Commit
•
02aed86
1
Parent(s):
c7efe3e
Upload folder using huggingface_hub
Browse files- README.md +59 -1
- checkpoint-1300/config.json +46 -0
- checkpoint-1300/generation_config.json +6 -0
- checkpoint-1300/optimizer.pt +3 -0
- checkpoint-1300/pytorch_model.bin +3 -0
- checkpoint-1300/rng_state.pth +3 -0
- checkpoint-1300/scheduler.pt +3 -0
- checkpoint-1300/trainer_state.json +183 -0
- checkpoint-1300/training_args.bin +3 -0
- checkpoint-2600/config.json +46 -0
- checkpoint-2600/generation_config.json +6 -0
- checkpoint-2600/optimizer.pt +3 -0
- checkpoint-2600/pytorch_model.bin +3 -0
- checkpoint-2600/rng_state.pth +3 -0
- checkpoint-2600/scheduler.pt +3 -0
- checkpoint-2600/trainer_state.json +347 -0
- checkpoint-2600/training_args.bin +3 -0
- checkpoint-3900/config.json +46 -0
- checkpoint-3900/generation_config.json +6 -0
- checkpoint-3900/optimizer.pt +3 -0
- checkpoint-3900/pytorch_model.bin +3 -0
- checkpoint-3900/rng_state.pth +3 -0
- checkpoint-3900/scheduler.pt +3 -0
- checkpoint-3900/trainer_state.json +511 -0
- checkpoint-3900/training_args.bin +3 -0
- config.json +46 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,61 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: distilgpt2
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: gpt2_dolly_lite
|
| 8 |
+
results: []
|
| 9 |
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# gpt2_dolly_lite
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 2.4067
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.001
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 32
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 4
|
| 42 |
+
- total_train_batch_size: 32
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 3
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 2.708 | 1.0 | 1300 | 2.5611 |
|
| 52 |
+
| 2.1768 | 2.0 | 2600 | 2.4149 |
|
| 53 |
+
| 1.7189 | 3.0 | 3900 | 2.4067 |
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- Transformers 4.32.1
|
| 59 |
+
- Pytorch 2.0.1+cu118
|
| 60 |
+
- Datasets 2.14.4
|
| 61 |
+
- Tokenizers 0.13.3
|
checkpoint-1300/config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilgpt2",
|
| 3 |
+
"_num_labels": 1,
|
| 4 |
+
"activation_function": "gelu_new",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"GPT2LMHeadModel"
|
| 7 |
+
],
|
| 8 |
+
"attn_pdrop": 0.1,
|
| 9 |
+
"bos_token_id": 50256,
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_epsilon": 1e-05,
|
| 20 |
+
"model_type": "gpt2",
|
| 21 |
+
"n_ctx": 1024,
|
| 22 |
+
"n_embd": 768,
|
| 23 |
+
"n_head": 12,
|
| 24 |
+
"n_inner": null,
|
| 25 |
+
"n_layer": 6,
|
| 26 |
+
"n_positions": 1024,
|
| 27 |
+
"reorder_and_upcast_attn": false,
|
| 28 |
+
"resid_pdrop": 0.1,
|
| 29 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 30 |
+
"scale_attn_weights": true,
|
| 31 |
+
"summary_activation": null,
|
| 32 |
+
"summary_first_dropout": 0.1,
|
| 33 |
+
"summary_proj_to_labels": true,
|
| 34 |
+
"summary_type": "cls_index",
|
| 35 |
+
"summary_use_proj": true,
|
| 36 |
+
"task_specific_params": {
|
| 37 |
+
"text-generation": {
|
| 38 |
+
"do_sample": true,
|
| 39 |
+
"max_length": 50
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.32.1",
|
| 44 |
+
"use_cache": true,
|
| 45 |
+
"vocab_size": 50257
|
| 46 |
+
}
|
checkpoint-1300/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.32.1"
|
| 6 |
+
}
|
checkpoint-1300/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f44c8f6c514ad8e349d345a46a159fc6ed4166c32d4626aa0a2f9d0ad011355
|
| 3 |
+
size 655364037
|
checkpoint-1300/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b5190e105a8a7362be16f16eaf1b51bfca3508ebfbe376e764a4a3f06b8bef7
|
| 3 |
+
size 327674773
|
checkpoint-1300/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65ebbc7268a7952f4f6c6443d3fc774fecab4069169a85def8a285e8a02168ec
|
| 3 |
+
size 14575
|
checkpoint-1300/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:212e58901c3687afbfbec22f9809a97294d8c570380f7ab9130924780eef0624
|
| 3 |
+
size 627
|
checkpoint-1300/trainer_state.json
ADDED
|
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.561117649078369,
|
| 3 |
+
"best_model_checkpoint": "./gpt2_dolly_lite/checkpoint-1300",
|
| 4 |
+
"epoch": 0.9998077292828302,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1300,
|
| 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 |
+
"learning_rate": 0.0009871794871794872,
|
| 14 |
+
"loss": 3.3078,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.08,
|
| 19 |
+
"learning_rate": 0.0009743589743589744,
|
| 20 |
+
"loss": 3.1249,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.12,
|
| 25 |
+
"learning_rate": 0.0009615384615384616,
|
| 26 |
+
"loss": 3.1026,
|
| 27 |
+
"step": 150
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.15,
