Upload folder using huggingface_hub (part 2)
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- checkpoint-144/rng_state_9.pth +3 -0
- checkpoint-144/scheduler.pt +3 -0
- checkpoint-144/tokenizer.json +3 -0
- checkpoint-144/tokenizer_config.json +32 -0
- checkpoint-144/trainer_state.json +314 -0
- checkpoint-144/training_args.bin +3 -0
- checkpoint-152/README.md +209 -0
- checkpoint-152/adapter_config.json +55 -0
- checkpoint-152/adapter_model.safetensors +3 -0
- checkpoint-152/chat_template.jinja +20 -0
- checkpoint-152/optimizer.pt +3 -0
- checkpoint-152/rng_state_0.pth +3 -0
- checkpoint-152/rng_state_1.pth +3 -0
- checkpoint-152/rng_state_10.pth +3 -0
- checkpoint-152/rng_state_11.pth +3 -0
- checkpoint-152/rng_state_12.pth +3 -0
- checkpoint-152/rng_state_13.pth +3 -0
- checkpoint-152/rng_state_14.pth +3 -0
- checkpoint-152/rng_state_15.pth +3 -0
- checkpoint-152/rng_state_16.pth +3 -0
- checkpoint-152/rng_state_17.pth +3 -0
- checkpoint-152/rng_state_18.pth +3 -0
- checkpoint-152/rng_state_19.pth +3 -0
- checkpoint-152/rng_state_2.pth +3 -0
- checkpoint-152/rng_state_20.pth +3 -0
- checkpoint-152/rng_state_21.pth +3 -0
- checkpoint-152/rng_state_22.pth +3 -0
- checkpoint-152/rng_state_23.pth +3 -0
- checkpoint-152/rng_state_24.pth +3 -0
- checkpoint-152/rng_state_25.pth +3 -0
- checkpoint-152/rng_state_26.pth +3 -0
- checkpoint-152/rng_state_27.pth +3 -0
- checkpoint-152/rng_state_28.pth +3 -0
- checkpoint-152/rng_state_29.pth +3 -0
- checkpoint-152/rng_state_3.pth +3 -0
- checkpoint-152/rng_state_30.pth +3 -0
- checkpoint-152/rng_state_31.pth +3 -0
- checkpoint-152/rng_state_4.pth +3 -0
- checkpoint-152/rng_state_5.pth +3 -0
- checkpoint-152/rng_state_6.pth +3 -0
- checkpoint-152/rng_state_7.pth +3 -0
- checkpoint-152/rng_state_8.pth +3 -0
- checkpoint-152/rng_state_9.pth +3 -0
- checkpoint-152/scheduler.pt +3 -0
- checkpoint-152/tokenizer.json +3 -0
- checkpoint-152/tokenizer_config.json +32 -0
- checkpoint-152/trainer_state.json +334 -0
- checkpoint-152/training_args.bin +3 -0
- checkpoint-160/README.md +209 -0
- checkpoint-160/adapter_config.json +55 -0
checkpoint-144/rng_state_9.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e0c53baa10c3f7bbc797afed620014c3354dc6129887af72ebe4af802a276cd
|
| 3 |
+
size 16389
|
checkpoint-144/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e974a563b4cf2d7b155094f237d692b5403539b809b4c68386103d62a66cb31
|
| 3 |
+
size 1465
|
checkpoint-144/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
checkpoint-144/tokenizer_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"local_files_only": false,
|
| 14 |
+
"model_max_length": 262144,
|
| 15 |
+
"model_specific_special_tokens": {
|
| 16 |
+
"audio_bos_token": "<|audio_start|>",
|
| 17 |
+
"audio_eos_token": "<|audio_end|>",
|
| 18 |
+
"audio_token": "<|audio_pad|>",
|
| 19 |
+
"image_token": "<|image_pad|>",
|
| 20 |
+
"video_token": "<|video_pad|>",
|
| 21 |
+
"vision_bos_token": "<|vision_start|>",
|
| 22 |
+
"vision_eos_token": "<|vision_end|>"
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|endoftext|>",
|
| 25 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"split_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
+
"unk_token": null,
|
| 29 |
+
"video_token": "<|video_pad|>",
|
| 30 |
+
"vision_bos_token": "<|vision_start|>",
|
| 31 |
+
"vision_eos_token": "<|vision_end|>"
|
| 32 |
+
}
|
checkpoint-144/trainer_state.json
ADDED
|
@@ -0,0 +1,314 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.2857142857142856,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 144,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 0.25798711776733396,
|
| 14 |
+
"epoch": 0.07936507936507936,
|
| 15 |
+
"grad_norm": 0.6395628452301025,
|
| 16 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 17 |
+
"loss": 0.33170533180236816,
|
| 18 |
+
"mean_token_accuracy": 0.9083019256591797,
|
| 19 |
+
"num_tokens": 2249744.0,
|
| 20 |
+
"step": 5
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 0.1518770933151245,
|
| 24 |
+
"epoch": 0.15873015873015872,
|
| 25 |
+
"grad_norm": 0.27742329239845276,
|
| 26 |
+
"learning_rate": 4.9966852247120764e-05,
|
| 27 |
+
"loss": 0.14515713453292847,
|
| 28 |
+
"mean_token_accuracy": 0.9476617932319641,
|
| 29 |
+
"num_tokens": 4502357.0,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 0.1205204889178276,
|
| 34 |
+
"epoch": 0.23809523809523808,
|
| 35 |
+
"grad_norm": 0.15280286967754364,
|
| 36 |
+
"learning_rate": 4.976460088644493e-05,
|
| 37 |
+
"loss": 0.11978392601013184,
|
| 38 |
+
"mean_token_accuracy": 0.9552689790725708,
|
| 39 |
+
"num_tokens": 6750630.0,
|
| 40 |
+
"step": 15
