Training in progress, epoch 27, checkpoint
Browse files- checkpoint-6750/README.md +9 -0
- checkpoint-6750/adapter_config.json +25 -0
- checkpoint-6750/adapter_model.safetensors +3 -0
- checkpoint-6750/added_tokens.json +5 -0
- checkpoint-6750/merges.txt +0 -0
- checkpoint-6750/optimizer.pt +3 -0
- checkpoint-6750/rng_state_0.pth +3 -0
- checkpoint-6750/rng_state_1.pth +3 -0
- checkpoint-6750/rng_state_2.pth +3 -0
- checkpoint-6750/rng_state_3.pth +3 -0
- checkpoint-6750/scheduler.pt +3 -0
- checkpoint-6750/special_tokens_map.json +14 -0
- checkpoint-6750/tokenizer.json +0 -0
- checkpoint-6750/tokenizer_config.json +43 -0
- checkpoint-6750/trainer_state.json +907 -0
- checkpoint-6750/training_args.bin +3 -0
- checkpoint-6750/vocab.json +0 -0
checkpoint-6750/README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
### Framework versions
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
- PEFT 0.5.0
|
checkpoint-6750/adapter_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "Qwen/Qwen1.5-4B",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 16,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"k_proj",
|
| 19 |
+
"v_proj",
|
| 20 |
+
"down_proj",
|
| 21 |
+
"gate_proj",
|
| 22 |
+
"up_proj"
|
| 23 |
+
],
|
| 24 |
+
"task_type": "CAUSAL_LM"
|
| 25 |
+
}
|
checkpoint-6750/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d0c7f02ea251f1b66a57bab1c73b696e53ee57e117420675a8551c70eaebdca
|
| 3 |
+
size 112130416
|
checkpoint-6750/added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
checkpoint-6750/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-6750/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b33aa9b6da0fb8dc226877b38dd30dd0e5242454f599b095a8834b11bbb4c1ca
|
| 3 |
+
size 224537202
|
checkpoint-6750/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72930b7ab233fd44befc2f98c1c927b3e12862d425464023e2bd781ea7a64530
|
| 3 |
+
size 15024
|
checkpoint-6750/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5522f68f4d97ce857285af5a008cffc517b844838b9df52a022987f59fa08ba1
|
| 3 |
+
size 15024
|
checkpoint-6750/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad1fe3cf988351cf115a56bb5692fa8004df851ab0e8c991d79677e41b093fea
|
| 3 |
+
size 15024
|
checkpoint-6750/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17bcf37688900ff717e91367cb73252aea6be31a8d6d2fa469f70b84a1995094
|
| 3 |
+
size 15024
|
checkpoint-6750/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f9d9e34b687bba9346b3e030247ecf36a8bf9843f59a283aa2859b0eb93d92d
|
| 3 |
+
size 1064
|
checkpoint-6750/special_tokens_map.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"eos_token": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"pad_token": "<|endoftext|>"
|
| 14 |
+
}
|
checkpoint-6750/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-6750/tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"additional_special_tokens": [
|
| 30 |
+
"<|im_start|>",
|
| 31 |
+
"<|im_end|>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": null,
|
| 34 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 35 |
+
"clean_up_tokenization_spaces": false,
|
| 36 |
+
"eos_token": "<|endoftext|>",
|
| 37 |
+
"errors": "replace",
|
| 38 |
+
"model_max_length": 32768,
|
| 39 |
+
"pad_token": "<|endoftext|>",
|
| 40 |
+
"split_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 42 |
+
"unk_token": null
|
| 43 |
+
}
|
checkpoint-6750/trainer_state.json
ADDED
|
@@ -0,0 +1,907 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 27.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6750,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.4,
|
| 13 |
+
"grad_norm": 0.6831097602844238,
|
| 14 |
+
"learning_rate": 3e-05,
|
| 15 |
+
"loss": 2.487,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.8,
