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:f23a87b4017034cbecefb7839e0261f78baea981cec8e71341757b8cd10769bb
|
| 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 sha256:497b361e153bd4122f96288e099ae24ff4bf800fa0ede2e2f7f8bd840df1b9e5
|
| 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:cc43f47fd629c2cbe778a3b5298c38e6f7b9c7e52335d3df350c12d64b1e15b6
|
| 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": 0.5897082090377808,
|
| 14 |
+
"learning_rate": 0.0001,
|
| 15 |
+
"loss": 2.3566,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.8,
|
| 20 |
+
"grad_norm": 0.5390245914459229,
|
| 21 |
+
"learning_rate": 0.0001,
|
| 22 |
+
"loss": 2.2503,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0,
|
| 27 |
+
"eval_accuracy": 0.5155873015873016,
|
| 28 |
+
"eval_loss": 2.3237216472625732,
|
| 29 |
+
"eval_runtime": 6.3164,
|
| 30 |
+
"eval_samples_per_second": 79.159,
|
| 31 |
+
"eval_steps_per_second": 9.974,
|
| 32 |
+
"step": 250
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.0,
|
| 36 |
+
"eval_exact_match": 17.2,
|
| 37 |
+
"eval_f1": 25.586581359816655,
|
| 38 |
+
"step": 250
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.2,
|
| 42 |
+
"grad_norm": 0.7468857169151306,
|
| 43 |
+
"learning_rate": 0.0001,
|
| 44 |
+
"loss": 2.1798,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.6,
|
| 49 |
+
"grad_norm": 0.9109599590301514,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 2.1094,
|
| 52 |
+
"step": 400
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 2.0,
|
| 56 |
+
"grad_norm": 0.8458774089813232,
|
| 57 |
+
"learning_rate": 0.0001,
|
| 58 |
+
"loss": 2.087,
|
| 59 |
+
"step": 500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.0,
|
| 63 |
+
"eval_accuracy": 0.5163809523809524,
|
| 64 |
+
"eval_loss": 2.3309242725372314,
|
| 65 |
+
"eval_runtime": 5.1896,
|
| 66 |
+
"eval_samples_per_second": 96.347,
|
| 67 |
+
"eval_steps_per_second": 12.14,
|
| 68 |
+
"step": 500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.0,
|
| 72 |
+
"eval_exact_match": 18.6,
|
| 73 |
+
"eval_f1": 26.043196248196264,
|
| 74 |
+
"step": 500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.4,
|
| 78 |
+
"grad_norm": 1.171212077140808,
|
| 79 |
+
"learning_rate": 0.0001,
|
| 80 |
+
"loss": 1.8413,
|
| 81 |
+
"step": 600
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.8,
|
| 85 |
+
"grad_norm": 1.1294909715652466,
|
| 86 |
+
"learning_rate": 0.0001,
|
| 87 |
+
"loss": 1.849,
|
| 88 |
+
"step": 700
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 3.0,
|
| 92 |
+
"eval_accuracy": 0.5144761904761905,
|
| 93 |
+
"eval_loss": 2.401942253112793,
|
| 94 |
+
"eval_runtime": 5.5775,
|
| 95 |
+
"eval_samples_per_second": 89.646,
|
| 96 |
+
"eval_steps_per_second": 11.295,
|
| 97 |
+
"step": 750
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 3.0,
|
| 101 |
+
"eval_exact_match": 18.4,
|
| 102 |
+
"eval_f1": 26.966370002546494,
|
| 103 |
+
"step": 750
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 3.2,
|
| 107 |
+
"grad_norm": 1.5013824701309204,
|
| 108 |
+
"learning_rate": 0.0001,
|
| 109 |
+
"loss": 1.7322,
|
| 110 |
+
"step": 800
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.6,
|
| 114 |
+
"grad_norm": 1.4516321420669556,
|
| 115 |
+