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.1094709500670433,
|
| 44 |
+
"epoch": 0.31746031746031744,
|
| 45 |
+
"grad_norm": 0.13621626794338226,
|
| 46 |
+
"learning_rate": 4.938000100611456e-05,
|
| 47 |
+
"loss": 0.10746543407440186,
|
| 48 |
+
"mean_token_accuracy": 0.9598726153373718,
|
| 49 |
+
"num_tokens": 8991471.0,
|
| 50 |
+
"step": 20
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.10419090241193771,
|
| 54 |
+
"epoch": 0.3968253968253968,
|
| 55 |
+
"grad_norm": 0.16320250928401947,
|
| 56 |
+
"learning_rate": 4.881588452008456e-05,
|
| 57 |
+
"loss": 0.10661067962646484,
|
| 58 |
+
"mean_token_accuracy": 0.9599695205688477,
|
| 59 |
+
"num_tokens": 11228489.0,
|
| 60 |
+
"step": 25
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.09569432139396668,
|
| 64 |
+
"epoch": 0.47619047619047616,
|
| 65 |
+
"grad_norm": 0.15873780846595764,
|
| 66 |
+
"learning_rate": 4.80764051721044e-05,
|
| 67 |
+
"loss": 0.09594419002532958,
|
| 68 |
+
"mean_token_accuracy": 0.9637031435966492,
|
| 69 |
+
"num_tokens": 13464387.0,
|
| 70 |
+
"step": 30
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 0.09625398516654968,
|
| 74 |
+
"epoch": 0.5555555555555556,
|
| 75 |
+
"grad_norm": 0.15297284722328186,
|
| 76 |
+
"learning_rate": 4.7167007950568505e-05,
|
| 77 |
+
"loss": 0.09495124220848083,
|
| 78 |
+
"mean_token_accuracy": 0.964220929145813,
|
| 79 |
+
"num_tokens": 15709681.0,
|
| 80 |
+
"step": 35
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 0.09195081293582916,
|
| 84 |
+
"epoch": 0.6349206349206349,
|
| 85 |
+
"grad_norm": 0.15219081938266754,
|
| 86 |
+
"learning_rate": 4.609438899557964e-05,
|
| 87 |
+
"loss": 0.09150891304016114,
|
| 88 |
+
"mean_token_accuracy": 0.9652478575706482,
|
| 89 |
+
"num_tokens": 17987403.0,
|
| 90 |
+
"step": 40
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"entropy": 0.08980809897184372,
|
| 94 |
+
"epoch": 0.7142857142857143,
|
| 95 |
+
"grad_norm": 0.1412411779165268,
|
| 96 |
+
"learning_rate": 4.4866446293440626e-05,
|
| 97 |
+
"loss": 0.0898817539215088,
|
| 98 |
+
"mean_token_accuracy": 0.965602707862854,
|
| 99 |
+
"num_tokens": 20231746.0,
|
| 100 |
+
"step": 45
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"entropy": 0.08743101209402085,
|
| 104 |
+
"epoch": 0.7936507936507936,
|
| 105 |
+
"grad_norm": 0.16695629060268402,
|
| 106 |
+
"learning_rate": 4.3492221521624174e-05,
|
| 107 |
+
"loss": 0.08715485334396363,
|
| 108 |
+
"mean_token_accuracy": 0.9668790459632873,
|
| 109 |
+
"num_tokens": 22491762.0,
|
| 110 |
+
"step": 50
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"entropy": 0.08765677958726883,
|
| 114 |
+
"epoch": 0.873015873015873,
|
| 115 |
+
"grad_norm": 0.21143023669719696,
|
| 116 |
+
"learning_rate": 4.198183347243233e-05,
|
| 117 |
+
"loss": 0.08766236305236816,
|
| 118 |
+
"mean_token_accuracy": 0.9668452143669128,
|
| 119 |
+
"num_tokens": 24752715.0,
|
| 120 |
+
"step": 55
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"entropy": 0.08127444982528687,
|
| 124 |
+
"epoch": 0.9523809523809523,
|
| 125 |
+
"grad_norm": 0.18779045343399048,
|
| 126 |
+
"learning_rate": 4.03464035455653e-05,
|
| 127 |
+
"loss": 0.08236484527587891,
|
| 128 |
+
"mean_token_accuracy": 0.9689654350280762,
|
| 129 |
+
"num_tokens": 26982538.0,
|
| 130 |
+
"step": 60
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"entropy": 0.07894417196512223,
|
| 134 |
+
"epoch": 1.0317460317460316,
|
| 135 |
+
"grad_norm": 0.1385810822248459,
|
| 136 |
+
"learning_rate": 3.859797385821812e-05,
|
| 137 |
+
"loss": 0.0778856873512268,
|
| 138 |
+
"mean_token_accuracy": 0.9699163198471069,
|
| 139 |
+
"num_tokens": 29221704.0,
|
| 140 |
+
"step": 65
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"entropy": 0.07985353171825409,
|
| 144 |
+
"epoch": 1.1111111111111112,
|
| 145 |
+
"grad_norm": 0.16439372301101685,
|
| 146 |
+
"learning_rate": 3.6749418575683e-05,
|
| 147 |
+
"loss": 0.07885851860046386,
|
| 148 |
+
"mean_token_accuracy": 0.969633674621582,
|
| 149 |
+
"num_tokens": 31470338.0,
|
| 150 |
+
"step": 70
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"entropy": 0.07194689065217971,
|
| 154 |
+
"epoch": 1.1904761904761905,
|
| 155 |
+
"grad_norm": 0.16862133145332336,
|
| 156 |
+
"learning_rate": 3.48143491153543e-05,
|
| 157 |
+
"loss": 0.074225252866745,
|
| 158 |
+
"mean_token_accuracy": 0.9716025114059448,
|
| 159 |
+
"num_tokens": 33719303.0,
|
| 160 |
+
"step": 75
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"entropy": 0.07757648378610611,
|
| 164 |
+
"epoch": 1.2698412698412698,
|
| 165 |
+
"grad_norm": 0.14261098206043243,
|
| 166 |
+
"learning_rate": 3.280701392214487e-05,
|
| 167 |
+