|
| 20 |
+
"grad_norm": 0.7073227763175964,
|
| 21 |
+
"learning_rate": 3e-05,
|
| 22 |
+
"loss": 2.276,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0,
|
| 27 |
+
"eval_accuracy": 0.5134285714285715,
|
| 28 |
+
"eval_loss": 2.3502681255340576,
|
| 29 |
+
"eval_runtime": 5.2185,
|
| 30 |
+
"eval_samples_per_second": 95.812,
|
| 31 |
+
"eval_steps_per_second": 12.072,
|
| 32 |
+
"step": 250
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.0,
|
| 36 |
+
"eval_exact_match": 17.0,
|
| 37 |
+
"eval_f1": 24.54219480519481,
|
| 38 |
+
"step": 250
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.2,
|
| 42 |
+
"grad_norm": 0.820932149887085,
|
| 43 |
+
"learning_rate": 3e-05,
|
| 44 |
+
"loss": 2.2479,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.6,
|
| 49 |
+
"grad_norm": 0.9243379831314087,
|
| 50 |
+
"learning_rate": 3e-05,
|
| 51 |
+
"loss": 2.2237,
|
| 52 |
+
"step": 400
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 2.0,
|
| 56 |
+
"grad_norm": 0.8742844462394714,
|
| 57 |
+
"learning_rate": 3e-05,
|
| 58 |
+
"loss": 2.1973,
|
| 59 |
+
"step": 500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.0,
|
| 63 |
+
"eval_accuracy": 0.5151746031746032,
|
| 64 |
+
"eval_loss": 2.330955743789673,
|
| 65 |
+
"eval_runtime": 5.5478,
|
| 66 |
+
"eval_samples_per_second": 90.125,
|
| 67 |
+
"eval_steps_per_second": 11.356,
|
| 68 |
+
"step": 500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.0,
|
| 72 |
+
"eval_exact_match": 16.2,
|
| 73 |
+
"eval_f1": 24.397655122655127,
|
| 74 |
+
"step": 500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.4,
|
| 78 |
+
"grad_norm": 1.034700632095337,
|
| 79 |
+
"learning_rate": 3e-05,
|
| 80 |
+
"loss": 2.1295,
|
| 81 |
+
"step": 600
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.8,
|
| 85 |
+
"grad_norm": 1.130967617034912,
|
| 86 |
+
"learning_rate": 3e-05,
|
| 87 |
+
"loss": 2.1128,
|
| 88 |
+
"step": 700
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 3.0,
|
| 92 |
+
"eval_accuracy": 0.516095238095238,
|
| 93 |
+
"eval_loss": 2.3357651233673096,
|
| 94 |
+
"eval_runtime": 5.8761,
|
| 95 |
+
"eval_samples_per_second": 85.091,
|
| 96 |
+
"eval_steps_per_second": 10.721,
|
| 97 |
+
"step": 750
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 3.0,
|
| 101 |
+
"eval_exact_match": 19.0,
|
| 102 |
+
"eval_f1": 26.202922077922086,
|
| 103 |
+
"step": 750
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 3.2,
|
| 107 |
+
"grad_norm": 1.4410409927368164,
|
| 108 |
+
"learning_rate": 3e-05,
|
| 109 |
+
"loss": 2.0768,
|
| 110 |
+
"step": 800
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.6,
|
| 114 |
+
"grad_norm": 1.5838419198989868,
|
| 115 |
+
"learning_rate": 3e-05,
|
| 116 |
+
"loss": 2.0139,
|
| 117 |
+
"step": 900
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.0,
|
| 121 |
+
"grad_norm": 1.824843406677246,
|
| 122 |
+
"learning_rate": 3e-05,
|
| 123 |
+
"loss": 2.0165,
|
| 124 |
+
"step": 1000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 4.0,
|
| 128 |
+
"eval_accuracy": 0.5151746031746032,
|
| 129 |
+
"eval_loss": 2.355579376220703,
|
| 130 |
+
"eval_runtime": 5.1124,
|
| 131 |
+
"eval_samples_per_second": 97.801,
|
| 132 |
+
"eval_steps_per_second": 12.323,
|
| 133 |
+
"step": 1000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 4.0,
|
| 137 |
+
"eval_exact_match": 19.0,
|
| 138 |
+
"eval_f1": 26.60538961038962,
|
| 139 |
+
"step": 1000
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 4.4,
|
| 143 |
+
"grad_norm": 1.988659381866455,
|
| 144 |
+
"learning_rate": 3e-05,
|
| 145 |
+
"loss": 1.8919,
|
| 146 |
+
"step": 1100
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 4.8,
|
| 150 |
+
"grad_norm": 2.1034774780273438,
|
| 151 |