"learning_rate": 0.0001,
|
| 116 |
+
"loss": 1.5908,
|
| 117 |
+
"step": 900
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.0,
|
| 121 |
+
"grad_norm": 1.6037466526031494,
|
| 122 |
+
"learning_rate": 0.0001,
|
| 123 |
+
"loss": 1.6193,
|
| 124 |
+
"step": 1000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 4.0,
|
| 128 |
+
"eval_accuracy": 0.5103809523809524,
|
| 129 |
+
"eval_loss": 2.5039021968841553,
|
| 130 |
+
"eval_runtime": 5.1568,
|
| 131 |
+
"eval_samples_per_second": 96.96,
|
| 132 |
+
"eval_steps_per_second": 12.217,
|
| 133 |
+
"step": 1000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 4.0,
|
| 137 |
+
"eval_exact_match": 18.4,
|
| 138 |
+
"eval_f1": 26.892813852813866,
|
| 139 |
+
"step": 1000
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 4.4,
|
| 143 |
+
"grad_norm": 1.7909170389175415,
|
| 144 |
+
"learning_rate": 0.0001,
|
| 145 |
+
"loss": 1.3298,
|
| 146 |
+
"step": 1100
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 4.8,
|
| 150 |
+
"grad_norm": 1.9236161708831787,
|
| 151 |
+
"learning_rate": 0.0001,
|
| 152 |
+
"loss": 1.3666,
|
| 153 |
+
"step": 1200
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 5.0,
|
| 157 |
+
"eval_accuracy": 0.505015873015873,
|
| 158 |
+
"eval_loss": 2.6543924808502197,
|
| 159 |
+
"eval_runtime": 5.5115,
|
| 160 |
+
"eval_samples_per_second": 90.719,
|
| 161 |
+
"eval_steps_per_second": 11.431,
|
| 162 |
+
"step": 1250
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 5.0,
|
| 166 |
+
"eval_exact_match": 18.4,
|
| 167 |
+
"eval_f1": 25.875286609941792,
|
| 168 |
+
"step": 1250
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 5.2,
|
| 172 |
+
"grad_norm": 1.8524874448776245,
|
| 173 |
+
"learning_rate": 0.0001,
|
| 174 |
+
"loss": 1.2381,
|
| 175 |
+
"step": 1300
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 5.6,
|
| 179 |
+
"grad_norm": 2.1092071533203125,
|
| 180 |
+
"learning_rate": 0.0001,
|
| 181 |
+
"loss": 1.1141,
|
| 182 |
+
"step": 1400
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 6.0,
|
| 186 |
+
"grad_norm": 2.065767288208008,
|
| 187 |
+
"learning_rate": 0.0001,
|
| 188 |
+
"loss": 1.1435,
|
| 189 |
+
"step": 1500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 6.0,
|
| 193 |
+
"eval_accuracy": 0.5010793650793651,
|
| 194 |
+
"eval_loss": 2.843566656112671,
|
| 195 |
+
"eval_runtime": 5.1394,
|
| 196 |
+
"eval_samples_per_second": 97.287,
|
| 197 |
+
"eval_steps_per_second": 12.258,
|
| 198 |
+
"step": 1500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 6.0,
|
| 202 |
+
"eval_exact_match": 17.4,
|
| 203 |
+
"eval_f1": 24.31514874014875,
|
| 204 |
+
"step": 1500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 6.4,
|
| 208 |
+
"grad_norm": 2.329406261444092,
|
| 209 |
+
"learning_rate": 0.0001,
|
| 210 |
+
"loss": 0.8887,
|
| 211 |
+
"step": 1600
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 6.8,
|
| 215 |
+
"grad_norm": 2.489598274230957,
|
| 216 |
+
"learning_rate": 0.0001,
|
| 217 |
+
"loss": 0.9171,
|
| 218 |
+
"step": 1700
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 7.0,
|
| 222 |
+
"eval_accuracy": 0.49707936507936507,
|
| 223 |
+
"eval_loss": 3.0319864749908447,
|
| 224 |
+
"eval_runtime": 5.3015,
|
| 225 |
+
"eval_samples_per_second": 94.313,