"loss": 0.07595503330230713,
|
| 168 |
+
"mean_token_accuracy": 0.9707554697990417,
|
| 169 |
+
"num_tokens": 35977913.0,
|
| 170 |
+
"step": 80
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"entropy": 0.07388863414525985,
|
| 174 |
+
"epoch": 1.3492063492063493,
|
| 175 |
+
"grad_norm": 0.16554316878318787,
|
| 176 |
+
"learning_rate": 3.07421935532949e-05,
|
| 177 |
+
"loss": 0.07574511766433716,
|
| 178 |
+
"mean_token_accuracy": 0.9704798936843873,
|
| 179 |
+
"num_tokens": 38220353.0,
|
| 180 |
+
"step": 85
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"entropy": 0.07249651849269867,
|
| 184 |
+
"epoch": 1.4285714285714286,
|
| 185 |
+
"grad_norm": 0.18186147511005402,
|
| 186 |
+
"learning_rate": 2.8635091845092247e-05,
|
| 187 |
+
"loss": 0.07062947750091553,
|
| 188 |
+
"mean_token_accuracy": 0.9724894285202026,
|
| 189 |
+
"num_tokens": 40476134.0,
|
| 190 |
+
"step": 90
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"entropy": 0.06985943019390106,
|
| 194 |
+
"epoch": 1.507936507936508,
|
| 195 |
+
"grad_norm": 0.13512398302555084,
|
| 196 |
+
"learning_rate": 2.650122396287371e-05,
|
| 197 |
+
"loss": 0.06756666898727418,
|
| 198 |
+
"mean_token_accuracy": 0.9738536238670349,
|
| 199 |
+
"num_tokens": 42711931.0,
|
| 200 |
+
"step": 95
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"entropy": 0.06709291264414788,
|
| 204 |
+
"epoch": 1.5873015873015874,
|
| 205 |
+
"grad_norm": 0.13330888748168945,
|
| 206 |
+
"learning_rate": 2.4356302158625288e-05,
|
| 207 |
+
"loss": 0.07059981226921082,
|
| 208 |
+
"mean_token_accuracy": 0.9723513960838318,
|
| 209 |
+
"num_tokens": 44948562.0,
|
| 210 |
+
"step": 100
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"entropy": 0.06978753134608269,
|
| 214 |
+
"epoch": 1.6666666666666665,
|
| 215 |
+
"grad_norm": 0.16254326701164246,
|
| 216 |
+
"learning_rate": 2.221612007737978e-05,
|
| 217 |
+
"loss": 0.06924379467964173,
|
| 218 |
+
"mean_token_accuracy": 0.9731807231903076,
|
| 219 |
+
"num_tokens": 47194289.0,
|
| 220 |
+
"step": 105
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"entropy": 0.06934378147125245,
|
| 224 |
+
"epoch": 1.746031746031746,
|
| 225 |
+
"grad_norm": 0.13457117974758148,
|
| 226 |
+
"learning_rate": 2.009643646429508e-05,
|
| 227 |
+
"loss": 0.06761763095855713,
|
| 228 |
+
"mean_token_accuracy": 0.9738588094711303,
|
| 229 |
+
"num_tokens": 49437033.0,
|
| 230 |
+
"step": 110
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"entropy": 0.06849471032619477,
|
| 234 |
+
"epoch": 1.8253968253968254,
|
| 235 |
+
"grad_norm": 0.14807309210300446,
|
| 236 |
+
"learning_rate": 1.8012859128709766e-05,
|
| 237 |
+
"loss": 0.06851363182067871,
|
| 238 |
+
"mean_token_accuracy": 0.9734799265861511,
|
| 239 |
+
"num_tokens": 51685754.0,
|
| 240 |
+
"step": 115
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"entropy": 0.06743545532226562,
|
| 244 |
+
"epoch": 1.9047619047619047,
|
| 245 |
+
"grad_norm": 0.14509981870651245,
|
| 246 |
+
"learning_rate": 1.598073001958042e-05,
|
| 247 |
+
"loss": 0.06817712187767029,
|
| 248 |
+
"mean_token_accuracy": 0.9735557198524475,
|
| 249 |
+
"num_tokens": 53931825.0,
|
| 250 |
+
"step": 120
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"entropy": 0.06640436649322509,
|
| 254 |
+
"epoch": 1.9841269841269842,
|
| 255 |
+
"grad_norm": 0.13425911962985992,
|
| 256 |
+
"learning_rate": 1.4015012258521454e-05,
|
| 257 |
+
"loss": 0.0663202166557312,
|
| 258 |
+
"mean_token_accuracy": 0.9740958571434021,
|
| 259 |
+
"num_tokens": 56203400.0,
|
| 260 |
+
"step": 125
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"entropy": 0.06114112734794617,
|
| 264 |
+
"epoch": 2.0634920634920633,
|
| 265 |
+
"grad_norm": 0.14675261080265045,
|
| 266 |
+
"learning_rate": 1.213017996225424e-05,
|
| 267 |
+
"loss": 0.0597736656665802,
|
| 268 |
+
"mean_token_accuracy": 0.9770057320594787,
|
| 269 |
+
"num_tokens": 58447264.0,
|
| 270 |
+
"step": 130
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"entropy": 0.06077109202742577,
|
| 274 |
+
"epoch": 2.142857142857143,
|
| 275 |
+
"grad_norm": 0.14722956717014313,
|
| 276 |
+
"learning_rate": 1.034011166573261e-05,
|
| 277 |
+
"loss": 0.0608077347278595,
|
| 278 |
+
"mean_token_accuracy": 0.9764052987098694,
|
| 279 |
+
"num_tokens": 60680203.0,
|
| 280 |
+
"step": 135
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"entropy": 0.06085996180772781,
|
| 284 |
+
"epoch": 2.2222222222222223,
|
| 285 |
+
"grad_norm": 0.13919851183891296,
|
| 286 |
+
"learning_rate": 8.657988130699848e-06,
|
| 287 |
+
"loss": 0.06093168258666992,
|
| 288 |
+
"mean_token_accuracy": 0.975907814502716,
|
| 289 |