|
| 31 |
+
"learning_rate": 0.0009487179487179487,
|
| 32 |
+
"loss": 3.0496,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.19,
|
| 37 |
+
"learning_rate": 0.000935897435897436,
|
| 38 |
+
"loss": 2.9706,
|
| 39 |
+
"step": 250
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.23,
|
| 43 |
+
"learning_rate": 0.0009230769230769232,
|
| 44 |
+
"loss": 3.0195,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.27,
|
| 49 |
+
"learning_rate": 0.0009102564102564102,
|
| 50 |
+
"loss": 2.9747,
|
| 51 |
+
"step": 350
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.31,
|
| 55 |
+
"learning_rate": 0.0008974358974358974,
|
| 56 |
+
"loss": 2.9205,
|
| 57 |
+
"step": 400
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.35,
|
| 61 |
+
"learning_rate": 0.0008846153846153846,
|
| 62 |
+
"loss": 2.9495,
|
| 63 |
+
"step": 450
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.38,
|
| 67 |
+
"learning_rate": 0.0008717948717948718,
|
| 68 |
+
"loss": 2.8866,
|
| 69 |
+
"step": 500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.42,
|
| 73 |
+
"learning_rate": 0.0008589743589743589,
|
| 74 |
+
"loss": 2.892,
|
| 75 |
+
"step": 550
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.46,
|
| 79 |
+
"learning_rate": 0.0008461538461538462,
|
| 80 |
+
"loss": 2.8849,
|
| 81 |
+
"step": 600
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.5,
|
| 85 |
+
"learning_rate": 0.0008333333333333334,
|
| 86 |
+
"loss": 2.8819,
|
| 87 |
+
"step": 650
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.54,
|
| 91 |
+
"learning_rate": 0.0008205128205128205,
|
| 92 |
+
"loss": 2.8561,
|
| 93 |
+
"step": 700
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.58,
|
| 97 |
+
"learning_rate": 0.0008076923076923078,
|
| 98 |
+
"loss": 2.8311,
|
| 99 |
+
"step": 750
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.62,
|
| 103 |
+
"learning_rate": 0.0007948717948717948,
|
| 104 |
+
"loss": 2.8176,
|
| 105 |
+
"step": 800
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.65,
|
| 109 |
+
"learning_rate": 0.000782051282051282,
|
| 110 |
+
"loss": 2.7782,
|
| 111 |
+
"step": 850
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.69,
|
| 115 |
+
"learning_rate": 0.0007692307692307693,
|
| 116 |
+
"loss": 2.7273,
|
| 117 |
+
"step": 900
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.73,
|
| 121 |
+
"learning_rate": 0.0007564102564102564,
|
| 122 |
+
"loss": 2.7686,
|
| 123 |
+
"step": 950
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.77,
|
| 127 |
+
"learning_rate": 0.0007435897435897436,
|
| 128 |
+
"loss": 2.7274,
|
| 129 |
+
"step": 1000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.81,
|
| 133 |
+
"learning_rate": 0.0007307692307692307,
|
| 134 |
+
"loss": 2.7514,
|
| 135 |
+
"step": 1050
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.85,
|
| 139 |
+
"learning_rate": 0.000717948717948718,
|
| 140 |
+
"loss": 2.7232,
|
| 141 |
+
"step": 1100
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.88,
|
| 145 |
+
"learning_rate": 0.0007051282051282052,
|
| 146 |
+
"loss": 2.6937,
|
| 147 |
+
"step": 1150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.92,
|
| 151 |
+
"learning_rate": 0.0006923076923076923,
|
| 152 |
+
"loss": 2.7209,
|
| 153 |
+
"step": 1200
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.96,
|
| 157 |
+
"learning_rate": 0.0006794871794871796,
|
| 158 |
+
"loss": 2.6832,
|
| 159 |
+
"step": 1250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.0,
|
| 163 |
+
"learning_rate": 0.0006666666666666666,
|
| 164 |
+
"loss": 2.708,
|
| 165 |
+
"step": 1300
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.0,
|
| 169 |
+
"eval_loss": 2.561117649078369,
|
| 170 |
+
"eval_runtime": 41.0726,
|
| 171 |
+
"eval_samples_per_second": 253.235,
|
| 172 |
+
"eval_steps_per_second": 7.937,
|
| 173 |
+
"step": 1300
|
| 174 |
+
}
|
| 175 |
+
],
|
| 176 |
+
"logging_steps": 50,
|
| 177 |
+
"max_steps": 3900,
|
| 178 |
+
"num_train_epochs": 3,
|
| 179 |
+
"save_steps": 500,
|
| 180 |
+
"total_flos": 2217745708572672.0,
|
| 181 |
+
"trial_name": null,
|
| 182 |
+
"trial_params": null
|
| 183 |
+
}
|
checkpoint-1300/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5863f7260e5f2acd6ed9097371440ce6f89c0fdc0fbea3c0b7bd599e0244316f
|
| 3 |
+
size 4027
|
checkpoint-2600/config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilgpt2",
|
| 3 |
+
"_num_labels": 1,
|
| 4 |
+
"activation_function": "gelu_new",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"GPT2LMHeadModel"
|
| 7 |
+
],
|
| 8 |
+
"attn_pdrop": 0.1,
|
| 9 |
+
"bos_token_id": 50256,
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_epsilon": 1e-05,
|
| 20 |
+
"model_type": "gpt2",
|
| 21 |
+
"n_ctx": 1024,
|
| 22 |
+
"n_embd": 768,
|
| 23 |
