Training in progress, epoch 18, checkpoint
Browse files- checkpoint-3562/README.md +9 -0
- checkpoint-3562/adapter_config.json +25 -0
- checkpoint-3562/adapter_model.safetensors +3 -0
- checkpoint-3562/added_tokens.json +5 -0
- checkpoint-3562/merges.txt +0 -0
- checkpoint-3562/optimizer.pt +3 -0
- checkpoint-3562/rng_state_0.pth +3 -0
- checkpoint-3562/rng_state_1.pth +3 -0
- checkpoint-3562/rng_state_2.pth +3 -0
- checkpoint-3562/rng_state_3.pth +3 -0
- checkpoint-3562/scheduler.pt +3 -0
- checkpoint-3562/special_tokens_map.json +14 -0
- checkpoint-3562/tokenizer.json +0 -0
- checkpoint-3562/tokenizer_config.json +43 -0
- checkpoint-3562/trainer_state.json +563 -0
- checkpoint-3562/training_args.bin +3 -0
- checkpoint-3562/vocab.json +0 -0
checkpoint-3562/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-3562/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-3562/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a96d6159f23467485ac613cb8006044fa85f51c91b0efde9cfd4415a8e9934aa
|
| 3 |
+
size 112130416
|
checkpoint-3562/added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
checkpoint-3562/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3562/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0299157b743b6bb9558bde9bee5df48cb0b2fa67c8e56dae22fc7ef1f3ce2018
|
| 3 |
+
size 224537202
|
checkpoint-3562/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72ad5dfb8bb726aa4231bd77a38b23d6f2fe6df968b245a46ae6f0a5becd6c1f
|
| 3 |
+
size 15024
|
checkpoint-3562/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5a06b55aba9654970fc0b75b17b39273dd130375498ffa1a022d0afe6d71902
|
| 3 |
+
size 15024
|
checkpoint-3562/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5757d1c1df8032c5312cc9664205b3becf9aacbe54e35f18f3ce670caed95eb3
|
| 3 |
+
size 15024
|
checkpoint-3562/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5bc6711a906886b319f58450ec41b0ec51abd65b10fff72d64cd9196000964d
|
| 3 |
+
size 15024
|
checkpoint-3562/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab845d352df1a96735f1c60b54f781c954e01aba8a2f84ba7b7197eee150826b
|
| 3 |
+
size 1064
|
checkpoint-3562/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-3562/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3562/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-3562/trainer_state.json
ADDED
|
@@ -0,0 +1,563 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 18.997333333333334,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3562,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.5333333333333333,
|
| 13 |
+
"grad_norm": 0.5194531679153442,
|
| 14 |
+
"learning_rate": 0.0003,
|
| 15 |
+
"loss": 1.7259,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.9973333333333333,
|
| 20 |
+
"eval_accuracy": 0.5753333333333334,
|
| 21 |
+
"eval_loss": 1.6105104684829712,
|
| 22 |
+
"eval_runtime": 5.418,
|
| 23 |
+
"eval_samples_per_second": 92.285,
|
| 24 |
+
"eval_steps_per_second": 11.628,
|
| 25 |
+
"step": 187
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.9973333333333333,
|
| 29 |
+
"eval_exact_match": 17.2,
|
| 30 |
+
"eval_f1": 26.890173160173163,
|
| 31 |
+
"step": 187
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.0666666666666667,
|
| 35 |
+
"grad_norm": 0.6734262704849243,
|
| 36 |
+