+
"num_tokens": 62928491.0,
|
| 290 |
+
"step": 140
|
| 291 |
+
}
|
| 292 |
+
],
|
| 293 |
+
"logging_steps": 5,
|
| 294 |
+
"max_steps": 189,
|
| 295 |
+
"num_input_tokens_seen": 0,
|
| 296 |
+
"num_train_epochs": 3,
|
| 297 |
+
"save_steps": 8,
|
| 298 |
+
"stateful_callbacks": {
|
| 299 |
+
"TrainerControl": {
|
| 300 |
+
"args": {
|
| 301 |
+
"should_epoch_stop": false,
|
| 302 |
+
"should_evaluate": false,
|
| 303 |
+
"should_log": false,
|
| 304 |
+
"should_save": true,
|
| 305 |
+
"should_training_stop": false
|
| 306 |
+
},
|
| 307 |
+
"attributes": {}
|
| 308 |
+
}
|
| 309 |
+
},
|
| 310 |
+
"total_flos": 3.609685068986974e+18,
|
| 311 |
+
"train_batch_size": 4,
|
| 312 |
+
"trial_name": null,
|
| 313 |
+
"trial_params": null
|
| 314 |
+
}
|
checkpoint-144/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63584b641880ca8f7031099a802ca6e2de6c8e3fdacc7cdffeaa3f69e77b5a9a
|
| 3 |
+
size 5969
|
checkpoint-152/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3.5-9B
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen3.5-9B
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.20.0
|
checkpoint-152/adapter_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3.5-9B",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 256,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"monteclora_config": null,
|
| 27 |
+
"peft_type": "LORA",
|
| 28 |
+
"peft_version": "0.20.0",
|
| 29 |
+
"qalora_group_size": 16,
|
| 30 |
+
"r": 128,
|
| 31 |
+
"rank_pattern": {},
|
| 32 |
+
"revision": null,
|
| 33 |
+
"target_modules": [
|
| 34 |
+
"in_proj_a",
|
| 35 |
+
"up_proj",
|
| 36 |
+
"gate_proj",
|
| 37 |
+
"o_proj",
|
| 38 |
+
"in_proj_z",
|
| 39 |
+
"v_proj",
|
| 40 |
+
"down_proj",
|
| 41 |
+
"in_proj_b",
|
| 42 |
+
"q_proj",
|
| 43 |
+
"out_proj",
|
| 44 |
+
"in_proj_qkv",
|
| 45 |
+
"k_proj"
|
| 46 |
+
],
|
| 47 |
+
"target_parameters": null,
|
| 48 |
+
"task_type": "CAUSAL_LM",
|
| 49 |
+
"trainable_token_indices": null,
|
| 50 |
+
"use_bdlora": null,
|
| 51 |
+
"use_dora": false,
|
| 52 |
+
"use_qalora": false,
|
| 53 |
+
"use_rslora": false,
|
| 54 |
+
"velora_config": null
|
| 55 |
+
}
|
checkpoint-152/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2edaaecd98438b73a28926cd659fddc9f4e4865a69ba1def5ebcfd05c984d74c
|
| 3 |
+
size 1384975816
|
checkpoint-152/chat_template.jinja
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if messages and messages[0].role == 'system' %}
|
| 2 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 3 |
+
{%- set loop_messages = messages[1:] %}
|
| 4 |
+
{%- else %}
|
| 5 |
+
{%- set loop_messages = messages %}
|
| 6 |
+
{%- endif %}
|
| 7 |
+
{%- for message in loop_messages %}
|
| 8 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 9 |
+
{%- if message.role == 'assistant' %}
|
| 10 |
+
{% generation %}{{- message.content + '<|im_end|>' }}{% endgeneration %}{{- '\n' }}
|
| 11 |
+
{%- else %}
|
| 12 |
+
{{- message.content + '<|im_end|>\n' }}
|
| 13 |
+
{%- endif %}
|
| 14 |
+
{%- endfor %}
|
| 15 |
+
{%- if add_generation_prompt %}
|
| 16 |
+
{{- '<|im_start|>assistant\n' }}
|
| 17 |
+
{%- if enable_thinking is not defined or not enable_thinking %}
|
| 18 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
checkpoint-152/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d68d0948e0c8288b7cf572516c525c40ce29cb4e29acc35f7c4587d517f978c0
|
| 3 |
+
size 2770239667
|
checkpoint-152/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0b30b11d9f33d91c7bcf02e341a59ac6524a8a360e2083b5676a78e25596c0e
|
| 3 |
+
size 16389
|
checkpoint-152/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8380d4da325f3707ff76c2f787f61ea3b1de18bd17c61a9c3ce75b1d988b2e28
|
| 3 |
+
size 16389
|
checkpoint-152/rng_state_10.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:971dfe429ee3fe6ecebc3dbb9f6b0c994c43220c9790f030592bd8f5031dd1b1
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_11.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8660952010354e1f5125288961973ceac30d62cc3ee56b27ac81229d7d5d06b3
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_12.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c24f89ad476fbe08d7eb735c901e7af0f3c049afe8e1c200cf3554b147fc742
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_13.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0300c025a31d2a5f87c32cd300912e8fe9c329915328dc97dbb16f6a346d102d
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_14.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd3753d31ac7cf44f403ea011af585c1167b70ab879e2373690486374eafd52e
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_15.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e36bb39d7b59ef27b42d259e6d9ff6830e100f6f445ab49a6ac3e88d4dd0bbdc