+
"n_head": 12,
|
| 24 |
+
"n_inner": null,
|
| 25 |
+
"n_layer": 6,
|
| 26 |
+
"n_positions": 1024,
|
| 27 |
+
"reorder_and_upcast_attn": false,
|
| 28 |
+
"resid_pdrop": 0.1,
|
| 29 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 30 |
+
"scale_attn_weights": true,
|
| 31 |
+
"summary_activation": null,
|
| 32 |
+
"summary_first_dropout": 0.1,
|
| 33 |
+
"summary_proj_to_labels": true,
|
| 34 |
+
"summary_type": "cls_index",
|
| 35 |
+
"summary_use_proj": true,
|
| 36 |
+
"task_specific_params": {
|
| 37 |
+
"text-generation": {
|
| 38 |
+
"do_sample": true,
|
| 39 |
+
"max_length": 50
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.32.1",
|
| 44 |
+
"use_cache": true,
|
| 45 |
+
"vocab_size": 50257
|
| 46 |
+
}
|
checkpoint-2600/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.32.1"
|
| 6 |
+
}
|
checkpoint-2600/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2f5f1a4c772f7ed8b56cd9b26fadd5b86d5a775421136ecefc1e753bf2cb96d
|
| 3 |
+
size 655364037
|
checkpoint-2600/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcab8e0ae7f44c5de6401e22a75acebe3915057a32af2cae6bb57a2745f7a34d
|
| 3 |
+
size 327674773
|
checkpoint-2600/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:950a675deac0bd82676ee97ba5d2d1126640847e7cfd72fc6877d8dfc8e26002
|
| 3 |
+
size 14575
|
checkpoint-2600/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89dbab01816d59b4bbc89d82d176e913e76e05dbd72b4fa6cac4ee1fc89a3eaa
|
| 3 |
+
size 627
|
checkpoint-2600/trainer_state.json
ADDED
|
@@ -0,0 +1,347 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.41491436958313,
|
| 3 |
+
"best_model_checkpoint": "./gpt2_dolly_lite/checkpoint-2600",
|
| 4 |
+
"epoch": 1.9996154585656605,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2600,
|
| 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 |
+
"learning_rate": 0.0009871794871794872,
|
| 14 |
+
"loss": 3.3078,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.08,
|
| 19 |
+
"learning_rate": 0.0009743589743589744,
|
| 20 |
+
"loss": 3.1249,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.12,
|
| 25 |
+
"learning_rate": 0.0009615384615384616,
|
| 26 |
+
"loss": 3.1026,
|
| 27 |
+
"step": 150
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.15,
|
| 31 |
+
"learning_rate": 0.0009487179487179487,
|
| 32 |
+
"loss": 3.0496,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.19,
|
| 37 |
+
"learning_rate": 0.000935897435897436,
|
| 38 |
+
"loss": 2.9706,
|
| 39 |
+
"step": 250
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.23,
|
| 43 |
+
"learning_rate": 0.0009230769230769232,
|
| 44 |
+
"loss": 3.0195,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.27,
|
| 49 |
+
"learning_rate": 0.0009102564102564102,
|
| 50 |
+
"loss": 2.9747,
|
| 51 |
+
"step": 350
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.31,
|
| 55 |
+
"learning_rate": 0.0008974358974358974,
|
| 56 |
+
"loss": 2.9205,
|
| 57 |
+
"step": 400
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.35,
|
| 61 |
+
"learning_rate": 0.0008846153846153846,
|
| 62 |
+
"loss": 2.9495,
|
| 63 |
+
"step": 450
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.38,
|
| 67 |
+
"learning_rate": 0.0008717948717948718,
|
| 68 |
+
"loss": 2.8866,
|
| 69 |
+
"step": 500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.42,
|
| 73 |
+
"learning_rate": 0.0008589743589743589,
|
| 74 |
+
"loss": 2.892,
|
| 75 |
+
"step": 550
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.46,
|
| 79 |
+
"learning_rate": 0.0008461538461538462,
|
| 80 |
+
"loss": 2.8849,
|
| 81 |
+
"step": 600
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.5,
|
| 85 |
+
"learning_rate": 0.0008333333333333334,
|
| 86 |
+
"loss": 2.8819,
|
| 87 |
+
"step": 650
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.54,
|
| 91 |
+
"learning_rate": 0.0008205128205128205,
|
| 92 |
+
"loss": 2.8561,
|
| 93 |
+
"step": 700
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.58,
|
| 97 |
+
"learning_rate": 0.0008076923076923078,
|
| 98 |
+
"loss": 2.8311,
|
| 99 |
+
"step": 750
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.62,
|
| 103 |
+
"learning_rate": 0.0007948717948717948,
|
| 104 |
+
"loss": 2.8176,
|
| 105 |
+
"step": 800
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.65,
|
| 109 |
+
"learning_rate": 0.000782051282051282,
|
| 110 |
+
"loss": 2.7782,
|
| 111 |
+
"step": 850
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.69,
|
| 115 |
+
"learning_rate": 0.0007692307692307693,
|
| 116 |
+
"loss": 2.7273,
|
| 117 |
+
"step": 900
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.73,
|
| 121 |
+
"learning_rate": 0.0007564102564102564,
|
| 122 |
+
"loss": 2.7686,
|
| 123 |
+
"step": 950
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.77,
|
| 127 |
