
| 404 |
+
"step": 660
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.98,
|
| 408 |
+
"learning_rate": 1.4094604563011472e-05,
|
| 409 |
+
"loss": 1.7024,
|
| 410 |
+
"step": 670
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 3.03,
|
| 414 |
+
"learning_rate": 1.2052624879351104e-05,
|
| 415 |
+
"loss": 1.6249,
|
| 416 |
+
"step": 680
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 3.07,
|
| 420 |
+
"learning_rate": 1.0160901810802115e-05,
|
| 421 |
+
"loss": 1.6777,
|
| 422 |
+
"step": 690
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 3.11,
|
| 426 |
+
"learning_rate": 8.422667334494249e-06,
|
| 427 |
+
"loss": 1.7344,
|
| 428 |
+
"step": 700
|
| 429 |
+
}
|
| 430 |
+
],
|
| 431 |
+
"max_steps": 800,
|
| 432 |
+
"num_train_epochs": 4,
|
| 433 |
+
"total_flos": 2.2824821692897536e+16,
|
| 434 |
+
"trial_name": null,
|
| 435 |
+
"trial_params": null
|
| 436 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:597f0e3b6a9e6e936460bb4b844f668bc44f15c6c3d41bd768ad1a6585bbfafc
|
| 3 |
+
size 3963
|