|
| 226 |
+
"eval_steps_per_second": 11.883,
|
| 227 |
+
"step": 1750
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 7.0,
|
| 231 |
+
"eval_exact_match": 16.0,
|
| 232 |
+
"eval_f1": 22.824985569985575,
|
| 233 |
+
"step": 1750
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 7.2,
|
| 237 |
+
"grad_norm": 2.764033794403076,
|
| 238 |
+
"learning_rate": 0.0001,
|
| 239 |
+
"loss": 0.8093,
|
| 240 |
+
"step": 1800
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 7.6,
|
| 244 |
+
"grad_norm": 2.5643441677093506,
|
| 245 |
+
"learning_rate": 0.0001,
|
| 246 |
+
"loss": 0.724,
|
| 247 |
+
"step": 1900
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 8.0,
|
| 251 |
+
"grad_norm": 2.074833631515503,
|
| 252 |
+
"learning_rate": 0.0001,
|
| 253 |
+
"loss": 0.7531,
|
| 254 |
+
"step": 2000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 8.0,
|
| 258 |
+
"eval_accuracy": 0.49304761904761907,
|
| 259 |
+
"eval_loss": 3.2584712505340576,
|
| 260 |
+
"eval_runtime": 5.2945,
|
| 261 |
+
"eval_samples_per_second": 94.438,
|
| 262 |
+
"eval_steps_per_second": 11.899,
|
| 263 |
+
"step": 2000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 8.0,
|
| 267 |
+
"eval_exact_match": 15.0,
|
| 268 |
+
"eval_f1": 21.895264180264185,
|
| 269 |
+
"step": 2000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 8.4,
|
| 273 |
+
"grad_norm": 2.649679660797119,
|
| 274 |
+
"learning_rate": 0.0001,
|
| 275 |
+
"loss": 0.5777,
|
| 276 |
+
"step": 2100
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 8.8,
|
| 280 |
+
"grad_norm": 2.1969234943389893,
|
| 281 |
+
"learning_rate": 0.0001,
|
| 282 |
+
"loss": 0.6101,
|
| 283 |
+
"step": 2200
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 9.0,
|
| 287 |
+
"eval_accuracy": 0.4925079365079365,
|
| 288 |
+
"eval_loss": 3.3418095111846924,
|
| 289 |
+
"eval_runtime": 5.1381,
|
| 290 |
+
"eval_samples_per_second": 97.312,
|
| 291 |
+
"eval_steps_per_second": 12.261,
|
| 292 |
+
"step": 2250
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 9.0,
|
| 296 |
+
"eval_exact_match": 14.4,
|
| 297 |
+
"eval_f1": 21.76202020202021,
|
| 298 |
+
"step": 2250
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 9.2,
|
| 302 |
+
"grad_norm": 1.8318747282028198,
|
| 303 |
+
"learning_rate": 0.0001,
|
| 304 |
+
"loss": 0.555,
|
| 305 |
+
"step": 2300
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 9.6,
|
| 309 |
+
"grad_norm": 1.9915804862976074,
|
| 310 |
+
"learning_rate": 0.0001,
|
| 311 |
+
"loss": 0.5102,
|
| 312 |
+
"step": 2400
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 10.0,
|
| 316 |
+
"grad_norm": 2.1287789344787598,
|
| 317 |
+
"learning_rate": 0.0001,
|
| 318 |
+
"loss": 0.5392,
|
| 319 |
+
"step": 2500
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 10.0,
|
| 323 |
+
"eval_accuracy": 0.4915555555555556,
|
| 324 |
+
"eval_loss": 3.537275791168213,
|
| 325 |
+
"eval_runtime": 5.1264,
|
| 326 |
+
"eval_samples_per_second": 97.534,
|
| 327 |
+
"eval_steps_per_second": 12.289,
|
| 328 |
+
"step": 2500
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 10.0,
|
| 332 |
+
"eval_exact_match": 15.4,
|
| 333 |
+
"eval_f1": 22.23013114336644,
|
| 334 |
+
"step": 2500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 10.4,
|