+
"learning_rate": 0.0007435897435897436,
|
| 128 |
+
"loss": 2.7274,
|
| 129 |
+
"step": 1000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.81,
|
| 133 |
+
"learning_rate": 0.0007307692307692307,
|
| 134 |
+
"loss": 2.7514,
|
| 135 |
+
"step": 1050
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.85,
|
| 139 |
+
"learning_rate": 0.000717948717948718,
|
| 140 |
+
"loss": 2.7232,
|
| 141 |
+
"step": 1100
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.88,
|
| 145 |
+
"learning_rate": 0.0007051282051282052,
|
| 146 |
+
"loss": 2.6937,
|
| 147 |
+
"step": 1150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.92,
|
| 151 |
+
"learning_rate": 0.0006923076923076923,
|
| 152 |
+
"loss": 2.7209,
|
| 153 |
+
"step": 1200
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.96,
|
| 157 |
+
"learning_rate": 0.0006794871794871796,
|
| 158 |
+
"loss": 2.6832,
|
| 159 |
+
"step": 1250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.0,
|
| 163 |
+
"learning_rate": 0.0006666666666666666,
|
| 164 |
+
"loss": 2.708,
|
| 165 |
+
"step": 1300
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.0,
|
| 169 |
+
"eval_loss": 2.561117649078369,
|
| 170 |
+
"eval_runtime": 41.0726,
|
| 171 |
+
"eval_samples_per_second": 253.235,
|
| 172 |
+
"eval_steps_per_second": 7.937,
|
| 173 |
+
"step": 1300
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.04,
|
| 177 |
+
"learning_rate": 0.0006538461538461538,
|
| 178 |
+
"loss": 2.2119,
|
| 179 |
+
"step": 1350
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.08,
|
| 183 |
+
"learning_rate": 0.0006410256410256411,
|
| 184 |
+
"loss": 2.2279,
|
| 185 |
+
"step": 1400
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.12,
|
| 189 |
+
"learning_rate": 0.0006282051282051282,
|
| 190 |
+
"loss": 2.1996,
|
| 191 |
+
"step": 1450
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.15,
|
| 195 |
+
"learning_rate": 0.0006153846153846154,
|
| 196 |
+
"loss": 2.1886,
|
| 197 |
+
"step": 1500
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.19,
|
| 201 |
+
"learning_rate": 0.0006025641025641026,
|
| 202 |
+
"loss": 2.268,
|
| 203 |
+
"step": 1550
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.23,
|
| 207 |
+
"learning_rate": 0.0005897435897435898,
|
| 208 |
+
"loss": 2.2118,
|
| 209 |
+
"step": 1600
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.27,
|
| 213 |
+
"learning_rate": 0.0005769230769230769,
|
| 214 |
+
"loss": 2.2831,
|
| 215 |
+
"step": 1650
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.31,
|
| 219 |
+
"learning_rate": 0.0005641025641025641,
|
| 220 |
+
"loss": 2.2317,
|
| 221 |
+
"step": 1700
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.35,
|
| 225 |
+
"learning_rate": 0.0005512820512820514,
|
| 226 |
+
"loss": 2.2504,
|
| 227 |
+
"step": 1750
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.38,
|
| 231 |
+
"learning_rate": 0.0005384615384615384,
|
| 232 |
+
"loss": 2.241,
|
| 233 |
+
"step": 1800
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.42,
|
| 237 |
+
"learning_rate": 0.0005256410256410256,
|
| 238 |
+
"loss": 2.2381,
|
| 239 |
+
"step": 1850
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.46,
|
| 243 |
+
"learning_rate": 0.0005128205128205128,
|
| 244 |
+
"loss": 2.2313,
|
| 245 |
+
"step": 1900
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.5,
|
| 249 |
+
"learning_rate": 0.0005,
|
| 250 |
+
"loss": 2.2493,
|
| 251 |
+
"step": 1950
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.54,
|
| 255 |
+
"learning_rate": 0.0004871794871794872,
|
| 256 |
+
"loss": 2.2056,
|
| 257 |
+
"step": 2000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.58,
|
| 261 |
+
"learning_rate": 0.00047435897435897434,
|
| 262 |
+
"loss": 2.2178,
|
| 263 |
+
"step": 2050
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.62,
|
| 267 |
+
"learning_rate": 0.0004615384615384616,
|
| 268 |
+
"loss": 2.2518,
|
| 269 |
+
"step": 2100
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.65,
|
| 273 |
+
"learning_rate": 0.0004487179487179487,
|
| 274 |
+
"loss": 2.2354,
|
| 275 |
+
"step": 2150
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.69,
|
| 279 |
+
"learning_rate": 0.0004358974358974359,
|
| 280 |
+
"loss": 2.2144,
|
| 281 |
+
"step": 2200
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.73,
|
| 285 |
+
"learning_rate": 0.0004230769230769231,
|
| 286 |
+
"loss": 2.2197,
|
| 287 |
+
"step": 2250
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.77,
|
| 291 |
+
"learning_rate": 0.00041025641025641023,
|
| 292 |
+
"loss": 2.2006,
|
| 293 |
+
"step": 2300
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.81,
|
| 297 |
+
"learning_rate": 0.0003974358974358974,
|
| 298 |
+
"loss": 2.1802,
|
| 299 |
+
"step": 2350