"learning_rate": 0.0003,
|
| 37 |
+
"loss": 1.6156,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.6,
|
| 42 |
+
"grad_norm": 0.7422465682029724,
|
| 43 |
+
"learning_rate": 0.0003,
|
| 44 |
+
"loss": 1.3358,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.0,
|
| 49 |
+
"eval_accuracy": 0.5722564102564103,
|
| 50 |
+
"eval_loss": 1.6464648246765137,
|
| 51 |
+
"eval_runtime": 5.1856,
|
| 52 |
+
"eval_samples_per_second": 96.422,
|
| 53 |
+
"eval_steps_per_second": 12.149,
|
| 54 |
+
"step": 375
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 2.0,
|
| 58 |
+
"eval_exact_match": 19.0,
|
| 59 |
+
"eval_f1": 27.762380952380955,
|
| 60 |
+
"step": 375
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 2.1333333333333333,
|
| 64 |
+
"grad_norm": 0.828364908695221,
|
| 65 |
+
"learning_rate": 0.0003,
|
| 66 |
+
"loss": 1.2607,
|
| 67 |
+
"step": 400
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 2.6666666666666665,
|
| 71 |
+
"grad_norm": 0.9025559425354004,
|
| 72 |
+
"learning_rate": 0.0003,
|
| 73 |
+
"loss": 0.9854,
|
| 74 |
+
"step": 500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.997333333333333,
|
| 78 |
+
"eval_accuracy": 0.5707692307692308,
|
| 79 |
+
"eval_loss": 1.7620763778686523,
|
| 80 |
+
"eval_runtime": 5.2589,
|
| 81 |
+
"eval_samples_per_second": 95.077,
|
| 82 |
+
"eval_steps_per_second": 11.98,
|
| 83 |
+
"step": 562
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 2.997333333333333,
|
| 87 |
+
"eval_exact_match": 18.2,
|
| 88 |
+
"eval_f1": 27.53142857142857,
|
| 89 |
+
"step": 562
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 3.2,
|
| 93 |
+
"grad_norm": 0.8217537999153137,
|
| 94 |
+
"learning_rate": 0.0003,
|
| 95 |
+
"loss": 0.9099,
|
| 96 |
+
"step": 600
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 3.7333333333333334,
|
| 100 |
+
"grad_norm": 0.8315110206604004,
|
| 101 |
+
"learning_rate": 0.0003,
|
| 102 |
+
"loss": 0.7508,
|
| 103 |
+
"step": 700
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 4.0,
|
| 107 |
+
"eval_accuracy": 0.5663076923076923,
|
| 108 |
+
"eval_loss": 1.9380683898925781,
|
| 109 |
+
"eval_runtime": 5.3338,
|
| 110 |
+
"eval_samples_per_second": 93.742,
|
| 111 |
+
"eval_steps_per_second": 11.811,
|
| 112 |
+
"step": 750
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 4.0,
|
| 116 |
+
"eval_exact_match": 16.0,
|
| 117 |
+
"eval_f1": 24.611904761904768,
|
| 118 |
+
"step": 750
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 4.266666666666667,
|
| 122 |
+
"grad_norm": 0.6763857007026672,
|
| 123 |
+
"learning_rate": 0.0003,
|
| 124 |
+
"loss": 0.6912,
|
| 125 |
+
"step": 800
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 4.8,
|
| 129 |
+
"grad_norm": 0.8408166766166687,
|
| 130 |
+
"learning_rate": 0.0003,
|
| 131 |
+
"loss": 0.6396,
|
| 132 |
+
"step": 900
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 4.997333333333334,
|
| 136 |
+
"eval_accuracy": 0.5634358974358974,
|
| 137 |
+
"eval_loss": 1.9925932884216309,
|
| 138 |
+
"eval_runtime": 5.3717,
|
| 139 |
+
"eval_samples_per_second": 93.08,
|
| 140 |
+
"eval_steps_per_second": 11.728,
|
| 141 |
+
"step": 937
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 4.997333333333334,
|
| 145 |
+
"eval_exact_match": 16.0,
|
| 146 |
+