| 338 |
+
"grad_norm": 1.6748021841049194,
|
| 339 |
+
"learning_rate": 0.0001,
|
| 340 |
+
"loss": 0.4426,
|
| 341 |
+
"step": 2600
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 10.8,
|
| 345 |
+
"grad_norm": 1.8744910955429077,
|
| 346 |
+
"learning_rate": 0.0001,
|
| 347 |
+
"loss": 0.4718,
|
| 348 |
+
"step": 2700
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 11.0,
|
| 352 |
+
"eval_accuracy": 0.48926984126984124,
|
| 353 |
+
"eval_loss": 3.631282091140747,
|
| 354 |
+
"eval_runtime": 5.3142,
|
| 355 |
+
"eval_samples_per_second": 94.087,
|
| 356 |
+
"eval_steps_per_second": 11.855,
|
| 357 |
+
"step": 2750
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 11.0,
|
| 361 |
+
"eval_exact_match": 15.6,
|
| 362 |
+
"eval_f1": 21.87386002886003,
|
| 363 |
+
"step": 2750
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 11.2,
|
| 367 |
+
"grad_norm": 2.1398115158081055,
|
| 368 |
+
"learning_rate": 0.0001,
|
| 369 |
+
"loss": 0.4456,
|
| 370 |
+
"step": 2800
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 11.6,
|
| 374 |
+
"grad_norm": 1.8851490020751953,
|
| 375 |
+
"learning_rate": 0.0001,
|
| 376 |
+
"loss": 0.4328,
|
| 377 |
+
"step": 2900
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 12.0,
|
| 381 |
+
"grad_norm": 1.6958885192871094,
|
| 382 |
+
"learning_rate": 0.0001,
|
| 383 |
+
"loss": 0.4446,
|
| 384 |
+
"step": 3000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 12.0,
|
| 388 |
+
"eval_accuracy": 0.49057142857142855,
|
| 389 |
+
"eval_loss": 3.6736366748809814,
|
| 390 |
+
"eval_runtime": 5.8652,
|
| 391 |
+
"eval_samples_per_second": 85.248,
|
| 392 |
+
"eval_steps_per_second": 10.741,
|
| 393 |
+
"step": 3000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 12.0,
|
| 397 |
+
"eval_exact_match": 15.2,
|
| 398 |
+
"eval_f1": 21.81304966962862,
|
| 399 |
+
"step": 3000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 12.4,
|
| 403 |
+
"grad_norm": 1.8530863523483276,
|
| 404 |
+
"learning_rate": 0.0001,
|
| 405 |
+
"loss": 0.3969,
|
| 406 |
+
"step": 3100
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 12.8,
|
| 410 |
+
"grad_norm": 1.9440696239471436,
|
| 411 |
+
"learning_rate": 0.0001,
|
| 412 |
+
"loss": 0.4204,
|
| 413 |
+
"step": 3200
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 13.0,
|
| 417 |
+
"eval_accuracy": 0.4906031746031746,
|
| 418 |
+
"eval_loss": 3.7342090606689453,
|
| 419 |
+
"eval_runtime": 5.4947,
|
| 420 |
+
"eval_samples_per_second": 90.996,
|
| 421 |
+
"eval_steps_per_second": 11.466,
|
| 422 |
+
"step": 3250
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 13.0,
|
| 426 |
+
"eval_exact_match": 15.8,
|
| 427 |
+
"eval_f1": 21.908780663780668,
|
| 428 |
+
"step": 3250
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 13.2,
|
| 432 |
+
"grad_norm": 1.7972825765609741,
|
| 433 |
+
"learning_rate": 0.0001,
|
| 434 |
+
"loss": 0.4036,
|
| 435 |
+
"step": 3300
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 13.6,
|
| 439 |
+
"grad_norm": 1.6307235956192017,
|
| 440 |
+
"learning_rate": 0.0001,
|
| 441 |
+
"loss": 0.3929,
|
| 442 |
+
"step": 3400
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 14.0,
|
| 446 |
+
"grad_norm": 2.7257182598114014,
|
| 447 |
+
"learning_rate": 0.0001,
|
| 448 |