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.85,
|
| 303 |
+
"learning_rate": 0.00038461538461538467,
|
| 304 |
+
"loss": 2.1656,
|
| 305 |
+
"step": 2400
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.88,
|
| 309 |
+
"learning_rate": 0.0003717948717948718,
|
| 310 |
+
"loss": 2.1592,
|
| 311 |
+
"step": 2450
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.92,
|
| 315 |
+
"learning_rate": 0.000358974358974359,
|
| 316 |
+
"loss": 2.1847,
|
| 317 |
+
"step": 2500
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.96,
|
| 321 |
+
"learning_rate": 0.00034615384615384613,
|
| 322 |
+
"loss": 2.1981,
|
| 323 |
+
"step": 2550
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.0,
|
| 327 |
+
"learning_rate": 0.0003333333333333333,
|
| 328 |
+
"loss": 2.1768,
|
| 329 |
+
"step": 2600
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.0,
|
| 333 |
+
"eval_loss": 2.41491436958313,
|
| 334 |
+
"eval_runtime": 39.8227,
|
| 335 |
+
"eval_samples_per_second": 261.183,
|
| 336 |
+
"eval_steps_per_second": 8.186,
|
| 337 |
+
"step": 2600
|
| 338 |
+
}
|
| 339 |
+
],
|
| 340 |
+
"logging_steps": 50,
|
| 341 |
+
"max_steps": 3900,
|
| 342 |
+
"num_train_epochs": 3,
|
| 343 |
+
"save_steps": 500,
|
| 344 |
+
"total_flos": 4433294636163072.0,
|
| 345 |
+
"trial_name": null,
|
| 346 |
+
"trial_params": null
|
| 347 |
+
}
|
checkpoint-2600/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5863f7260e5f2acd6ed9097371440ce6f89c0fdc0fbea3c0b7bd599e0244316f
|
| 3 |
+
size 4027
|
checkpoint-3900/config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilgpt2",
|
| 3 |
+
"_num_labels": 1,
|
| 4 |
+
"activation_function": "gelu_new",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"GPT2LMHeadModel"
|
| 7 |
+
],
|
| 8 |
+
"attn_pdrop": 0.1,
|
| 9 |
+
"bos_token_id": 50256,
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_epsilon": 1e-05,
|
| 20 |
+
"model_type": "gpt2",
|
| 21 |
+
"n_ctx": 1024,
|
| 22 |
+
"n_embd": 768,
|
| 23 |
+
"n_head": 12,
|
| 24 |
+
"n_inner": null,
|
| 25 |
+
"n_layer": 6,
|
| 26 |
+
"n_positions": 1024,
|
| 27 |
+
"reorder_and_upcast_attn": false,
|
| 28 |
+
"resid_pdrop": 0.1,
|
| 29 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 30 |
+
"scale_attn_weights": true,
|
| 31 |
+
"summary_activation": null,
|
| 32 |
+
"summary_first_dropout": 0.1,
|
| 33 |
+
"summary_proj_to_labels": true,
|
| 34 |
+
"summary_type": "cls_index",
|
| 35 |
+
"summary_use_proj": true,
|
| 36 |
+
"task_specific_params": {
|
| 37 |
+
"text-generation": {
|
| 38 |
+
"do_sample": true,
|
| 39 |
+
"max_length": 50
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.32.1",
|
| 44 |
+
"use_cache": true,
|
| 45 |
+
"vocab_size": 50257
|
| 46 |
+
}
|
checkpoint-3900/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.32.1"
|
| 6 |
+
}
|
checkpoint-3900/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a2cdf22127a37d9cbfec1697d33a6dd20c5bed3db9c6597819288615554f655
|
| 3 |
+
size 655364037
|
checkpoint-3900/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d254aeaf5388d54112768c1e776c979981bbe1ff7708fe3e83c9c20870b05fa
|
| 3 |
+
size 327674773
|
checkpoint-3900/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e64853923e7e2bdc8669bfd7cdf72aa2ac6db3c7b3f443ec85518ea3ca067872
|
| 3 |
+
size 14575
|
checkpoint-3900/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddb3e76f913ba655b35f1677dd9ce4b515a60ebabae02f9cef6d01938028d265
|
| 3 |
+
size 627
|
checkpoint-3900/trainer_state.json
ADDED
|
@@ -0,0 +1,511 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.406733751296997,
|
| 3 |
+
"best_model_checkpoint": "./gpt2_dolly_lite/checkpoint-3900",
|
| 4 |
+
"epoch": 2.9994231878484907,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3900,
|
| 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 |
+
"learning_rate": 0.0009871794871794872,
|
| 14 |
+
"loss": 3.3078,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.08,
|
| 19 |
+
"learning_rate": 0.0009743589743589744,
|
| 20 |
+
"loss": 3.1249,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.12,
|
| 25 |
+
"learning_rate": 0.0009615384615384616,
|
| 26 |
+
"loss": 3.1026,
|
| 27 |
+
"step": 150
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.15,
|
| 31 |
+
"learning_rate": 0.0009487179487179487,
|
| 32 |
+
"loss": 3.0496,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.19,
|
| 37 |
+
"learning_rate": 0.000935897435897436,
|
| 38 |
+
"loss": 2.9706,
|
| 39 |
+
"step": 250
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.23,
|
| 43 |
+
"learning_rate": 0.0009230769230769232,
|
| 44 |
+
"loss": 3.0195,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.27,
|
| 49 |
+
"learning_rate": 0.0009102564102564102,
|
| 50 |
+
"loss": 2.9747,
|
| 51 |
+
"step": 350