"eval_f1": 24.313809523809528,
|
| 147 |
+
"step": 937
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 5.333333333333333,
|
| 151 |
+
"grad_norm": 0.6721271276473999,
|
| 152 |
+
"learning_rate": 0.0003,
|
| 153 |
+
"loss": 0.5959,
|
| 154 |
+
"step": 1000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 5.866666666666667,
|
| 158 |
+
"grad_norm": 0.9258321523666382,
|
| 159 |
+
"learning_rate": 0.0003,
|
| 160 |
+
"loss": 0.5833,
|
| 161 |
+
"step": 1100
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 6.0,
|
| 165 |
+
"eval_accuracy": 0.5611794871794872,
|
| 166 |
+
"eval_loss": 2.101524829864502,
|
| 167 |
+
"eval_runtime": 5.4208,
|
| 168 |
+
"eval_samples_per_second": 92.238,
|
| 169 |
+
"eval_steps_per_second": 11.622,
|
| 170 |
+
"step": 1125
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 6.0,
|
| 174 |
+
"eval_exact_match": 17.0,
|
| 175 |
+
"eval_f1": 25.444285714285726,
|
| 176 |
+
"step": 1125
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 6.4,
|
| 180 |
+
"grad_norm": 0.6029295921325684,
|
| 181 |
+
"learning_rate": 0.0003,
|
| 182 |
+
"loss": 0.545,
|
| 183 |
+
"step": 1200
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 6.933333333333334,
|
| 187 |
+
"grad_norm": 0.5719736814498901,
|
| 188 |
+
"learning_rate": 0.0003,
|
| 189 |
+
"loss": 0.5567,
|
| 190 |
+
"step": 1300
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 6.997333333333334,
|
| 194 |
+
"eval_accuracy": 0.5607179487179487,
|
| 195 |
+
"eval_loss": 2.1645195484161377,
|
| 196 |
+
"eval_runtime": 5.1974,
|
| 197 |
+
"eval_samples_per_second": 96.202,
|
| 198 |
+
"eval_steps_per_second": 12.121,
|
| 199 |
+
"step": 1312
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 6.997333333333334,
|
| 203 |
+
"eval_exact_match": 15.0,
|
| 204 |
+
"eval_f1": 23.618095238095247,
|
| 205 |
+
"step": 1312
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 7.466666666666667,
|
| 209 |
+
"grad_norm": 0.49924588203430176,
|
| 210 |
+
"learning_rate": 0.0003,
|
| 211 |
+
"loss": 0.5205,
|
| 212 |
+
"step": 1400
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 8.0,
|
| 216 |
+
"grad_norm": 0.5360875129699707,
|
| 217 |
+
"learning_rate": 0.0003,
|
| 218 |
+
"loss": 0.5411,
|
| 219 |
+
"step": 1500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 8.0,
|
| 223 |
+
"eval_accuracy": 0.5614358974358974,
|
| 224 |
+
"eval_loss": 2.2039756774902344,
|
| 225 |
+
"eval_runtime": 5.0936,
|
| 226 |
+
"eval_samples_per_second": 98.162,
|
| 227 |
+
"eval_steps_per_second": 12.368,
|
| 228 |
+
"step": 1500
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 8.0,
|
| 232 |
+
"eval_exact_match": 16.8,
|
| 233 |
+
"eval_f1": 25.132380952380966,
|
| 234 |
+
"step": 1500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 8.533333333333333,
|
| 238 |
+
"grad_norm": 0.44560280442237854,
|
| 239 |
+
"learning_rate": 0.0003,
|
| 240 |
+
"loss": 0.5028,
|
| 241 |
+
"step": 1600
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 8.997333333333334,
|
| 245 |
+
"eval_accuracy": 0.5608205128205128,
|
| 246 |
+
"eval_loss": 2.236473321914673,
|
| 247 |
+
"eval_runtime": 5.2122,
|
| 248 |
+
"eval_samples_per_second": 95.93,
|
| 249 |
+
"eval_steps_per_second": 12.087,
|
| 250 |
+
"step": 1687
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 8.997333333333334,