+
"loss": 0.4131,
|
| 449 |
+
"step": 3500
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 14.0,
|
| 453 |
+
"eval_accuracy": 0.4897142857142857,
|
| 454 |
+
"eval_loss": 3.7777669429779053,
|
| 455 |
+
"eval_runtime": 5.8394,
|
| 456 |
+
"eval_samples_per_second": 85.626,
|
| 457 |
+
"eval_steps_per_second": 10.789,
|
| 458 |
+
"step": 3500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 14.0,
|
| 462 |
+
"eval_exact_match": 15.0,
|
| 463 |
+
"eval_f1": 21.873367129946075,
|
| 464 |
+
"step": 3500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 14.4,
|
| 468 |
+
"grad_norm": 1.1628468036651611,
|
| 469 |
+
"learning_rate": 0.0001,
|
| 470 |
+
"loss": 0.3756,
|
| 471 |
+
"step": 3600
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 14.8,
|
| 475 |
+
"grad_norm": 2.109792470932007,
|
| 476 |
+
"learning_rate": 0.0001,
|
| 477 |
+
"loss": 0.3924,
|
| 478 |
+
"step": 3700
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 15.0,
|
| 482 |
+
"eval_accuracy": 0.48965079365079367,
|
| 483 |
+
"eval_loss": 3.820950746536255,
|
| 484 |
+
"eval_runtime": 5.3214,
|
| 485 |
+
"eval_samples_per_second": 93.96,
|
| 486 |
+
"eval_steps_per_second": 11.839,
|
| 487 |
+
"step": 3750
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 15.0,
|
| 491 |
+
"eval_exact_match": 14.6,
|
| 492 |
+
"eval_f1": 22.25867243867245,
|
| 493 |
+
"step": 3750
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 15.2,
|
| 497 |
+
"grad_norm": 1.2581037282943726,
|
| 498 |
+
"learning_rate": 0.0001,
|
| 499 |
+
"loss": 0.3792,
|
| 500 |
+
"step": 3800
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 15.6,
|
| 504 |
+
"grad_norm": 1.0244629383087158,
|
| 505 |
+
"learning_rate": 0.0001,
|
| 506 |
+
"loss": 0.3767,
|
| 507 |
+
"step": 3900
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 16.0,
|
| 511 |
+
"grad_norm": 1.3548619747161865,
|
| 512 |
+
"learning_rate": 0.0001,
|
| 513 |
+
"loss": 0.3913,
|
| 514 |
+
"step": 4000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 16.0,
|
| 518 |
+
"eval_accuracy": 0.49038095238095236,
|
| 519 |
+
"eval_loss": 3.8832576274871826,
|
| 520 |
+
"eval_runtime": 5.4233,
|
| 521 |
+
"eval_samples_per_second": 92.195,
|
| 522 |
+
"eval_steps_per_second": 11.617,
|
| 523 |
+
"step": 4000
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 16.0,
|
| 527 |
+
"eval_exact_match": 15.0,
|
| 528 |
+
"eval_f1": 21.823196411431713,
|
| 529 |
+
"step": 4000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 16.4,
|
| 533 |
+
"grad_norm": 1.5730881690979004,
|
| 534 |
+
"learning_rate": 0.0001,
|
| 535 |
+
"loss": 0.3606,
|
| 536 |
+
"step": 4100
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 16.8,
|
| 540 |
+
"grad_norm": 1.619290828704834,
|
| 541 |
+
"learning_rate": 0.0001,
|
| 542 |
+
"loss": 0.376,
|
| 543 |
+
"step": 4200
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 17.0,
|
| 547 |
+
"eval_accuracy": 0.4898095238095238,
|
| 548 |
+
"eval_loss": 3.8935556411743164,
|
| 549 |
+
"eval_runtime": 5.3789,
|
| 550 |
+
"eval_samples_per_second": 92.957,
|
| 551 |
+
"eval_steps_per_second": 11.713,
|
| 552 |
+
"step": 4250
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 17.0,
|
| 556 |
+
"eval_exact_match": 15.2,
|
| 557 |
+
"eval_f1": 21.284107517869135,