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.31,
|
| 55 |
+
"learning_rate": 0.0008974358974358974,
|
| 56 |
+
"loss": 2.9205,
|
| 57 |
+
"step": 400
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.35,
|
| 61 |
+
"learning_rate": 0.0008846153846153846,
|
| 62 |
+
"loss": 2.9495,
|
| 63 |
+
"step": 450
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.38,
|
| 67 |
+
"learning_rate": 0.0008717948717948718,
|
| 68 |
+
"loss": 2.8866,
|
| 69 |
+
"step": 500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.42,
|
| 73 |
+
"learning_rate": 0.0008589743589743589,
|
| 74 |
+
"loss": 2.892,
|
| 75 |
+
"step": 550
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.46,
|
| 79 |
+
"learning_rate": 0.0008461538461538462,
|
| 80 |
+
"loss": 2.8849,
|
| 81 |
+
"step": 600
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.5,
|
| 85 |
+
"learning_rate": 0.0008333333333333334,
|
| 86 |
+
"loss": 2.8819,
|
| 87 |
+
"step": 650
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.54,
|
| 91 |
+
"learning_rate": 0.0008205128205128205,
|
| 92 |
+
"loss": 2.8561,
|
| 93 |
+
"step": 700
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.58,
|
| 97 |
+
"learning_rate": 0.0008076923076923078,
|
| 98 |
+
"loss": 2.8311,
|
| 99 |
+
"step": 750
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.62,
|
| 103 |
+
"learning_rate": 0.0007948717948717948,
|
| 104 |
+
"loss": 2.8176,
|
| 105 |
+
"step": 800
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.65,
|
| 109 |
+
"learning_rate": 0.000782051282051282,
|
| 110 |
+
"loss": 2.7782,
|
| 111 |
+
"step": 850
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.69,
|
| 115 |
+
"learning_rate": 0.0007692307692307693,
|
| 116 |
+
"loss": 2.7273,
|
| 117 |
+
"step": 900
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.73,
|
| 121 |
+
"learning_rate": 0.0007564102564102564,
|
| 122 |
+
"loss": 2.7686,
|
| 123 |
+
"step": 950
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.77,
|
| 127 |
+
"learning_rate": 0.0007435897435897436,
|
| 128 |
+
"loss": 2.7274,
|
| 129 |
+
"step": 1000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.81,
|
| 133 |
+
"learning_rate": 0.0007307692307692307,
|
| 134 |
+
"loss": 2.7514,
|
| 135 |
+
"step": 1050
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.85,
|
| 139 |
+
"learning_rate": 0.000717948717948718,
|
| 140 |
+
"loss": 2.7232,
|
| 141 |
+
"step": 1100
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.88,
|
| 145 |
+
"learning_rate": 0.0007051282051282052,
|
| 146 |
+
"loss": 2.6937,
|
| 147 |
+
"step": 1150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.92,
|
| 151 |
+
"learning_rate": 0.0006923076923076923,
|
| 152 |
+
"loss": 2.7209,
|
| 153 |
+
"step": 1200
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.96,
|
| 157 |
+
"learning_rate": 0.0006794871794871796,
|
| 158 |
+
"loss": 2.6832,
|
| 159 |
+
"step": 1250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.0,
|
| 163 |
+
"learning_rate": 0.0006666666666666666,
|
| 164 |
+
"loss": 2.708,
|
| 165 |
+
"step": 1300
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.0,
|
| 169 |
+
"eval_loss": 2.561117649078369,
|
| 170 |
+
"eval_runtime": 41.0726,
|
| 171 |
+
"eval_samples_per_second": 253.235,
|
| 172 |
+
"eval_steps_per_second": 7.937,
|
| 173 |
+
"step": 1300
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.04,
|
| 177 |
+
"learning_rate": 0.0006538461538461538,
|
| 178 |
+
"loss": 2.2119,
|
| 179 |
+
"step": 1350
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.08,
|
| 183 |
+
"learning_rate": 0.0006410256410256411,
|
| 184 |
+
"loss": 2.2279,
|
| 185 |
+
"step": 1400
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.12,
|
| 189 |
+
"learning_rate": 0.0006282051282051282,
|
| 190 |
+
"loss": 2.1996,
|
| 191 |
+
"step": 1450
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.15,
|
| 195 |
+
"learning_rate": 0.0006153846153846154,
|
| 196 |
+
"loss": 2.1886,
|
| 197 |
+
"step": 1500
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.19,
|
| 201 |
+
"learning_rate": 0.0006025641025641026,
|
| 202 |
+
"loss": 2.268,
|
| 203 |
+
"step": 1550
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.23,
|
| 207 |
+
"learning_rate": 0.0005897435897435898,
|
| 208 |
+
"loss": 2.2118,
|
| 209 |
+
"step": 1600
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.27,
|
| 213 |
+
"learning_rate": 0.0005769230769230769,
|
| 214 |
+
"loss": 2.2831,
|
| 215 |
+
"step": 1650
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.31,
|
| 219 |
+
"learning_rate": 0.0005641025641025641,
|
| 220 |
+
"loss": 2.2317,
|
| 221 |
+
"step": 1700
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.35,
|
| 225 |
+
"learning_rate": 0.0005512820512820514,
|
| 226 |
+
"loss": 2.2504,
|
| 227 |
+
"step": 1750