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_16.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:810c0bcff19f59474412ea63bbe668ad3f83670b28ed13645c7396a762777f02
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_17.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39520afbd6d1613ab8382b740bedec4b68194c807f7d54bc54bc816c7c14002a
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_18.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc5ac19fa5636053e53fdcb668ce1a5d3cba1c1a6e5d1056bf05c2935b3bd074
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_19.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e97609728ca998827635cb1b4cb23b0536833993870f1c8a0d8ea7fc66bf429
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5927461517cbfca54f3318107f1f73e6a46ca4e7789b90f41f7c888cb1bcbc5b
|
| 3 |
+
size 16389
|
checkpoint-152/rng_state_20.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4a4885228c3c9037416abdbab65690ce75e28493983f91f123ea4a0a20553f0
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_21.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f240687e3aaa70f4cae52421a4b28fffc5b85c39a01d9a5f878518d4a74fa590
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_22.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2cb504adc16869e88d7ece06d13e48e2331628b32b4d057e9e15c8a2a3a76ff
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_23.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d3cbc24cc8e00c9f724d8d99ecd2c9ec370dcb5a41c9c09047272a83fe0ba68
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_24.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:453f1afbc3bc83a8b1f349ad34c336866183508f3dbae1dda497b72b7ffc12ff
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_25.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ba1c6c5443ad94f98d4b9452586470f24f17909271d3e4d06dc820d5fcb87df
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_26.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:509a644b57548ceb7eb5edb75eef7bbdc7f34a4721bb9852f7445c8b5e9e32b8
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_27.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1a54cc3124146e218df0907aca6c13747459de14572b13cc77b7a02568bd6e9
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_28.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:541aa0d50af4827c96bbe92db001502b56436edf643ae852b4dfc40efc7590c4
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_29.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92eb096c79f83ad338af93fead4452ce6f9d4f6bc90808601f4debf9e0c4ad29
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25441b8817383163c1f117d4cc028ea819ca9563b2f8487c2d2c441e959f49cd
|
| 3 |
+
size 16389
|
checkpoint-152/rng_state_30.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a33888fc4467183272841759a1fa7cb0dddc02dcf1a15f1f36d60d978a6884d4
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_31.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae980258ed44b36f67af3e9ff5103a73820ea9f550a1e6c21e1d7c1c124eb679
|
| 3 |
+
size 16404
|
checkpoint-152/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f596d71bd50636afdde88fb7c66a9548eab0330d7b32ab88933a8f3efd7e2b5
|
| 3 |
+
size 16389
|
checkpoint-152/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47f526c0754504badcf137a61eb13caa7101e2476e3dbbb50af8f6d84e4ef72a
|
| 3 |
+
size 16389
|
checkpoint-152/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b88c7948e5555a9a87336f99ddae2f3fad239383b2e154264499bbdb9ee69ac8
|
| 3 |
+
size 16389
|
checkpoint-152/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f0b1dbe82aa2b965b606363d8aa54718f77bb64150455f460de3319562f0d54
|
| 3 |
+
size 16389
|
checkpoint-152/rng_state_8.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09b4a7d45fcc95f84ab6b400d74dfacb7f7b2ea38b5ef1ff105df8aa343c4a98
|
| 3 |
+
size 16389
|
checkpoint-152/rng_state_9.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a93f717098002279b609755dac4d39c0565f63b9731e0deb3964f9c27f332f22
|
| 3 |
+
size 16389
|
checkpoint-152/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6f16e67122541f81beb25aa5d1a92ef46493e35c25e08c6d488cfeb37fe4725
|
| 3 |
+
size 1465
|
checkpoint-152/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
checkpoint-152/tokenizer_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"local_files_only": false,
|
| 14 |
+
"model_max_length": 262144,
|
| 15 |
+
"model_specific_special_tokens": {
|
| 16 |
+
"audio_bos_token": "<|audio_start|>",
|
| 17 |
+
"audio_eos_token": "<|audio_end|>",
|
| 18 |
+
"audio_token": "<|audio_pad|>",
|
| 19 |
+
"image_token": "<|image_pad|>",
|
| 20 |
+
"video_token": "<|video_pad|>",