|
| 558 |
+
"step": 4250
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 17.2,
|
| 562 |
+
"grad_norm": 2.23779559135437,
|
| 563 |
+
"learning_rate": 0.0001,
|
| 564 |
+
"loss": 0.3697,
|
| 565 |
+
"step": 4300
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 17.6,
|
| 569 |
+
"grad_norm": 1.2932429313659668,
|
| 570 |
+
"learning_rate": 0.0001,
|
| 571 |
+
"loss": 0.3618,
|
| 572 |
+
"step": 4400
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 18.0,
|
| 576 |
+
"grad_norm": 1.6087582111358643,
|
| 577 |
+
"learning_rate": 0.0001,
|
| 578 |
+
"loss": 0.3785,
|
| 579 |
+
"step": 4500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 18.0,
|
| 583 |
+
"eval_accuracy": 0.49,
|
| 584 |
+
"eval_loss": 3.882444381713867,
|
| 585 |
+
"eval_runtime": 5.3456,
|
| 586 |
+
"eval_samples_per_second": 93.536,
|
| 587 |
+
"eval_steps_per_second": 11.785,
|
| 588 |
+
"step": 4500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 18.0,
|
| 592 |
+
"eval_exact_match": 15.4,
|
| 593 |
+
"eval_f1": 21.950805305805307,
|
| 594 |
+
"step": 4500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 18.4,
|
| 598 |
+
"grad_norm": 1.20901620388031,
|
| 599 |
+
"learning_rate": 0.0001,
|
| 600 |
+
"loss": 0.3532,
|
| 601 |
+
"step": 4600
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 18.8,
|
| 605 |
+
"grad_norm": 1.3064277172088623,
|
| 606 |
+
"learning_rate": 0.0001,
|
| 607 |
+
"loss": 0.367,
|
| 608 |
+
"step": 4700
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 19.0,
|
| 612 |
+
"eval_accuracy": 0.4900952380952381,
|
| 613 |
+
"eval_loss": 3.972047805786133,
|
| 614 |
+
"eval_runtime": 5.1196,
|
| 615 |
+
"eval_samples_per_second": 97.664,
|
| 616 |
+
"eval_steps_per_second": 12.306,
|
| 617 |
+
"step": 4750
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 19.0,
|
| 621 |
+
"eval_exact_match": 16.4,
|
| 622 |
+
"eval_f1": 23.046717171717184,
|
| 623 |
+
"step": 4750
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 19.2,
|
| 627 |
+
"grad_norm": 1.4567475318908691,
|
| 628 |
+
"learning_rate": 0.0001,
|
| 629 |
+
"loss": 0.3578,
|
| 630 |
+
"step": 4800
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 19.6,
|
| 634 |
+
"grad_norm": 1.274679183959961,
|
| 635 |
+
"learning_rate": 0.0001,
|
| 636 |
+
"loss": 0.3588,
|
| 637 |
+
"step": 4900
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 20.0,
|
| 641 |
+
"grad_norm": 1.5081045627593994,
|
| 642 |
+
"learning_rate": 0.0001,
|
| 643 |
+
"loss": 0.3676,
|
| 644 |
+
"step": 5000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 20.0,
|
| 648 |
+
"eval_accuracy": 0.4908888888888889,
|
| 649 |
+
"eval_loss": 3.937361717224121,
|
| 650 |
+
"eval_runtime": 5.3304,
|
| 651 |
+
"eval_samples_per_second": 93.801,
|
| 652 |
+
"eval_steps_per_second": 11.819,
|
| 653 |
+
"step": 5000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 20.0,
|
| 657 |
+
"eval_exact_match": 16.2,
|
| 658 |
+
"eval_f1": 22.572724497724508,
|
| 659 |
+
"step": 5000
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 20.4,
|
| 663 |
+
"grad_norm": 1.343906044960022,
|
| 664 |
+
"learning_rate": 0.0001,
|
| 665 |
+
"loss": 0.3445,
|
| 666 |
+
"step": 5100
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 20.8,
|
| 670 |
+