|
| 254 |
+
"eval_exact_match": 16.0,
|
| 255 |
+
"eval_f1": 24.712380952380958,
|
| 256 |
+
"step": 1687
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 9.066666666666666,
|
| 260 |
+
"grad_norm": 0.42847225069999695,
|
| 261 |
+
"learning_rate": 0.0003,
|
| 262 |
+
"loss": 0.5246,
|
| 263 |
+
"step": 1700
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 9.6,
|
| 267 |
+
"grad_norm": 0.4186452627182007,
|
| 268 |
+
"learning_rate": 0.0003,
|
| 269 |
+
"loss": 0.5041,
|
| 270 |
+
"step": 1800
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 10.0,
|
| 274 |
+
"eval_accuracy": 0.5604615384615385,
|
| 275 |
+
"eval_loss": 2.2862467765808105,
|
| 276 |
+
"eval_runtime": 5.8141,
|
| 277 |
+
"eval_samples_per_second": 85.998,
|
| 278 |
+
"eval_steps_per_second": 10.836,
|
| 279 |
+
"step": 1875
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 10.0,
|
| 283 |
+
"eval_exact_match": 14.4,
|
| 284 |
+
"eval_f1": 22.683333333333344,
|
| 285 |
+
"step": 1875
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 10.133333333333333,
|
| 289 |
+
"grad_norm": 0.427721232175827,
|
| 290 |
+
"learning_rate": 0.0003,
|
| 291 |
+
"loss": 0.5083,
|
| 292 |
+
"step": 1900
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 10.666666666666666,
|
| 296 |
+
"grad_norm": 0.4298701584339142,
|
| 297 |
+
"learning_rate": 0.0003,
|
| 298 |
+
"loss": 0.4991,
|
| 299 |
+
"step": 2000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 10.997333333333334,
|
| 303 |
+
"eval_accuracy": 0.5602564102564103,
|
| 304 |
+
"eval_loss": 2.285149574279785,
|
| 305 |
+
"eval_runtime": 5.1591,
|
| 306 |
+
"eval_samples_per_second": 96.916,
|
| 307 |
+
"eval_steps_per_second": 12.211,
|
| 308 |
+
"step": 2062
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 10.997333333333334,
|
| 312 |
+
"eval_exact_match": 14.4,
|
| 313 |
+
"eval_f1": 22.41619047619048,
|
| 314 |
+
"step": 2062
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 11.2,
|
| 318 |
+
"grad_norm": 0.40195176005363464,
|
| 319 |
+
"learning_rate": 0.0003,
|
| 320 |
+
"loss": 0.5053,
|
| 321 |
+
"step": 2100
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 11.733333333333333,
|
| 325 |
+
"grad_norm": 0.6030442118644714,
|
| 326 |
+
"learning_rate": 0.0003,
|
| 327 |
+
"loss": 0.5048,
|
| 328 |
+
"step": 2200
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 12.0,
|
| 332 |
+
"eval_accuracy": 0.560974358974359,
|
| 333 |
+
"eval_loss": 2.2454702854156494,
|
| 334 |
+
"eval_runtime": 5.1149,
|
| 335 |
+
"eval_samples_per_second": 97.753,
|
| 336 |
+
"eval_steps_per_second": 12.317,
|
| 337 |
+
"step": 2250
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 12.0,
|
| 341 |
+
"eval_exact_match": 16.2,
|
| 342 |
+
"eval_f1": 24.622857142857157,
|
| 343 |
+
"step": 2250
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 12.266666666666667,
|
| 347 |
+
"grad_norm": 0.4596252143383026,
|
| 348 |
+
"learning_rate": 0.0003,
|
| 349 |
+
"loss": 0.4995,
|
| 350 |
+
"step": 2300
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 12.8,
|
| 354 |
+
"grad_norm": 0.4469389021396637,
|
| 355 |
+
"learning_rate": 0.0003,
|
| 356 |
+
"loss": 0.5067,
|
| 357 |
+
"step": 2400
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 12.997333333333334,
