Upload 32 files
Browse files- essays/README.md +55 -0
- essays/added_tokens.json +3 -0
- essays/all_results.json +15 -0
- essays/checkpoint-500/added_tokens.json +3 -0
- essays/checkpoint-500/config.json +42 -0
- essays/checkpoint-500/generation_config.json +6 -0
- essays/checkpoint-500/merges.txt +0 -0
- essays/checkpoint-500/optimizer.pt +3 -0
- essays/checkpoint-500/pytorch_model.bin +3 -0
- essays/checkpoint-500/rng_state.pth +3 -0
- essays/checkpoint-500/scheduler.pt +3 -0
- essays/checkpoint-500/special_tokens_map.json +23 -0
- essays/checkpoint-500/tokenizer.json +0 -0
- essays/checkpoint-500/tokenizer_config.json +34 -0
- essays/checkpoint-500/trainer_state.json +22 -0
- essays/checkpoint-500/training_args.bin +3 -0
- essays/checkpoint-500/vocab.json +0 -0
- essays/config.json +42 -0
- essays/eval_results.json +10 -0
- essays/generation_config.json +6 -0
- essays/merges.txt +0 -0
- essays/pytorch_model.bin +3 -0
- essays/runs/Apr06_11-49-42_c4a44d0e4fd9/1680781807.6289053/events.out.tfevents.1680781807.c4a44d0e4fd9.196.1 +3 -0
- essays/runs/Apr06_11-49-42_c4a44d0e4fd9/events.out.tfevents.1680781807.c4a44d0e4fd9.196.0 +3 -0
- essays/runs/Apr06_11-49-42_c4a44d0e4fd9/events.out.tfevents.1680782185.c4a44d0e4fd9.196.2 +3 -0
- essays/special_tokens_map.json +23 -0
- essays/tokenizer.json +0 -0
- essays/tokenizer_config.json +34 -0
- essays/train_results.json +8 -0
- essays/trainer_state.json +31 -0
- essays/training_args.bin +3 -0
- essays/vocab.json +0 -0
essays/README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- accuracy
|
6 |
+
model-index:
|
7 |
+
- name: essays
|
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 |
+
# essays
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [sberbank-ai/rugpt3medium_based_on_gpt2](https://huggingface.co/sberbank-ai/rugpt3medium_based_on_gpt2) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 2.3529
|
19 |
+
- Accuracy: 0.5525
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 5e-05
|
39 |
+
- train_batch_size: 1
|
40 |
+
- eval_batch_size: 1
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 3.0
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- Transformers 4.28.0.dev0
|
53 |
+
- Pytorch 1.13.0
|
54 |
+
- Datasets 2.1.0
|
55 |
+
- Tokenizers 0.13.2
|
essays/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 50257
|
3 |
+
}
|
essays/all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.5524600847181492,
|
4 |
+
"eval_loss": 2.352853775024414,
|
5 |
+
"eval_runtime": 3.3047,
|
6 |
+
"eval_samples": 18,
|
7 |
+
"eval_samples_per_second": 5.447,
|
8 |
+
"eval_steps_per_second": 5.447,
|
9 |
+
"perplexity": 10.515535919777124,
|
10 |
+
"train_loss": 2.2163170891839106,
|
11 |
+
"train_runtime": 371.3638,
|
12 |
+
"train_samples": 185,
|
13 |
+
"train_samples_per_second": 1.494,
|
14 |
+
"train_steps_per_second": 1.494
|
15 |
+
}
|
essays/checkpoint-500/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 50257
|
3 |
+
}
|
essays/checkpoint-500/config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sberbank-ai/rugpt3medium_based_on_gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"label2id": {
|
16 |
+
"LABEL_0": 0
|
17 |
+
},
|
18 |
+
"layer_norm_epsilon": 1e-05,
|
19 |
+
"model_type": "gpt2",
|
20 |
+
"n_ctx": 2048,
|
21 |
+
"n_embd": 1024,
|
22 |
+
"n_head": 16,
|
23 |
+
"n_inner": null,
|
24 |
+
"n_layer": 24,
|
25 |
+
"n_positions": 2048,
|
26 |
+
"n_special": 0,
|
27 |
+
"output_past": true,
|
28 |
+
"predict_special_tokens": true,
|
29 |
+
"reorder_and_upcast_attn": false,
|
30 |
+
"resid_pdrop": 0.1,
|
31 |
+
"scale_attn_by_inverse_layer_idx": false,
|
32 |
+
"scale_attn_weights": true,
|
33 |
+
"summary_activation": null,
|
34 |
+
"summary_first_dropout": 0.1,
|
35 |
+
"summary_proj_to_labels": true,
|
36 |
+
"summary_type": "cls_index",
|
37 |
+
"summary_use_proj": true,
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.28.0.dev0",
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 50258
|
42 |
+
}
|
essays/checkpoint-500/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": "4.28.0.dev0"
|
6 |
+
}
|
essays/checkpoint-500/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
essays/checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:918d50b58ee0cb8747805cae2e4a787f7ef848eb21c7f4da4c799d0f5193e4a5
|
3 |
+
size 2847153349
|
essays/checkpoint-500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ccec3a81bf5d2599586dde1be12e73b88f61be7901a0caa4c880d1f11998d0b
|
3 |
+
size 1524265245
|
essays/checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7131747db73d14f50009ddafb9783592fd9286191b52c4e70fed693af48eaf53
|
3 |
+
size 14575
|
essays/checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b355d81bdb20ea2acf79e39128e85de5aa051c9f16ee4faade2b6f23dbeada4
|
3 |
+
size 627
|
essays/checkpoint-500/special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
essays/checkpoint-500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
essays/checkpoint-500/tokenizer_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": true,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "<|endoftext|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"errors": "replace",