"grad_norm": 1.7303237915039062,
|
| 671 |
+
"learning_rate": 0.0001,
|
| 672 |
+
"loss": 0.3602,
|
| 673 |
+
"step": 5200
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 21.0,
|
| 677 |
+
"eval_accuracy": 0.49044444444444446,
|
| 678 |
+
"eval_loss": 3.9380335807800293,
|
| 679 |
+
"eval_runtime": 5.2455,
|
| 680 |
+
"eval_samples_per_second": 95.32,
|
| 681 |
+
"eval_steps_per_second": 12.01,
|
| 682 |
+
"step": 5250
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 21.0,
|
| 686 |
+
"eval_exact_match": 16.4,
|
| 687 |
+
"eval_f1": 23.159069264069274,
|
| 688 |
+
"step": 5250
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 21.2,
|
| 692 |
+
"grad_norm": 1.4770017862319946,
|
| 693 |
+
"learning_rate": 0.0001,
|
| 694 |
+
"loss": 0.3518,
|
| 695 |
+
"step": 5300
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 21.6,
|
| 699 |
+
"grad_norm": 0.7377692461013794,
|
| 700 |
+
"learning_rate": 0.0001,
|
| 701 |
+
"loss": 0.3498,
|
| 702 |
+
"step": 5400
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 22.0,
|
| 706 |
+
"grad_norm": 0.7583816051483154,
|
| 707 |
+
"learning_rate": 0.0001,
|
| 708 |
+
"loss": 0.3639,
|
| 709 |
+
"step": 5500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 22.0,
|
| 713 |
+
"eval_accuracy": 0.49098412698412697,
|
| 714 |
+
"eval_loss": 3.951629400253296,
|
| 715 |
+
"eval_runtime": 5.1413,
|
| 716 |
+
"eval_samples_per_second": 97.251,
|
| 717 |
+
"eval_steps_per_second": 12.254,
|
| 718 |
+
"step": 5500
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 22.0,
|
| 722 |
+
"eval_exact_match": 16.2,
|
| 723 |
+
"eval_f1": 22.613965478965486,
|
| 724 |
+
"step": 5500
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 22.4,
|
| 728 |
+
"grad_norm": 2.125830888748169,
|
| 729 |
+
"learning_rate": 0.0001,
|
| 730 |
+
"loss": 0.3386,
|
| 731 |
+
"step": 5600
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 22.8,
|
| 735 |
+
"grad_norm": 0.958363950252533,
|
| 736 |
+
"learning_rate": 0.0001,
|
| 737 |
+
"loss": 0.3533,
|
| 738 |
+
"step": 5700
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 23.0,
|
| 742 |
+
"eval_accuracy": 0.4915555555555556,
|
| 743 |
+
"eval_loss": 4.020674228668213,
|
| 744 |
+
"eval_runtime": 5.154,
|
| 745 |
+
"eval_samples_per_second": 97.011,
|
| 746 |
+
"eval_steps_per_second": 12.223,
|
| 747 |
+
"step": 5750
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 23.0,
|
| 751 |
+
"eval_exact_match": 16.6,
|
| 752 |
+
"eval_f1": 21.791541236541246,
|
| 753 |
+
"step": 5750
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 23.2,
|
| 757 |
+
"grad_norm": 1.526780605316162,
|
| 758 |
+
"learning_rate": 0.0001,
|
| 759 |
+
"loss": 0.3437,
|
| 760 |
+
"step": 5800
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 23.6,
|
| 764 |
+
"grad_norm": 1.0150421857833862,
|
| 765 |
+
"learning_rate": 0.0001,
|
| 766 |
+
"loss": 0.341,
|
| 767 |
+
"step": 5900
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 24.0,
|
| 771 |
+
"grad_norm": 0.9590368866920471,
|
| 772 |
+
"learning_rate": 0.0001,
|
| 773 |
+
"loss": 0.3587,
|
| 774 |
+
"step": 6000
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 24.0,
|
| 778 |
+
"eval_accuracy": 0.49165079365079367,
|
| 779 |
+
"eval_loss": 3.990480661392212,
|
| 780 |
+