|
| 361 |
+
"eval_accuracy": 0.5591794871794872,
|
| 362 |
+
"eval_loss": 2.258878707885742,
|
| 363 |
+
"eval_runtime": 5.1623,
|
| 364 |
+
"eval_samples_per_second": 96.856,
|
| 365 |
+
"eval_steps_per_second": 12.204,
|
| 366 |
+
"step": 2437
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 12.997333333333334,
|
| 370 |
+
"eval_exact_match": 14.0,
|
| 371 |
+
"eval_f1": 22.422539682539693,
|
| 372 |
+
"step": 2437
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 13.333333333333334,
|
| 376 |
+
"grad_norm": 0.4875074028968811,
|
| 377 |
+
"learning_rate": 0.0003,
|
| 378 |
+
"loss": 0.4998,
|
| 379 |
+
"step": 2500
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 13.866666666666667,
|
| 383 |
+
"grad_norm": 0.5969555974006653,
|
| 384 |
+
"learning_rate": 0.0003,
|
| 385 |
+
"loss": 0.508,
|
| 386 |
+
"step": 2600
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 14.0,
|
| 390 |
+
"eval_accuracy": 0.5583589743589744,
|
| 391 |
+
"eval_loss": 2.2630844116210938,
|
| 392 |
+
"eval_runtime": 5.2013,
|
| 393 |
+
"eval_samples_per_second": 96.129,
|
| 394 |
+
"eval_steps_per_second": 12.112,
|
| 395 |
+
"step": 2625
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 14.0,
|
| 399 |
+
"eval_exact_match": 15.0,
|
| 400 |
+
"eval_f1": 22.224285714285717,
|
| 401 |
+
"step": 2625
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 14.4,
|
| 405 |
+
"grad_norm": 0.3906678259372711,
|
| 406 |
+
"learning_rate": 0.0003,
|
| 407 |
+
"loss": 0.5008,
|
| 408 |
+
"step": 2700
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 14.933333333333334,
|
| 412 |
+
"grad_norm": 0.6833591461181641,
|
| 413 |
+
"learning_rate": 0.0003,
|
| 414 |
+
"loss": 0.514,
|
| 415 |
+
"step": 2800
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 14.997333333333334,
|
| 419 |
+
"eval_accuracy": 0.5563589743589744,
|
| 420 |
+
"eval_loss": 2.277346134185791,
|
| 421 |
+
"eval_runtime": 5.1497,
|
| 422 |
+
"eval_samples_per_second": 97.094,
|
| 423 |
+
"eval_steps_per_second": 12.234,
|
| 424 |
+
"step": 2812
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 14.997333333333334,
|
| 428 |
+
"eval_exact_match": 14.2,
|
| 429 |
+
"eval_f1": 22.277792207792217,
|
| 430 |
+
"step": 2812
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 15.466666666666667,
|
| 434 |
+
"grad_norm": 0.6206196546554565,
|
| 435 |
+
"learning_rate": 0.0003,
|
| 436 |
+
"loss": 0.4902,
|
| 437 |
+
"step": 2900
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 16.0,
|
| 441 |
+
"grad_norm": 0.4821285903453827,
|
| 442 |
+
"learning_rate": 0.0003,
|
| 443 |
+
"loss": 0.5149,
|
| 444 |
+
"step": 3000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 16.0,
|
| 448 |
+
"eval_accuracy": 0.5576410256410257,
|
| 449 |
+
"eval_loss": 2.286123514175415,
|
| 450 |
+
"eval_runtime": 5.1003,
|
| 451 |
+
"eval_samples_per_second": 98.034,
|
| 452 |
+
"eval_steps_per_second": 12.352,
|
| 453 |
+
"step": 3000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 16.0,
|
| 457 |
+
"eval_exact_match": 15.8,
|
| 458 |
+
"eval_f1": 23.748730158730165,
|
| 459 |
+
"step": 3000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 16.533333333333335,
|
| 463 |
+
"grad_norm": 0.7102397084236145,
|
| 464 |
+
"learning_rate": 0.0003,
|
| 465 |
+