+
"learning_rate": 3e-05,
|
| 152 |
+
"loss": 1.9024,
|
| 153 |
+
"step": 1200
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 5.0,
|
| 157 |
+
"eval_accuracy": 0.5138730158730159,
|
| 158 |
+
"eval_loss": 2.4047114849090576,
|
| 159 |
+
"eval_runtime": 5.507,
|
| 160 |
+
"eval_samples_per_second": 90.794,
|
| 161 |
+
"eval_steps_per_second": 11.44,
|
| 162 |
+
"step": 1250
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 5.0,
|
| 166 |
+
"eval_exact_match": 19.2,
|
| 167 |
+
"eval_f1": 27.08811688311689,
|
| 168 |
+
"step": 1250
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 5.2,
|
| 172 |
+
"grad_norm": 2.2108240127563477,
|
| 173 |
+
"learning_rate": 3e-05,
|
| 174 |
+
"loss": 1.852,
|
| 175 |
+
"step": 1300
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 5.6,
|
| 179 |
+
"grad_norm": 2.507085084915161,
|
| 180 |
+
"learning_rate": 3e-05,
|
| 181 |
+
"loss": 1.7877,
|
| 182 |
+
"step": 1400
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 6.0,
|
| 186 |
+
"grad_norm": 2.3765366077423096,
|
| 187 |
+
"learning_rate": 3e-05,
|
| 188 |
+
"loss": 1.7989,
|
| 189 |
+
"step": 1500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 6.0,
|
| 193 |
+
"eval_accuracy": 0.5111111111111111,
|
| 194 |
+
"eval_loss": 2.4534740447998047,
|
| 195 |
+
"eval_runtime": 5.199,
|
| 196 |
+
"eval_samples_per_second": 96.172,
|
| 197 |
+
"eval_steps_per_second": 12.118,
|
| 198 |
+
"step": 1500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 6.0,
|
| 202 |
+
"eval_exact_match": 18.2,
|
| 203 |
+
"eval_f1": 26.325503531556176,
|
| 204 |
+
"step": 1500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 6.4,
|
| 208 |
+
"grad_norm": 2.944777727127075,
|
| 209 |
+
"learning_rate": 3e-05,
|
| 210 |
+
"loss": 1.6784,
|
| 211 |
+
"step": 1600
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 6.8,
|
| 215 |
+
"grad_norm": 2.8724122047424316,
|
| 216 |
+
"learning_rate": 3e-05,
|
| 217 |
+
"loss": 1.692,
|
| 218 |
+
"step": 1700
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 7.0,
|
| 222 |
+
"eval_accuracy": 0.5085714285714286,
|
| 223 |
+
"eval_loss": 2.527308464050293,
|
| 224 |
+
"eval_runtime": 5.9179,
|
| 225 |
+
"eval_samples_per_second": 84.489,
|
| 226 |
+
"eval_steps_per_second": 10.646,
|
| 227 |
+
"step": 1750
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 7.0,
|
| 231 |
+
"eval_exact_match": 17.4,
|
| 232 |
+
"eval_f1": 25.36568542568543,
|
| 233 |
+
"step": 1750
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 7.2,
|
| 237 |
+
"grad_norm": 3.7004809379577637,
|
| 238 |
+
"learning_rate": 3e-05,
|
| 239 |
+
"loss": 1.6336,
|
| 240 |
+
"step": 1800
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 7.6,
|
| 244 |
+
"grad_norm": 3.611534595489502,
|
| 245 |
+
"learning_rate": 3e-05,
|
| 246 |
+
"loss": 1.5772,
|
| 247 |
+
"step": 1900
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 8.0,
|
| 251 |
+
"grad_norm": 3.311814546585083,
|
| 252 |
+
"learning_rate": 3e-05,
|
| 253 |
+
"loss": 1.5963,
|
| 254 |
+
"step": 2000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 8.0,
|
| 258 |
+
"eval_accuracy": 0.5057142857142857,
|
| 259 |
+
"eval_loss": 2.6106724739074707,
|
| 260 |
+
"eval_runtime": 5.9096,
|
| 261 |
+
"eval_samples_per_second": 84.608,
|
| 262 |
+
"eval_steps_per_second": 10.661,
|
| 263 |
+
"step": 2000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 8.0,
|
| 267 |
+
"eval_exact_match": 16.4,
|
| 268 |
+
"eval_f1": 24.649942279942284,
|
| 269 |
+
"step": 2000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 8.4,
|
| 273 |
+
"grad_norm": 4.057112693786621,
|
| 274 |
+
"learning_rate": 3e-05,
|
| 275 |
+
"loss": 1.4604,
|
| 276 |
+
"step": 2100
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 8.8,