"eval_runtime": 5.2849,
|
| 781 |
+
"eval_samples_per_second": 94.608,
|
| 782 |
+
"eval_steps_per_second": 11.921,
|
| 783 |
+
"step": 6000
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 24.0,
|
| 787 |
+
"eval_exact_match": 14.8,
|
| 788 |
+
"eval_f1": 20.68870512528408,
|
| 789 |
+
"step": 6000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 24.4,
|
| 793 |
+
"grad_norm": 0.7218676209449768,
|
| 794 |
+
"learning_rate": 0.0001,
|
| 795 |
+
"loss": 0.3355,
|
| 796 |
+
"step": 6100
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 24.8,
|
| 800 |
+
"grad_norm": 1.0547350645065308,
|
| 801 |
+
"learning_rate": 0.0001,
|
| 802 |
+
"loss": 0.3479,
|
| 803 |
+
"step": 6200
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 25.0,
|
| 807 |
+
"eval_accuracy": 0.4914920634920635,
|
| 808 |
+
"eval_loss": 4.061710357666016,
|
| 809 |
+
"eval_runtime": 5.1785,
|
| 810 |
+
"eval_samples_per_second": 96.553,
|
| 811 |
+
"eval_steps_per_second": 12.166,
|
| 812 |
+
"step": 6250
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 25.0,
|
| 816 |
+
"eval_exact_match": 15.2,
|
| 817 |
+
"eval_f1": 21.924090149616465,
|
| 818 |
+
"step": 6250
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 25.2,
|
| 822 |
+
"grad_norm": 0.8290365934371948,
|
| 823 |
+
"learning_rate": 0.0001,
|
| 824 |
+
"loss": 0.339,
|
| 825 |
+
"step": 6300
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 25.6,
|
| 829 |
+
"grad_norm": 1.2108442783355713,
|
| 830 |
+
"learning_rate": 0.0001,
|
| 831 |
+
"loss": 0.3409,
|
| 832 |
+
"step": 6400
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 26.0,
|
| 836 |
+
"grad_norm": 1.596282720565796,
|
| 837 |
+
"learning_rate": 0.0001,
|
| 838 |
+
"loss": 0.3511,
|
| 839 |
+
"step": 6500
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 26.0,
|
| 843 |
+
"eval_accuracy": 0.4903174603174603,
|
| 844 |
+
"eval_loss": 4.0105509757995605,
|
| 845 |
+
"eval_runtime": 5.1332,
|
| 846 |
+
"eval_samples_per_second": 97.405,
|
| 847 |
+
"eval_steps_per_second": 12.273,
|
| 848 |
+
"step": 6500
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 26.0,
|
| 852 |
+
"eval_exact_match": 15.2,
|
| 853 |
+
"eval_f1": 22.125512265512278,
|
| 854 |
+
"step": 6500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 26.4,
|
| 858 |
+
"grad_norm": 0.607507050037384,
|
| 859 |
+
"learning_rate": 0.0001,
|
| 860 |
+
"loss": 0.3289,
|
| 861 |
+
"step": 6600
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 26.8,
|
| 865 |
+
"grad_norm": 0.8661500215530396,
|
| 866 |
+
"learning_rate": 0.0001,
|
| 867 |
+
"loss": 0.3442,
|
| 868 |
+
"step": 6700
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 27.0,
|
| 872 |
+
"eval_accuracy": 0.491015873015873,
|
| 873 |
+
"eval_loss": 4.040103435516357,
|
| 874 |
+
"eval_runtime": 5.3436,
|
| 875 |
+
"eval_samples_per_second": 93.57,
|
| 876 |
+
"eval_steps_per_second": 11.79,
|
| 877 |
+
"step": 6750
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 27.0,
|
| 881 |
+
"eval_exact_match": 15.8,
|
| 882 |
+
"eval_f1": 23.22610556110557,
|
| 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:c3414153f69372b550d629c900d05ab7510b14d218f2d8546142e7b41d948d3e
|
| 3 |
+
size 5304
|
checkpoint-6750/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|