|
| 21 |
+
"vision_bos_token": "<|vision_start|>",
|
| 22 |
+
"vision_eos_token": "<|vision_end|>"
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|endoftext|>",
|
| 25 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"split_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
+
"unk_token": null,
|
| 29 |
+
"video_token": "<|video_pad|>",
|
| 30 |
+
"vision_bos_token": "<|vision_start|>",
|
| 31 |
+
"vision_eos_token": "<|vision_end|>"
|
| 32 |
+
}
|
checkpoint-152/trainer_state.json
ADDED
|
@@ -0,0 +1,334 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.4126984126984126,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 152,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 0.25798711776733396,
|
| 14 |
+
"epoch": 0.07936507936507936,
|
| 15 |
+
"grad_norm": 0.6395628452301025,
|
| 16 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 17 |
+
"loss": 0.33170533180236816,
|
| 18 |
+
"mean_token_accuracy": 0.9083019256591797,
|
| 19 |
+
"num_tokens": 2249744.0,
|
| 20 |
+
"step": 5
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 0.1518770933151245,
|
| 24 |
+
"epoch": 0.15873015873015872,
|
| 25 |
+
"grad_norm": 0.27742329239845276,
|
| 26 |
+
"learning_rate": 4.9966852247120764e-05,
|
| 27 |
+
"loss": 0.14515713453292847,
|
| 28 |
+
"mean_token_accuracy": 0.9476617932319641,
|
| 29 |
+
"num_tokens": 4502357.0,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 0.1205204889178276,
|
| 34 |
+
"epoch": 0.23809523809523808,
|
| 35 |
+
"grad_norm": 0.15280286967754364,
|
| 36 |
+
"learning_rate": 4.976460088644493e-05,
|
| 37 |
+
"loss": 0.11978392601013184,
|
| 38 |
+
"mean_token_accuracy": 0.9552689790725708,
|
| 39 |
+
"num_tokens": 6750630.0,
|
| 40 |
+
"step": 15
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.1094709500670433,
|
| 44 |
+
"epoch": 0.31746031746031744,
|
| 45 |
+
"grad_norm": 0.13621626794338226,
|
| 46 |
+
"learning_rate": 4.938000100611456e-05,
|
| 47 |
+
"loss": 0.10746543407440186,
|
| 48 |
+
"mean_token_accuracy": 0.9598726153373718,
|
| 49 |
+
"num_tokens": 8991471.0,
|
| 50 |
+
"step": 20
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.10419090241193771,
|
| 54 |
+
"epoch": 0.3968253968253968,
|
| 55 |
+
"grad_norm": 0.16320250928401947,
|
| 56 |
+
"learning_rate": 4.881588452008456e-05,
|
| 57 |
+
"loss": 0.10661067962646484,
|
| 58 |
+
"mean_token_accuracy": 0.9599695205688477,
|
| 59 |
+
"num_tokens": 11228489.0,
|
| 60 |
+
"step": 25
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.09569432139396668,
|
| 64 |
+
"epoch": 0.47619047619047616,
|
| 65 |
+
"grad_norm": 0.15873780846595764,
|
| 66 |
+
"learning_rate": 4.80764051721044e-05,
|
| 67 |
+
"loss": 0.09594419002532958,
|
| 68 |
+
"mean_token_accuracy": 0.9637031435966492,
|
| 69 |
+
"num_tokens": 13464387.0,
|
| 70 |
+
"step": 30
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 0.09625398516654968,
|
| 74 |
+
"epoch": 0.5555555555555556,
|
| 75 |
+
"grad_norm": 0.15297284722328186,
|
| 76 |
+
"learning_rate": 4.7167007950568505e-05,
|
| 77 |
+
"loss": 0.09495124220848083,
|
| 78 |
+
"mean_token_accuracy": 0.964220929145813,
|
| 79 |
+
"num_tokens": 15709681.0,
|
| 80 |
+
"step": 35
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 0.09195081293582916,
|
| 84 |
+
"epoch": 0.6349206349206349,
|
| 85 |
+
"grad_norm": 0.15219081938266754,
|
| 86 |
+
"learning_rate": 4.609438899557964e-05,
|
| 87 |
+
"loss": 0.09150891304016114,
|
| 88 |
+
"mean_token_accuracy": 0.9652478575706482,
|
| 89 |
+
"num_tokens": 17987403.0,
|
| 90 |
+
"step": 40
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"entropy": 0.08980809897184372,
|
| 94 |
+
"epoch": 0.7142857142857143,
|
| 95 |
+
"grad_norm": 0.1412411779165268,
|
| 96 |
+
"learning_rate": 4.4866446293440626e-05,
|
| 97 |
+
"loss": 0.0898817539215088,
|
| 98 |
+
"mean_token_accuracy": 0.965602707862854,
|
| 99 |
+
"num_tokens": 20231746.0,
|
| 100 |
+
"step": 45
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"entropy": 0.08743101209402085,
|
| 104 |
+
"epoch": 0.7936507936507936,
|
| 105 |
+
"grad_norm": 0.16695629060268402,
|
| 106 |
+
"learning_rate": 4.3492221521624174e-05,
|
| 107 |
+
"loss": 0.08715485334396363,
|
| 108 |
+
"mean_token_accuracy": 0.9668790459632873,
|
| 109 |
+
"num_tokens": 22491762.0,
|
| 110 |
+
"step": 50
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"entropy": 0.08765677958726883,
|
| 114 |
+
"epoch": 0.873015873015873,
|
| 115 |
+
"grad_norm": 0.21143023669719696,
|
| 116 |
+
"learning_rate": 4.198183347243233e-05,
|
| 117 |
+
"loss": 0.08766236305236816,
|
| 118 |
+
"mean_token_accuracy": 0.9668452143669128,
|
| 119 |
+
"num_tokens": 24752715.0,
|