|
| 280 |
+
"grad_norm": 3.5819571018218994,
|
| 281 |
+
"learning_rate": 3e-05,
|
| 282 |
+
"loss": 1.482,
|
| 283 |
+
"step": 2200
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 9.0,
|
| 287 |
+
"eval_accuracy": 0.5044761904761905,
|
| 288 |
+
"eval_loss": 2.6719970703125,
|
| 289 |
+
"eval_runtime": 5.8123,
|
| 290 |
+
"eval_samples_per_second": 86.024,
|
| 291 |
+
"eval_steps_per_second": 10.839,
|
| 292 |
+
"step": 2250
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 9.0,
|
| 296 |
+
"eval_exact_match": 16.0,
|
| 297 |
+
"eval_f1": 24.24823953823954,
|
| 298 |
+
"step": 2250
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 9.2,
|
| 302 |
+
"grad_norm": 4.373803615570068,
|
| 303 |
+
"learning_rate": 3e-05,
|
| 304 |
+
"loss": 1.4256,
|
| 305 |
+
"step": 2300
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 9.6,
|
| 309 |
+
"grad_norm": 4.550878047943115,
|
| 310 |
+
"learning_rate": 3e-05,
|
| 311 |
+
"loss": 1.3686,
|
| 312 |
+
"step": 2400
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 10.0,
|
| 316 |
+
"grad_norm": 4.786899566650391,
|
| 317 |
+
"learning_rate": 3e-05,
|
| 318 |
+
"loss": 1.4113,
|
| 319 |
+
"step": 2500
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 10.0,
|
| 323 |
+
"eval_accuracy": 0.502,
|
| 324 |
+
"eval_loss": 2.7534008026123047,
|
| 325 |
+
"eval_runtime": 5.7013,
|
| 326 |
+
"eval_samples_per_second": 87.699,
|
| 327 |
+
"eval_steps_per_second": 11.05,
|
| 328 |
+
"step": 2500
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 10.0,
|
| 332 |
+
"eval_exact_match": 15.4,
|
| 333 |
+
"eval_f1": 23.549242424242422,
|
| 334 |
+
"step": 2500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 10.4,
|
| 338 |
+
"grad_norm": 4.900534152984619,
|
| 339 |
+
"learning_rate": 3e-05,
|
| 340 |
+
"loss": 1.2413,
|
| 341 |
+
"step": 2600
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 10.8,
|
| 345 |
+
"grad_norm": 4.867775917053223,
|
| 346 |
+
"learning_rate": 3e-05,
|
| 347 |
+
"loss": 1.2975,
|
| 348 |
+
"step": 2700
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 11.0,
|
| 352 |
+
"eval_accuracy": 0.49768253968253967,
|
| 353 |
+
"eval_loss": 2.879622459411621,
|
| 354 |
+
"eval_runtime": 5.1716,
|
| 355 |
+
"eval_samples_per_second": 96.682,
|
| 356 |
+
"eval_steps_per_second": 12.182,
|
| 357 |
+
"step": 2750
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 11.0,
|
| 361 |
+
"eval_exact_match": 14.4,
|
| 362 |
+
"eval_f1": 22.511400984636275,
|
| 363 |
+
"step": 2750
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 11.2,
|
| 367 |
+
"grad_norm": 5.5839762687683105,
|
| 368 |
+
"learning_rate": 3e-05,
|
| 369 |
+
"loss": 1.2278,
|
| 370 |
+
"step": 2800
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 11.6,
|
| 374 |
+
"grad_norm": 5.194231033325195,
|
| 375 |
+
"learning_rate": 3e-05,
|
| 376 |
+
"loss": 1.1735,
|
| 377 |
+
"step": 2900
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 12.0,
|
| 381 |
+
"grad_norm": 5.112034320831299,
|
| 382 |
+
"learning_rate": 3e-05,
|
| 383 |
+
"loss": 1.2252,
|
| 384 |
+
"step": 3000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 12.0,
|
| 388 |
+
"eval_accuracy": 0.49726984126984125,
|
| 389 |
+
"eval_loss": 2.9103872776031494,
|
| 390 |
+
"eval_runtime": 5.5732,
|
| 391 |
+
"eval_samples_per_second": 89.715,
|
| 392 |
+
"eval_steps_per_second": 11.304,
|
| 393 |
+
"step": 3000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 12.0,
|
| 397 |
+
"eval_exact_match": 15.2,
|
| 398 |
+
"eval_f1": 23.043532578532574,
|
| 399 |
+
"step": 3000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 12.4,
|
| 403 |
+
"grad_norm": 5.978336811065674,
|
| 404 |
+
"learning_rate": 3e-05,
|
| 405 |
+
"loss": 1.0547,
|
| 406 |
+
"step": 3100