|
22 |
+
"model_max_length": 1000000000000000019884624838656,
|
23 |
+
"pad_token": null,
|
24 |
+
"special_tokens_map_file": null,
|
25 |
+
"tokenizer_class": "GPT2Tokenizer",
|
26 |
+
"unk_token": {
|
27 |
+
"__type": "AddedToken",
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
essays/checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.7027027027027026,
|
5 |
+
"global_step": 500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 2.7,
|
12 |
+
"learning_rate": 4.954954954954955e-06,
|
13 |
+
"loss": 2.2712,
|
14 |
+
"step": 500
|
15 |
+
}
|
16 |
+
],
|
17 |
+
"max_steps": 555,
|
18 |
+
"num_train_epochs": 3,
|
19 |
+
"total_flos": 928700694528000.0,
|
20 |
+
"trial_name": null,
|
21 |
+
"trial_params": null
|
22 |
+
}
|
essays/checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59932aaaf017b52565ed949386730e8ba6500baffdb5bf042664bd41503926f8
|
3 |
+
size 3579
|
essays/checkpoint-500/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
essays/config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sberbank-ai/rugpt3medium_based_on_gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"label2id": {
|
16 |
+
"LABEL_0": 0
|
17 |
+
},
|
18 |
+
"layer_norm_epsilon": 1e-05,
|
19 |
+
"model_type": "gpt2",
|
20 |
+
"n_ctx": 2048,
|
21 |
+
"n_embd": 1024,
|
22 |
+
"n_head": 16,
|
23 |
+
"n_inner": null,
|
24 |
+
"n_layer": 24,
|
25 |
+
"n_positions": 2048,
|
26 |
+
"n_special": 0,
|
27 |
+
"output_past": true,
|
28 |
+
"predict_special_tokens": true,
|
29 |
+
"reorder_and_upcast_attn": false,
|
30 |
+
"resid_pdrop": 0.1,
|
31 |
+
"scale_attn_by_inverse_layer_idx": false,
|
32 |
+
"scale_attn_weights": true,
|
33 |
+
"summary_activation": null,
|
34 |
+
"summary_first_dropout": 0.1,
|
35 |
+
"summary_proj_to_labels": true,
|
36 |
+
"summary_type": "cls_index",
|
37 |
+
"summary_use_proj": true,
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.28.0.dev0",
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 50258
|
42 |
+
}
|
essays/eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.5524600847181492,
|
4 |
+
"eval_loss": 2.352853775024414,
|
5 |
+
"eval_runtime": 3.3047,
|
6 |
+
"eval_samples": 18,
|
7 |
+
"eval_samples_per_second": 5.447,
|
8 |
+
"eval_steps_per_second": 5.447,
|
9 |
+
"perplexity": 10.515535919777124
|
10 |
+
}
|
essays/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": "4.28.0.dev0"
|
6 |
+
}
|
essays/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
essays/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa1807f8948208c0df1351973a78e3f1418d3c5d24ebf6eab692ca5af121486c
|
3 |
+
size 1524265245
|
essays/runs/Apr06_11-49-42_c4a44d0e4fd9/1680781807.6289053/events.out.tfevents.1680781807.c4a44d0e4fd9.196.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00b3ea5b3426894cca6236e1626971dd9c5083cedd79ff294a08f0c0e5d1cd79
|
3 |
+
size 5816
|
essays/runs/Apr06_11-49-42_c4a44d0e4fd9/events.out.tfevents.1680781807.c4a44d0e4fd9.196.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc71a0de09ebbba3b212337071cdf09d5b2f3304d95ca78d4e3695a7865daeed
|
3 |
+
size 4722
|
essays/runs/Apr06_11-49-42_c4a44d0e4fd9/events.out.tfevents.1680782185.c4a44d0e4fd9.196.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:691fb419bdfe55603829db2d6d215564e29ba254de4b6905f8a916602d7c834e
|
3 |
+
size 363
|
essays/special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
essays/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
essays/tokenizer_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": true,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "<|endoftext|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"errors": "replace",
|
22 |
+
"model_max_length": 1000000000000000019884624838656,
|
23 |
+
"pad_token": null,
|
24 |
+
"special_tokens_map_file": null,
|
25 |
+
"tokenizer_class": "GPT2Tokenizer",
|
26 |
+
"unk_token": {
|
27 |
+
"__type": "AddedToken",
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
essays/train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 2.2163170891839106,
|
4 |
+
"train_runtime": 371.3638,
|
5 |
+
"train_samples": 185,
|
6 |
+
"train_samples_per_second": 1.494,
|
7 |
+
"train_steps_per_second": 1.494
|
8 |
+
}
|
essays/trainer_state.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 555,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 2.7,
|
12 |
+
"learning_rate": 4.954954954954955e-06,
|
13 |
+
"loss": 2.2712,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 3.0,
|
18 |
+
"step": 555,
|
19 |
+
"total_flos": 1030857770926080.0,
|
20 |
+
"train_loss": 2.2163170891839106,
|
21 |
+
"train_runtime": 371.3638,
|
22 |
+
"train_samples_per_second": 1.494,
|
23 |
+
"train_steps_per_second": 1.494
|
24 |
+
}
|
25 |
+
],
|
26 |
+
"max_steps": 555,
|
27 |
+
"num_train_epochs": 3,
|
28 |
+
"total_flos": 1030857770926080.0,
|
29 |
+
"trial_name": null,
|
30 |
+
"trial_params": null
|
31 |
+
}
|
essays/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59932aaaf017b52565ed949386730e8ba6500baffdb5bf042664bd41503926f8
|
3 |
+
size 3579
|
essays/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|