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.38,
|
| 231 |
+
"learning_rate": 0.0005384615384615384,
|
| 232 |
+
"loss": 2.241,
|
| 233 |
+
"step": 1800
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.42,
|
| 237 |
+
"learning_rate": 0.0005256410256410256,
|
| 238 |
+
"loss": 2.2381,
|
| 239 |
+
"step": 1850
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.46,
|
| 243 |
+
"learning_rate": 0.0005128205128205128,
|
| 244 |
+
"loss": 2.2313,
|
| 245 |
+
"step": 1900
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.5,
|
| 249 |
+
"learning_rate": 0.0005,
|
| 250 |
+
"loss": 2.2493,
|
| 251 |
+
"step": 1950
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.54,
|
| 255 |
+
"learning_rate": 0.0004871794871794872,
|
| 256 |
+
"loss": 2.2056,
|
| 257 |
+
"step": 2000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.58,
|
| 261 |
+
"learning_rate": 0.00047435897435897434,
|
| 262 |
+
"loss": 2.2178,
|
| 263 |
+
"step": 2050
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.62,
|
| 267 |
+
"learning_rate": 0.0004615384615384616,
|
| 268 |
+
"loss": 2.2518,
|
| 269 |
+
"step": 2100
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.65,
|
| 273 |
+
"learning_rate": 0.0004487179487179487,
|
| 274 |
+
"loss": 2.2354,
|
| 275 |
+
"step": 2150
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.69,
|
| 279 |
+
"learning_rate": 0.0004358974358974359,
|
| 280 |
+
"loss": 2.2144,
|
| 281 |
+
"step": 2200
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.73,
|
| 285 |
+
"learning_rate": 0.0004230769230769231,
|
| 286 |
+
"loss": 2.2197,
|
| 287 |
+
"step": 2250
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.77,
|
| 291 |
+
"learning_rate": 0.00041025641025641023,
|
| 292 |
+
"loss": 2.2006,
|
| 293 |
+
"step": 2300
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.81,
|
| 297 |
+
"learning_rate": 0.0003974358974358974,
|
| 298 |
+
"loss": 2.1802,
|
| 299 |
+
"step": 2350
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.85,
|
| 303 |
+
"learning_rate": 0.00038461538461538467,
|
| 304 |
+
"loss": 2.1656,
|
| 305 |
+
"step": 2400
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.88,
|
| 309 |
+
"learning_rate": 0.0003717948717948718,
|
| 310 |
+
"loss": 2.1592,
|
| 311 |
+
"step": 2450
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.92,
|
| 315 |
+
"learning_rate": 0.000358974358974359,
|
| 316 |
+
"loss": 2.1847,
|
| 317 |
+
"step": 2500
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.96,
|
| 321 |
+
"learning_rate": 0.00034615384615384613,
|
| 322 |
+
"loss": 2.1981,
|
| 323 |
+
"step": 2550
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.0,
|
| 327 |
+
"learning_rate": 0.0003333333333333333,
|
| 328 |
+
"loss": 2.1768,
|
| 329 |
+
"step": 2600
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.0,
|
| 333 |
+
"eval_loss": 2.41491436958313,
|
| 334 |
+
"eval_runtime": 39.8227,
|
| 335 |
+
"eval_samples_per_second": 261.183,
|
| 336 |
+
"eval_steps_per_second": 8.186,
|
| 337 |
+
"step": 2600
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 2.04,
|
| 341 |
+
"learning_rate": 0.00032051282051282057,
|
| 342 |
+
"loss": 1.7593,
|
| 343 |
+
"step": 2650
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 2.08,
|
| 347 |
+
"learning_rate": 0.0003076923076923077,
|
| 348 |
+
"loss": 1.7591,
|
| 349 |
+
"step": 2700
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 2.11,
|
| 353 |
+
"learning_rate": 0.0002948717948717949,
|
| 354 |
+
"loss": 1.7473,
|
| 355 |
+
"step": 2750
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 2.15,
|
| 359 |
+
"learning_rate": 0.00028205128205128203,
|
| 360 |
+
"loss": 1.7836,
|
| 361 |
+
"step": 2800
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 2.19,
|
| 365 |
+
"learning_rate": 0.0002692307692307692,
|
| 366 |
+
"loss": 1.7636,
|
| 367 |
+
"step": 2850
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.23,
|
| 371 |
+
"learning_rate": 0.0002564102564102564,
|
| 372 |
+
"loss": 1.763,
|
| 373 |
+
"step": 2900
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.27,
|
| 377 |
+
"learning_rate": 0.0002435897435897436,
|
| 378 |
+
"loss": 1.7639,
|
| 379 |
+
"step": 2950
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 2.31,
|
| 383 |
+
"learning_rate": 0.0002307692307692308,
|
| 384 |
+
"loss": 1.791,
|
| 385 |
+
"step": 3000
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.35,
|
| 389 |
+
"learning_rate": 0.00021794871794871795,
|
| 390 |
+
"loss": 1.7802,
|
| 391 |
+
"step": 3050
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.38,
|
| 395 |
+
"learning_rate": 0.00020512820512820512,
|
| 396 |
+
"loss": 1.7899,
|
| 397 |
+
"step": 3100
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 2.42,
|
| 401 |
+