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 12.8,
|
| 410 |
+
"grad_norm": 6.005147457122803,
|
| 411 |
+
"learning_rate": 3e-05,
|
| 412 |
+
"loss": 1.1115,
|
| 413 |
+
"step": 3200
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 13.0,
|
| 417 |
+
"eval_accuracy": 0.4933968253968254,
|
| 418 |
+
"eval_loss": 3.0717053413391113,
|
| 419 |
+
"eval_runtime": 5.9334,
|
| 420 |
+
"eval_samples_per_second": 84.268,
|
| 421 |
+
"eval_steps_per_second": 10.618,
|
| 422 |
+
"step": 3250
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 13.0,
|
| 426 |
+
"eval_exact_match": 14.6,
|
| 427 |
+
"eval_f1": 22.054864188099476,
|
| 428 |
+
"step": 3250
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 13.2,
|
| 432 |
+
"grad_norm": 5.244001865386963,
|
| 433 |
+
"learning_rate": 3e-05,
|
| 434 |
+
"loss": 1.0529,
|
| 435 |
+
"step": 3300
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 13.6,
|
| 439 |
+
"grad_norm": 5.950862407684326,
|
| 440 |
+
"learning_rate": 3e-05,
|
| 441 |
+
"loss": 0.9932,
|
| 442 |
+
"step": 3400
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 14.0,
|
| 446 |
+
"grad_norm": 6.013063430786133,
|
| 447 |
+
"learning_rate": 3e-05,
|
| 448 |
+
"loss": 1.0383,
|
| 449 |
+
"step": 3500
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 14.0,
|
| 453 |
+
"eval_accuracy": 0.49266666666666664,
|
| 454 |
+
"eval_loss": 3.125173807144165,
|
| 455 |
+
"eval_runtime": 5.6035,
|
| 456 |
+
"eval_samples_per_second": 89.231,
|
| 457 |
+
"eval_steps_per_second": 11.243,
|
| 458 |
+
"step": 3500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 14.0,
|
| 462 |
+
"eval_exact_match": 15.0,
|
| 463 |
+
"eval_f1": 21.879737484737486,
|
| 464 |
+
"step": 3500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 14.4,
|
| 468 |
+
"grad_norm": 5.269447326660156,
|
| 469 |
+
"learning_rate": 3e-05,
|
| 470 |
+
"loss": 0.8977,
|
| 471 |
+
"step": 3600
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 14.8,
|
| 475 |
+
"grad_norm": 6.836198806762695,
|
| 476 |
+
"learning_rate": 3e-05,
|
| 477 |
+
"loss": 0.9499,
|
| 478 |
+
"step": 3700
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 15.0,
|
| 482 |
+
"eval_accuracy": 0.4914603174603175,
|
| 483 |
+
"eval_loss": 3.2221622467041016,
|
| 484 |
+
"eval_runtime": 5.3505,
|
| 485 |
+
"eval_samples_per_second": 93.45,
|
| 486 |
+
"eval_steps_per_second": 11.775,
|
| 487 |
+
"step": 3750
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 15.0,
|
| 491 |
+
"eval_exact_match": 13.4,
|
| 492 |
+
"eval_f1": 20.79952508276038,
|
| 493 |
+
"step": 3750
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 15.2,
|
| 497 |
+
"grad_norm": 6.335363864898682,
|
| 498 |
+
"learning_rate": 3e-05,
|
| 499 |
+
"loss": 0.8826,
|
| 500 |
+
"step": 3800
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 15.6,
|
| 504 |
+
"grad_norm": 5.659422874450684,
|
| 505 |
+
"learning_rate": 3e-05,
|
| 506 |
+
"loss": 0.856,
|
| 507 |
+
"step": 3900
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 16.0,
|
| 511 |
+
"grad_norm": 6.786794662475586,
|
| 512 |
+
"learning_rate": 3e-05,
|
| 513 |
+
"loss": 0.8822,
|
| 514 |
+
"step": 4000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 16.0,
|
| 518 |
+
"eval_accuracy": 0.4902222222222222,
|
| 519 |
+
"eval_loss": 3.3250105381011963,
|
| 520 |
+
"eval_runtime": 5.1577,
|
| 521 |
+
"eval_samples_per_second": 96.942,
|
| 522 |
+
"eval_steps_per_second": 12.215,
|
| 523 |
+
"step": 4000
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 16.0,
|
| 527 |
+
"eval_exact_match": 14.2,
|
| 528 |
+
"eval_f1": 21.066072261072264,
|
| 529 |
+
"step": 4000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 16.4,
|
| 533 |
+
"grad_norm": 5.888409614562988,
|
| 534 |
+