| 120 |
+
"step": 55
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"entropy": 0.08127444982528687,
|
| 124 |
+
"epoch": 0.9523809523809523,
|
| 125 |
+
"grad_norm": 0.18779045343399048,
|
| 126 |
+
"learning_rate": 4.03464035455653e-05,
|
| 127 |
+
"loss": 0.08236484527587891,
|
| 128 |
+
"mean_token_accuracy": 0.9689654350280762,
|
| 129 |
+
"num_tokens": 26982538.0,
|
| 130 |
+
"step": 60
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"entropy": 0.07894417196512223,
|
| 134 |
+
"epoch": 1.0317460317460316,
|
| 135 |
+
"grad_norm": 0.1385810822248459,
|
| 136 |
+
"learning_rate": 3.859797385821812e-05,
|
| 137 |
+
"loss": 0.0778856873512268,
|
| 138 |
+
"mean_token_accuracy": 0.9699163198471069,
|
| 139 |
+
"num_tokens": 29221704.0,
|
| 140 |
+
"step": 65
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"entropy": 0.07985353171825409,
|
| 144 |
+
"epoch": 1.1111111111111112,
|
| 145 |
+
"grad_norm": 0.16439372301101685,
|
| 146 |
+
"learning_rate": 3.6749418575683e-05,
|
| 147 |
+
"loss": 0.07885851860046386,
|
| 148 |
+
"mean_token_accuracy": 0.969633674621582,
|
| 149 |
+
"num_tokens": 31470338.0,
|
| 150 |
+
"step": 70
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"entropy": 0.07194689065217971,
|
| 154 |
+
"epoch": 1.1904761904761905,
|
| 155 |
+
"grad_norm": 0.16862133145332336,
|
| 156 |
+
"learning_rate": 3.48143491153543e-05,
|
| 157 |
+
"loss": 0.074225252866745,
|
| 158 |
+
"mean_token_accuracy": 0.9716025114059448,
|
| 159 |
+
"num_tokens": 33719303.0,
|
| 160 |
+
"step": 75
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"entropy": 0.07757648378610611,
|
| 164 |
+
"epoch": 1.2698412698412698,
|
| 165 |
+
"grad_norm": 0.14261098206043243,
|
| 166 |
+
"learning_rate": 3.280701392214487e-05,
|
| 167 |
+
"loss": 0.07595503330230713,
|
| 168 |
+
"mean_token_accuracy": 0.9707554697990417,
|
| 169 |
+
"num_tokens": 35977913.0,
|
| 170 |
+
"step": 80
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"entropy": 0.07388863414525985,
|
| 174 |
+
"epoch": 1.3492063492063493,
|
| 175 |
+
"grad_norm": 0.16554316878318787,
|
| 176 |
+
"learning_rate": 3.07421935532949e-05,
|
| 177 |
+
"loss": 0.07574511766433716,
|
| 178 |
+
"mean_token_accuracy": 0.9704798936843873,
|
| 179 |
+
"num_tokens": 38220353.0,
|
| 180 |
+
"step": 85
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"entropy": 0.07249651849269867,
|
| 184 |
+
"epoch": 1.4285714285714286,
|
| 185 |
+
"grad_norm": 0.18186147511005402,
|
| 186 |
+
"learning_rate": 2.8635091845092247e-05,
|
| 187 |
+
"loss": 0.07062947750091553,
|
| 188 |
+
"mean_token_accuracy": 0.9724894285202026,
|
| 189 |
+
"num_tokens": 40476134.0,
|
| 190 |
+
"step": 90
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"entropy": 0.06985943019390106,
|
| 194 |
+
"epoch": 1.507936507936508,
|
| 195 |
+
"grad_norm": 0.13512398302555084,
|
| 196 |
+
"learning_rate": 2.650122396287371e-05,
|
| 197 |
+
"loss": 0.06756666898727418,
|
| 198 |
+
"mean_token_accuracy": 0.9738536238670349,
|
| 199 |
+
"num_tokens": 42711931.0,
|
| 200 |
+
"step": 95
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"entropy": 0.06709291264414788,
|
| 204 |
+
"epoch": 1.5873015873015874,
|
| 205 |
+
"grad_norm": 0.13330888748168945,
|
| 206 |
+
"learning_rate": 2.4356302158625288e-05,
|
| 207 |
+
"loss": 0.07059981226921082,
|
| 208 |
+
"mean_token_accuracy": 0.9723513960838318,
|
| 209 |
+
"num_tokens": 44948562.0,
|
| 210 |
+
"step": 100
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"entropy": 0.06978753134608269,
|
| 214 |
+
"epoch": 1.6666666666666665,
|
| 215 |
+
"grad_norm": 0.16254326701164246,
|
| 216 |
+
"learning_rate": 2.221612007737978e-05,
|
| 217 |
+
"loss": 0.06924379467964173,
|
| 218 |
+
"mean_token_accuracy": 0.9731807231903076,
|
| 219 |
+
"num_tokens": 47194289.0,
|
| 220 |
+
"step": 105
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"entropy": 0.06934378147125245,
|
| 224 |
+
"epoch": 1.746031746031746,
|
| 225 |
+
"grad_norm": 0.13457117974758148,
|
| 226 |
+
"learning_rate": 2.009643646429508e-05,
|
| 227 |
+
"loss": 0.06761763095855713,
|
| 228 |
+
"mean_token_accuracy": 0.9738588094711303,
|
| 229 |
+
"num_tokens": 49437033.0,
|
| 230 |
+
"step": 110
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"entropy": 0.06849471032619477,
|
| 234 |
+
"epoch": 1.8253968253968254,
|
| 235 |
+
"grad_norm": 0.14807309210300446,
|
| 236 |
+
"learning_rate": 1.8012859128709766e-05,
|
| 237 |
+
"loss": 0.06851363182067871,
|
| 238 |
+
"mean_token_accuracy": 0.9734799265861511,
|
| 239 |
+
"num_tokens": 51685754.0,
|
| 240 |
+
"step": 115
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"entropy": 0.06743545532226562,