"loss": 0.4835,
|
| 466 |
+
"step": 3100
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 16.997333333333334,
|
| 470 |
+
"eval_accuracy": 0.5587692307692308,
|
| 471 |
+
"eval_loss": 2.2662925720214844,
|
| 472 |
+
"eval_runtime": 5.8917,
|
| 473 |
+
"eval_samples_per_second": 84.865,
|
| 474 |
+
"eval_steps_per_second": 10.693,
|
| 475 |
+
"step": 3187
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 16.997333333333334,
|
| 479 |
+
"eval_exact_match": 13.8,
|
| 480 |
+
"eval_f1": 22.173809523809535,
|
| 481 |
+
"step": 3187
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 17.066666666666666,
|
| 485 |
+
"grad_norm": 0.4603720009326935,
|
| 486 |
+
"learning_rate": 0.0003,
|
| 487 |
+
"loss": 0.5031,
|
| 488 |
+
"step": 3200
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 17.6,
|
| 492 |
+
"grad_norm": 0.45880746841430664,
|
| 493 |
+
"learning_rate": 0.0003,
|
| 494 |
+
"loss": 0.484,
|
| 495 |
+
"step": 3300
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 18.0,
|
| 499 |
+
"eval_accuracy": 0.5574871794871795,
|
| 500 |
+
"eval_loss": 2.31445050239563,
|
| 501 |
+
"eval_runtime": 5.3978,
|
| 502 |
+
"eval_samples_per_second": 92.63,
|
| 503 |
+
"eval_steps_per_second": 11.671,
|
| 504 |
+
"step": 3375
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 18.0,
|
| 508 |
+
"eval_exact_match": 15.0,
|
| 509 |
+
"eval_f1": 22.527301587301594,
|
| 510 |
+
"step": 3375
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 18.133333333333333,
|
| 514 |
+
"grad_norm": 0.4228228032588959,
|
| 515 |
+
"learning_rate": 0.0003,
|
| 516 |
+
"loss": 0.4953,
|
| 517 |
+
"step": 3400
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 18.666666666666668,
|
| 521 |
+
"grad_norm": 0.42700931429862976,
|
| 522 |
+
"learning_rate": 0.0003,
|
| 523 |
+
"loss": 0.4862,
|
| 524 |
+
"step": 3500
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 18.997333333333334,
|
| 528 |
+
"eval_accuracy": 0.5559487179487179,
|
| 529 |
+
"eval_loss": 2.2948524951934814,
|
| 530 |
+
"eval_runtime": 5.1396,
|
| 531 |
+
"eval_samples_per_second": 97.283,
|
| 532 |
+
"eval_steps_per_second": 12.258,
|
| 533 |
+
"step": 3562
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 18.997333333333334,
|
| 537 |
+
"eval_exact_match": 14.0,
|
| 538 |
+
"eval_f1": 21.949682539682552,
|
| 539 |
+
"step": 3562
|
| 540 |
+
}
|
| 541 |
+
],
|
| 542 |
+
"logging_steps": 100,
|
| 543 |
+
"max_steps": 9350,
|
| 544 |
+
"num_input_tokens_seen": 0,
|
| 545 |
+
"num_train_epochs": 50,
|
| 546 |
+
"save_steps": 500,
|
| 547 |
+
"stateful_callbacks": {
|
| 548 |
+
"TrainerControl": {
|
| 549 |
+
"args": {
|
| 550 |
+
"should_epoch_stop": false,
|
| 551 |
+
"should_evaluate": false,
|
| 552 |
+
"should_log": false,
|
| 553 |
+
"should_save": true,
|
| 554 |
+
"should_training_stop": false
|
| 555 |
+
},
|
| 556 |
+
"attributes": {}
|
| 557 |
+
}
|
| 558 |
+
},
|
| 559 |
+
"total_flos": 6.204378145252966e+16,
|
| 560 |
+
"train_batch_size": 1,
|
| 561 |
+
"trial_name": null,
|
| 562 |
+
"trial_params": null
|
| 563 |
+
}
|
checkpoint-3562/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a48aaa718d03f9c3a1cf4e80dbff36330a05dd346d42a3b722f1ae2626aabe3c
|
| 3 |
+
size 5304
|
checkpoint-3562/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|