"learning_rate": 3e-05,
|
| 535 |
+
"loss": 0.7622,
|
| 536 |
+
"step": 4100
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 16.8,
|
| 540 |
+
"grad_norm": 7.211881637573242,
|
| 541 |
+
"learning_rate": 3e-05,
|
| 542 |
+
"loss": 0.8066,
|
| 543 |
+
"step": 4200
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 17.0,
|
| 547 |
+
"eval_accuracy": 0.48803174603174604,
|
| 548 |
+
"eval_loss": 3.4266793727874756,
|
| 549 |
+
"eval_runtime": 5.4926,
|
| 550 |
+
"eval_samples_per_second": 91.032,
|
| 551 |
+
"eval_steps_per_second": 11.47,
|
| 552 |
+
"step": 4250
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 17.0,
|
| 556 |
+
"eval_exact_match": 12.8,
|
| 557 |
+
"eval_f1": 19.07007936507936,
|
| 558 |
+
"step": 4250
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 17.2,
|
| 562 |
+
"grad_norm": 6.758857727050781,
|
| 563 |
+
"learning_rate": 3e-05,
|
| 564 |
+
"loss": 0.7589,
|
| 565 |
+
"step": 4300
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 17.6,
|
| 569 |
+
"grad_norm": 7.02708625793457,
|
| 570 |
+
"learning_rate": 3e-05,
|
| 571 |
+
"loss": 0.7328,
|
| 572 |
+
"step": 4400
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 18.0,
|
| 576 |
+
"grad_norm": 7.599416732788086,
|
| 577 |
+
"learning_rate": 3e-05,
|
| 578 |
+
"loss": 0.7585,
|
| 579 |
+
"step": 4500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 18.0,
|
| 583 |
+
"eval_accuracy": 0.48698412698412696,
|
| 584 |
+
"eval_loss": 3.494581460952759,
|
| 585 |
+
"eval_runtime": 5.1805,
|
| 586 |
+
"eval_samples_per_second": 96.517,
|
| 587 |
+
"eval_steps_per_second": 12.161,
|
| 588 |
+
"step": 4500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 18.0,
|
| 592 |
+
"eval_exact_match": 13.0,
|
| 593 |
+
"eval_f1": 20.018020313020315,
|
| 594 |
+
"step": 4500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 18.4,
|
| 598 |
+
"grad_norm": 6.632185935974121,
|
| 599 |
+
"learning_rate": 3e-05,
|
| 600 |
+
"loss": 0.6582,
|
| 601 |
+
"step": 4600
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 18.8,
|
| 605 |
+
"grad_norm": 5.955983638763428,
|
| 606 |
+
"learning_rate": 3e-05,
|
| 607 |
+
"loss": 0.6964,
|
| 608 |
+
"step": 4700
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 19.0,
|
| 612 |
+
"eval_accuracy": 0.48695238095238097,
|
| 613 |
+
"eval_loss": 3.539303779602051,
|
| 614 |
+
"eval_runtime": 5.9008,
|
| 615 |
+
"eval_samples_per_second": 84.734,
|
| 616 |
+
"eval_steps_per_second": 10.676,
|
| 617 |
+
"step": 4750
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 19.0,
|
| 621 |
+
"eval_exact_match": 12.8,
|
| 622 |
+
"eval_f1": 19.46184426684427,
|
| 623 |
+
"step": 4750
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 19.2,
|
| 627 |
+
"grad_norm": 5.696877479553223,
|
| 628 |
+
"learning_rate": 3e-05,
|
| 629 |
+
"loss": 0.6615,
|
| 630 |
+
"step": 4800
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 19.6,
|
| 634 |
+
"grad_norm": 7.173152446746826,
|
| 635 |
+
"learning_rate": 3e-05,
|
| 636 |
+
"loss": 0.6289,
|
| 637 |
+
"step": 4900
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 20.0,
|
| 641 |
+
"grad_norm": 6.438709259033203,
|
| 642 |
+
"learning_rate": 3e-05,
|
| 643 |
+
"loss": 0.6691,
|
| 644 |
+
"step": 5000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 20.0,
|
| 648 |
+
"eval_accuracy": 0.4853968253968254,
|
| 649 |
+
"eval_loss": 3.6216397285461426,
|
| 650 |
+
"eval_runtime": 5.1221,
|
| 651 |
+
"eval_samples_per_second": 97.616,
|
| 652 |
+
"eval_steps_per_second": 12.3,
|
| 653 |
+
"step": 5000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 20.0,
|
| 657 |
+
"eval_exact_match": 12.8,
|
| 658 |
+
"eval_f1": 19.78559607059607,
|
| 659 |
+
"step": 5000
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 20.4,
