Training in progress, epoch 1, checkpoint
Browse files- checkpoint-4/README.md +21 -0
- checkpoint-4/adapter_config.json +26 -0
- checkpoint-4/adapter_model.bin +3 -0
- checkpoint-4/merges.txt +0 -0
- checkpoint-4/optimizer.pt +3 -0
- checkpoint-4/rng_state.pth +3 -0
- checkpoint-4/scheduler.pt +3 -0
- checkpoint-4/special_tokens_map.json +20 -0
- checkpoint-4/tokenizer_config.json +26 -0
- checkpoint-4/trainer_state.json +27 -0
- checkpoint-4/training_args.bin +3 -0
- checkpoint-4/vocab.json +0 -0
checkpoint-4/README.md
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- quant_method: bitsandbytes
|
9 |
+
- load_in_8bit: True
|
10 |
+
- load_in_4bit: False
|
11 |
+
- llm_int8_threshold: 4.0
|
12 |
+
- llm_int8_skip_modules: None
|
13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
14 |
+
- llm_int8_has_fp16_weight: False
|
15 |
+
- bnb_4bit_quant_type: fp4
|
16 |
+
- bnb_4bit_use_double_quant: False
|
17 |
+
- bnb_4bit_compute_dtype: bfloat16
|
18 |
+
### Framework versions
|
19 |
+
|
20 |
+
|
21 |
+
- PEFT 0.5.0
|
checkpoint-4/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "flaubert/flaubert_large_cased",
|
4 |
+
"bias": "all",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 16,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": [
|
13 |
+
"classifier.bias",
|
14 |
+
"classifier.weight"
|
15 |
+
],
|
16 |
+
"peft_type": "LORA",
|
17 |
+
"r": 16,
|
18 |
+
"revision": null,
|
19 |
+
"target_modules": [
|
20 |
+
"q_lin",
|
21 |
+
"k_lin",
|
22 |
+
"v_lin",
|
23 |
+
"out_lin"
|
24 |
+
],
|
25 |
+
"task_type": "TOKEN_CLS"
|
26 |
+
}
|
checkpoint-4/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69d01cdfa8b30ff745d5e612123a815e0dbf4ddb3e1700172d7314d8d02e5d09
|
3 |
+
size 30440349
|
checkpoint-4/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-4/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7815b4c9010c60064ea3325b4eee9b32c34b150449f33c6c62e8951c223fbe3d
|
3 |
+
size 60898982
|
checkpoint-4/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5336281f41cb1f2a85ef1320992a24517ea5d9b76a7aacbdce850019a0f51d6
|
3 |
+
size 14575
|
checkpoint-4/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae3094f0027b432eee076116a5efe082c1c77789c9c2288da023fc9e05266808
|
3 |
+
size 627
|
checkpoint-4/special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<special0>",
|
4 |
+
"<special1>",
|
5 |
+
"<special2>",
|
6 |
+
"<special3>",
|
7 |
+
"<special4>",
|
8 |
+
"<special5>",
|
9 |
+
"<special6>",
|
10 |
+
"<special7>",
|
11 |
+
"<special8>",
|
12 |
+
"<special9>"
|
13 |
+
],
|
14 |
+
"bos_token": "<s>",
|
15 |
+
"cls_token": "</s>",
|
16 |
+
"mask_token": "<special1>",
|
17 |
+
"pad_token": "<pad>",
|
18 |
+
"sep_token": "</s>",
|
19 |
+
"unk_token": "<unk>"
|
20 |
+
}
|
checkpoint-4/tokenizer_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<special0>",
|
4 |
+
"<special1>",
|
5 |
+
"<special2>",
|
6 |
+
"<special3>",
|
7 |
+
"<special4>",
|
8 |
+
"<special5>",
|
9 |
+
"<special6>",
|
10 |
+
"<special7>",
|
11 |
+
"<special8>",
|
12 |
+
"<special9>"
|
13 |
+
],
|
14 |
+
"bos_token": "<s>",
|
15 |
+
"clean_up_tokenization_spaces": true,
|
16 |
+
"cls_token": "</s>",
|
17 |
+
"do_lower_case": false,
|
18 |
+
"id2lang": null,
|
19 |
+
"lang2id": null,
|
20 |
+
"mask_token": "<special1>",
|
21 |
+
"model_max_length": 512,
|
22 |
+
"pad_token": "<pad>",
|
23 |
+
"sep_token": "</s>",
|
24 |
+
"tokenizer_class": "FlaubertTokenizer",
|
25 |
+
"unk_token": "<unk>"
|
26 |
+
}
|
checkpoint-4/trainer_state.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 4,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": NaN,
|
14 |
+
"eval_runtime": 11.7568,
|
15 |
+
"eval_samples_per_second": 430.984,
|
16 |
+
"eval_steps_per_second": 13.524,
|
17 |
+
"step": 4
|
18 |
+
}
|
19 |
+
],
|
20 |
+
"logging_steps": 2000,
|
21 |
+
"max_steps": 400,
|
22 |
+
"num_train_epochs": 100,
|
23 |
+
"save_steps": 500,
|
24 |
+
"total_flos": 7161154002048.0,
|
25 |
+
"trial_name": null,
|
26 |
+
"trial_params": null
|
27 |
+
}
|
checkpoint-4/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:238151b110e2e4dfc6ebf1dd217dc2b2ee63a49132a41b9b3baa63652e9edd25
|
3 |
+
size 4219
|
checkpoint-4/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|