"learning_rate": 0.00019230769230769233,
|
| 402 |
+
"loss": 1.7601,
|
| 403 |
+
"step": 3150
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 2.46,
|
| 407 |
+
"learning_rate": 0.0001794871794871795,
|
| 408 |
+
"loss": 1.7696,
|
| 409 |
+
"step": 3200
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.5,
|
| 413 |
+
"learning_rate": 0.00016666666666666666,
|
| 414 |
+
"loss": 1.7586,
|
| 415 |
+
"step": 3250
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.54,
|
| 419 |
+
"learning_rate": 0.00015384615384615385,
|
| 420 |
+
"loss": 1.7312,
|
| 421 |
+
"step": 3300
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 2.58,
|
| 425 |
+
"learning_rate": 0.00014102564102564101,
|
| 426 |
+
"loss": 1.7353,
|
| 427 |
+
"step": 3350
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 2.61,
|
| 431 |
+
"learning_rate": 0.0001282051282051282,
|
| 432 |
+
"loss": 1.7453,
|
| 433 |
+
"step": 3400
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 2.65,
|
| 437 |
+
"learning_rate": 0.0001153846153846154,
|
| 438 |
+
"loss": 1.7397,
|
| 439 |
+
"step": 3450
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 2.69,
|
| 443 |
+
"learning_rate": 0.00010256410256410256,
|
| 444 |
+
"loss": 1.7529,
|
| 445 |
+
"step": 3500
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 2.73,
|
| 449 |
+
"learning_rate": 8.974358974358975e-05,
|
| 450 |
+
"loss": 1.7464,
|
| 451 |
+
"step": 3550
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.77,
|
| 455 |
+
"learning_rate": 7.692307692307693e-05,
|
| 456 |
+
"loss": 1.7271,
|
| 457 |
+
"step": 3600
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.81,
|
| 461 |
+
"learning_rate": 6.41025641025641e-05,
|
| 462 |
+
"loss": 1.7631,
|
| 463 |
+
"step": 3650
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 2.85,
|
| 467 |
+
"learning_rate": 5.128205128205128e-05,
|
| 468 |
+
"loss": 1.7462,
|
| 469 |
+
"step": 3700
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 2.88,
|
| 473 |
+
"learning_rate": 3.846153846153846e-05,
|
| 474 |
+
"loss": 1.7318,
|
| 475 |
+
"step": 3750
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 2.92,
|
| 479 |
+
"learning_rate": 2.564102564102564e-05,
|
| 480 |
+
"loss": 1.724,
|
| 481 |
+
"step": 3800
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 2.96,
|
| 485 |
+
"learning_rate": 1.282051282051282e-05,
|
| 486 |
+
"loss": 1.7065,
|
| 487 |
+
"step": 3850
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 3.0,
|
| 491 |
+
"learning_rate": 0.0,
|
| 492 |
+
"loss": 1.7189,
|
| 493 |
+
"step": 3900
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 3.0,
|
| 497 |
+
"eval_loss": 2.406733751296997,
|
| 498 |
+
"eval_runtime": 39.7653,
|
| 499 |
+
"eval_samples_per_second": 261.56,
|
| 500 |
+
"eval_steps_per_second": 8.198,
|
| 501 |
+
"step": 3900
|
| 502 |
+
}
|
| 503 |
+
],
|
| 504 |
+
"logging_steps": 50,
|
| 505 |
+
"max_steps": 3900,
|
| 506 |
+
"num_train_epochs": 3,
|
| 507 |
+
"save_steps": 500,
|
| 508 |
+
"total_flos": 6647135438315520.0,
|
| 509 |
+
"trial_name": null,
|
| 510 |
+
"trial_params": null
|
| 511 |
+
}
|
checkpoint-3900/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5863f7260e5f2acd6ed9097371440ce6f89c0fdc0fbea3c0b7bd599e0244316f
|
| 3 |
+
size 4027
|
config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilgpt2",
|
| 3 |
+
"_num_labels": 1,
|
| 4 |
+
"activation_function": "gelu_new",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"GPT2LMHeadModel"
|
| 7 |
+
],
|
| 8 |
+
"attn_pdrop": 0.1,
|
| 9 |
+
"bos_token_id": 50256,
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_epsilon": 1e-05,
|
| 20 |
+
"model_type": "gpt2",
|
| 21 |
+
"n_ctx": 1024,
|
| 22 |
+
"n_embd": 768,
|
| 23 |
+
"n_head": 12,
|
| 24 |
+
"n_inner": null,
|
| 25 |
+
"n_layer": 6,
|
| 26 |
+
"n_positions": 1024,
|
| 27 |
+
"reorder_and_upcast_attn": false,
|
| 28 |
+
"resid_pdrop": 0.1,
|
| 29 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 30 |
+
"scale_attn_weights": true,
|
| 31 |
+
"summary_activation": null,
|
| 32 |
+
"summary_first_dropout": 0.1,
|
| 33 |
+
"summary_proj_to_labels": true,
|
| 34 |
+
"summary_type": "cls_index",
|
| 35 |
+
"summary_use_proj": true,
|
| 36 |
+
"task_specific_params": {
|
| 37 |
+
"text-generation": {
|
| 38 |
+
"do_sample": true,
|
| 39 |
+
"max_length": 50
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.32.1",
|
| 44 |
+
"use_cache": true,
|
| 45 |
+
"vocab_size": 50257
|
| 46 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.32.1"
|
| 6 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d254aeaf5388d54112768c1e776c979981bbe1ff7708fe3e83c9c20870b05fa
|
| 3 |
+
size 327674773
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5863f7260e5f2acd6ed9097371440ce6f89c0fdc0fbea3c0b7bd599e0244316f
|
| 3 |
+
size 4027
|