|
| 663 |
+
"grad_norm": 6.839606761932373,
|
| 664 |
+
"learning_rate": 3e-05,
|
| 665 |
+
"loss": 0.5758,
|
| 666 |
+
"step": 5100
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 20.8,
|
| 670 |
+
"grad_norm": 6.10357666015625,
|
| 671 |
+
"learning_rate": 3e-05,
|
| 672 |
+
"loss": 0.6149,
|
| 673 |
+
"step": 5200
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 21.0,
|
| 677 |
+
"eval_accuracy": 0.483968253968254,
|
| 678 |
+
"eval_loss": 3.7136757373809814,
|
| 679 |
+
"eval_runtime": 5.1433,
|
| 680 |
+
"eval_samples_per_second": 97.214,
|
| 681 |
+
"eval_steps_per_second": 12.249,
|
| 682 |
+
"step": 5250
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 21.0,
|
| 686 |
+
"eval_exact_match": 12.8,
|
| 687 |
+
"eval_f1": 19.9559423909424,
|
| 688 |
+
"step": 5250
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 21.2,
|
| 692 |
+
"grad_norm": 5.318624973297119,
|
| 693 |
+
"learning_rate": 3e-05,
|
| 694 |
+
"loss": 0.5813,
|
| 695 |
+
"step": 5300
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 21.6,
|
| 699 |
+
"grad_norm": 6.141844749450684,
|
| 700 |
+
"learning_rate": 3e-05,
|
| 701 |
+
"loss": 0.5679,
|
| 702 |
+
"step": 5400
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 22.0,
|
| 706 |
+
"grad_norm": 6.578658580780029,
|
| 707 |
+
"learning_rate": 3e-05,
|
| 708 |
+
"loss": 0.5868,
|
| 709 |
+
"step": 5500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 22.0,
|
| 713 |
+
"eval_accuracy": 0.48473015873015873,
|
| 714 |
+
"eval_loss": 3.7464139461517334,
|
| 715 |
+
"eval_runtime": 5.1846,
|
| 716 |
+
"eval_samples_per_second": 96.439,
|
| 717 |
+
"eval_steps_per_second": 12.151,
|
| 718 |
+
"step": 5500
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 22.0,
|
| 722 |
+
"eval_exact_match": 13.2,
|
| 723 |
+
"eval_f1": 19.690881504116803,
|
| 724 |
+
"step": 5500
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 22.4,
|
| 728 |
+
"grad_norm": 5.74013614654541,
|
| 729 |
+
"learning_rate": 3e-05,
|
| 730 |
+
"loss": 0.5198,
|
| 731 |
+
"step": 5600
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 22.8,
|
| 735 |
+
"grad_norm": 5.257986068725586,
|
| 736 |
+
"learning_rate": 3e-05,
|
| 737 |
+
"loss": 0.5482,
|
| 738 |
+
"step": 5700
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 23.0,
|
| 742 |
+
"eval_accuracy": 0.4843174603174603,
|
| 743 |
+
"eval_loss": 3.8386082649230957,
|
| 744 |
+
"eval_runtime": 5.2897,
|
| 745 |
+
"eval_samples_per_second": 94.524,
|
| 746 |
+
"eval_steps_per_second": 11.91,
|
| 747 |
+
"step": 5750
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 23.0,
|
| 751 |
+
"eval_exact_match": 12.4,
|
| 752 |
+
"eval_f1": 18.668079698079698,
|
| 753 |
+
"step": 5750
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 23.2,
|
| 757 |
+
"grad_norm": 5.609368324279785,
|
| 758 |
+
"learning_rate": 3e-05,
|
| 759 |
+
"loss": 0.5263,
|
| 760 |
+
"step": 5800
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 23.6,
|
| 764 |
+
"grad_norm": 4.999100208282471,
|
| 765 |
+
"learning_rate": 3e-05,
|
| 766 |
+
"loss": 0.5088,
|
| 767 |
+
"step": 5900
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 24.0,
|
| 771 |
+
"grad_norm": 5.820481777191162,
|
| 772 |
+
"learning_rate": 3e-05,
|
| 773 |
+
"loss": 0.5378,
|
| 774 |
+
"step": 6000
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 24.0,
|
| 778 |
+
"eval_accuracy": 0.483968253968254,
|
| 779 |
+
"eval_loss": 3.8912558555603027,
|
| 780 |
+
"eval_runtime": 5.3394,
|
| 781 |
+
"eval_samples_per_second": 93.643,
|
| 782 |
+
"eval_steps_per_second": 11.799,
|
| 783 |
+
"step": 6000
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 24.0,
|
| 787 |
+
"eval_exact_match": 12.8,
|
| 788 |
+
"eval_f1": 19.066715669950973,