|
| 244 |
+
"epoch": 1.9047619047619047,
|
| 245 |
+
"grad_norm": 0.14509981870651245,
|
| 246 |
+
"learning_rate": 1.598073001958042e-05,
|
| 247 |
+
"loss": 0.06817712187767029,
|
| 248 |
+
"mean_token_accuracy": 0.9735557198524475,
|
| 249 |
+
"num_tokens": 53931825.0,
|
| 250 |
+
"step": 120
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"entropy": 0.06640436649322509,
|
| 254 |
+
"epoch": 1.9841269841269842,
|
| 255 |
+
"grad_norm": 0.13425911962985992,
|
| 256 |
+
"learning_rate": 1.4015012258521454e-05,
|
| 257 |
+
"loss": 0.0663202166557312,
|
| 258 |
+
"mean_token_accuracy": 0.9740958571434021,
|
| 259 |
+
"num_tokens": 56203400.0,
|
| 260 |
+
"step": 125
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"entropy": 0.06114112734794617,
|
| 264 |
+
"epoch": 2.0634920634920633,
|
| 265 |
+
"grad_norm": 0.14675261080265045,
|
| 266 |
+
"learning_rate": 1.213017996225424e-05,
|
| 267 |
+
"loss": 0.0597736656665802,
|
| 268 |
+
"mean_token_accuracy": 0.9770057320594787,
|
| 269 |
+
"num_tokens": 58447264.0,
|
| 270 |
+
"step": 130
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"entropy": 0.06077109202742577,
|
| 274 |
+
"epoch": 2.142857142857143,
|
| 275 |
+
"grad_norm": 0.14722956717014313,
|
| 276 |
+
"learning_rate": 1.034011166573261e-05,
|
| 277 |
+
"loss": 0.0608077347278595,
|
| 278 |
+
"mean_token_accuracy": 0.9764052987098694,
|
| 279 |
+
"num_tokens": 60680203.0,
|
| 280 |
+
"step": 135
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"entropy": 0.06085996180772781,
|
| 284 |
+
"epoch": 2.2222222222222223,
|
| 285 |
+
"grad_norm": 0.13919851183891296,
|
| 286 |
+
"learning_rate": 8.657988130699848e-06,
|
| 287 |
+
"loss": 0.06093168258666992,
|
| 288 |
+
"mean_token_accuracy": 0.975907814502716,
|
| 289 |
+
"num_tokens": 62928491.0,
|
| 290 |
+
"step": 140
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"entropy": 0.06154095679521561,
|
| 294 |
+
"epoch": 2.3015873015873014,
|
| 295 |
+
"grad_norm": 0.1471860557794571,
|
| 296 |
+
"learning_rate": 7.096195292140173e-06,
|
| 297 |
+
"loss": 0.06225389242172241,
|
| 298 |
+
"mean_token_accuracy": 0.9755991458892822,
|
| 299 |
+
"num_tokens": 65183865.0,
|
| 300 |
+
"step": 145
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"entropy": 0.06028798446059227,
|
| 304 |
+
"epoch": 2.380952380952381,
|
| 305 |
+
"grad_norm": 0.1381225436925888,
|
| 306 |
+
"learning_rate": 5.666233057256756e-06,
|
| 307 |
+
"loss": 0.05946478247642517,
|
| 308 |
+
"mean_token_accuracy": 0.9772057175636292,
|
| 309 |
+
"num_tokens": 67455033.0,
|
| 310 |
+
"step": 150
|
| 311 |
+
}
|
| 312 |
+
],
|
| 313 |
+
"logging_steps": 5,
|
| 314 |
+
"max_steps": 189,
|
| 315 |
+
"num_input_tokens_seen": 0,
|
| 316 |
+
"num_train_epochs": 3,
|
| 317 |
+
"save_steps": 8,
|
| 318 |
+
"stateful_callbacks": {
|
| 319 |
+
"TrainerControl": {
|
| 320 |
+
"args": {
|
| 321 |
+
"should_epoch_stop": false,
|
| 322 |
+
"should_evaluate": false,
|
| 323 |
+
"should_log": false,
|
| 324 |
+
"should_save": true,
|
| 325 |
+
"should_training_stop": false
|
| 326 |
+
},
|
| 327 |
+
"attributes": {}
|
| 328 |
+
}
|
| 329 |
+
},
|
| 330 |
+
"total_flos": 3.8107234557965107e+18,
|
| 331 |
+
"train_batch_size": 4,
|
| 332 |
+
"trial_name": null,
|
| 333 |
+
"trial_params": null
|
| 334 |
+
}
|
checkpoint-152/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63584b641880ca8f7031099a802ca6e2de6c8e3fdacc7cdffeaa3f69e77b5a9a
|
| 3 |
+
size 5969
|
checkpoint-160/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3.5-9B
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen3.5-9B
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.20.0
|
checkpoint-160/adapter_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3.5-9B",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 256,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"monteclora_config": null,
|
| 27 |
+
"peft_type": "LORA",
|
| 28 |
+
"peft_version": "0.20.0",
|
| 29 |
+
"qalora_group_size": 16,
|
| 30 |
+
"r": 128,
|
| 31 |
+
"rank_pattern": {},
|
| 32 |
+
"revision": null,
|
| 33 |
+
"target_modules": [
|
| 34 |
+
"in_proj_a",
|
| 35 |
+
"up_proj",
|
| 36 |
+
"gate_proj",
|
| 37 |
+
"o_proj",
|
| 38 |
+
"in_proj_z",
|
| 39 |
+
"v_proj",
|
| 40 |
+
"down_proj",
|
| 41 |
+
"in_proj_b",
|
| 42 |
+
"q_proj",
|
| 43 |
+
"out_proj",
|
| 44 |
+
"in_proj_qkv",
|
| 45 |
+
"k_proj"
|
| 46 |
+
],
|
| 47 |
+
"target_parameters": null,
|
| 48 |
+
"task_type": "CAUSAL_LM",
|
| 49 |
+
"trainable_token_indices": null,
|
| 50 |
+
"use_bdlora": null,
|
| 51 |
+
"use_dora": false,
|
| 52 |
+
"use_qalora": false,
|
| 53 |
+
"use_rslora": false,
|
| 54 |
+
"velora_config": null
|
| 55 |
+
}
|