|
| 789 |
+
"step": 6000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 24.4,
|
| 793 |
+
"grad_norm": 6.189323425292969,
|
| 794 |
+
"learning_rate": 3e-05,
|
| 795 |
+
"loss": 0.4814,
|
| 796 |
+
"step": 6100
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 24.8,
|
| 800 |
+
"grad_norm": 5.2845377922058105,
|
| 801 |
+
"learning_rate": 3e-05,
|
| 802 |
+
"loss": 0.4999,
|
| 803 |
+
"step": 6200
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 25.0,
|
| 807 |
+
"eval_accuracy": 0.4838730158730159,
|
| 808 |
+
"eval_loss": 3.8836069107055664,
|
| 809 |
+
"eval_runtime": 5.4771,
|
| 810 |
+
"eval_samples_per_second": 91.289,
|
| 811 |
+
"eval_steps_per_second": 11.502,
|
| 812 |
+
"step": 6250
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 25.0,
|
| 816 |
+
"eval_exact_match": 13.6,
|
| 817 |
+
"eval_f1": 20.643636526871827,
|
| 818 |
+
"step": 6250
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 25.2,
|
| 822 |
+
"grad_norm": 4.954625606536865,
|
| 823 |
+
"learning_rate": 3e-05,
|
| 824 |
+
"loss": 0.4858,
|
| 825 |
+
"step": 6300
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 25.6,
|
| 829 |
+
"grad_norm": 6.256702899932861,
|
| 830 |
+
"learning_rate": 3e-05,
|
| 831 |
+
"loss": 0.4767,
|
| 832 |
+
"step": 6400
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 26.0,
|
| 836 |
+
"grad_norm": 4.940384387969971,
|
| 837 |
+
"learning_rate": 3e-05,
|
| 838 |
+
"loss": 0.4916,
|
| 839 |
+
"step": 6500
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 26.0,
|
| 843 |
+
"eval_accuracy": 0.4831111111111111,
|
| 844 |
+
"eval_loss": 3.9729866981506348,
|
| 845 |
+
"eval_runtime": 5.8996,
|
| 846 |
+
"eval_samples_per_second": 84.752,
|
| 847 |
+
"eval_steps_per_second": 10.679,
|
| 848 |
+
"step": 6500
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 26.0,
|
| 852 |
+
"eval_exact_match": 12.6,
|
| 853 |
+
"eval_f1": 19.084161540214172,
|
| 854 |
+
"step": 6500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 26.4,
|
| 858 |
+
"grad_norm": 4.9096879959106445,
|
| 859 |
+
"learning_rate": 3e-05,
|
| 860 |
+
"loss": 0.4407,
|
| 861 |
+
"step": 6600
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 26.8,
|
| 865 |
+
"grad_norm": 5.645080089569092,
|
| 866 |
+
"learning_rate": 3e-05,
|
| 867 |
+
"loss": 0.4695,
|
| 868 |
+
"step": 6700
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 27.0,
|
| 872 |
+
"eval_accuracy": 0.4840952380952381,
|
| 873 |
+
"eval_loss": 4.012541770935059,
|
| 874 |
+
"eval_runtime": 5.3441,
|
| 875 |
+
"eval_samples_per_second": 93.561,
|
| 876 |
+
"eval_steps_per_second": 11.789,
|
| 877 |
+
"step": 6750
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 27.0,
|
| 881 |
+
"eval_exact_match": 12.8,
|
| 882 |
+
"eval_f1": 19.277558552558556,
|
| 883 |
+
"step": 6750
|
| 884 |
+
}
|
| 885 |
+
],
|
| 886 |
+
"logging_steps": 100,
|
| 887 |
+
"max_steps": 12500,
|
| 888 |
+
"num_input_tokens_seen": 0,
|
| 889 |
+
"num_train_epochs": 50,
|
| 890 |
+
"save_steps": 500,
|
| 891 |
+
"stateful_callbacks": {
|
| 892 |
+
"TrainerControl": {
|
| 893 |
+
"args": {
|
| 894 |
+
"should_epoch_stop": false,
|
| 895 |
+
"should_evaluate": false,
|
| 896 |
+
"should_log": false,
|
| 897 |
+
"should_save": true,
|
| 898 |
+
"should_training_stop": false
|
| 899 |
+
},
|
| 900 |
+
"attributes": {}
|
| 901 |
+
}
|
| 902 |
+
},
|
| 903 |
+
"total_flos": 2.065271732830208e+17,
|
| 904 |
+
"train_batch_size": 2,
|
| 905 |
+
"trial_name": null,
|
| 906 |
+
"trial_params": null
|
| 907 |
+
}
|
checkpoint-6750/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76141cb7041782161f7695865881a4df3a03be3731ae75640f405be3a5a6f23d
|
| 3 |
+
size 5304
|
checkpoint-6750/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|