Training in progress, epoch 22, checkpoint
Browse files- checkpoint-11638/README.md +9 -0
- checkpoint-11638/adapter_config.json +25 -0
- checkpoint-11638/adapter_model.safetensors +3 -0
- checkpoint-11638/added_tokens.json +5 -0
- checkpoint-11638/merges.txt +0 -0
- checkpoint-11638/optimizer.pt +3 -0
- checkpoint-11638/rng_state_0.pth +3 -0
- checkpoint-11638/rng_state_1.pth +3 -0
- checkpoint-11638/rng_state_2.pth +3 -0
- checkpoint-11638/rng_state_3.pth +3 -0
- checkpoint-11638/scheduler.pt +3 -0
- checkpoint-11638/special_tokens_map.json +14 -0
- checkpoint-11638/tokenizer.json +0 -0
- checkpoint-11638/tokenizer_config.json +43 -0
- checkpoint-11638/trainer_state.json +1175 -0
- checkpoint-11638/training_args.bin +3 -0
- checkpoint-11638/vocab.json +0 -0
checkpoint-11638/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-11638/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-11638/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d105b826ae44ed41e95c42815586784cb24578d05991cd02a2449261fbe957a0
|
| 3 |
+
size 112130416
|
checkpoint-11638/added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
checkpoint-11638/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-11638/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4bfbc86ca0dca4c496817a264a2812852d5043ec726dff544cfe51eb6797b31
|
| 3 |
+
size 224537202
|
checkpoint-11638/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b59f7691c16009795b6ae9b4bc57d0ee0f8972e51d642460a87acb2a4c7a05f
|
| 3 |
+
size 15024
|
checkpoint-11638/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09d50fbd750430cc89e797693745919b71c8bb58a44a0183d4c1c70b8ee812ca
|
| 3 |
+
size 15024
|
checkpoint-11638/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ab6271fc322625398da657f487f1faf5de2acbfabb25ed71af1e63b99613eba
|
| 3 |
+
size 15024
|
checkpoint-11638/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:312e4525a38bf2e83328e0d2b221dc6f2fb79ca8f38934576570553bbbcdbe35
|
| 3 |
+
size 15024
|
checkpoint-11638/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37812951c6a608f63bb5c0cf12d2b21ab4ff3dc143de2bd668d91247bb8aeda6
|
| 3 |
+
size 1064
|
checkpoint-11638/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-11638/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-11638/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-11638/trainer_state.json
ADDED
|
@@ -0,0 +1,1175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 22.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 11638,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1890359168241966,
|
| 13 |
+
"grad_norm": 0.5107442140579224,
|
| 14 |
+
"learning_rate": 5e-05,
|
| 15 |
+
"loss": 2.0482,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.3780718336483932,
|
| 20 |
+
"grad_norm": 0.5563424229621887,
|
| 21 |
+
"learning_rate": 5e-05,
|
| 22 |
+
"loss": 1.8835,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.5671077504725898,
|
| 27 |
+
"grad_norm": 0.4735371172428131,
|
| 28 |
+
"learning_rate": 5e-05,
|
| 29 |
+
"loss": 1.8512,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.7561436672967864,
|
| 34 |
+
"grad_norm": 0.4543495178222656,
|
| 35 |
+
"learning_rate": 5e-05,
|
| 36 |
+
"loss": 1.8489,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.945179584120983,
|
| 41 |
+
"grad_norm": 0.5007112622261047,
|
| 42 |
+
"learning_rate": 5e-05,
|
| 43 |
+
"loss": 1.8439,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.0,
|
| 48 |
+
"eval_accuracy": 0.5733333333333334,
|
| 49 |
+
"eval_loss": 1.6194567680358887,
|
| 50 |
+
"eval_runtime": 5.4154,
|
| 51 |
+
"eval_samples_per_second": 92.33,
|
| 52 |
+
"eval_steps_per_second": 11.634,
|
| 53 |
+
"step": 529
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.0,
|
| 57 |
+
"eval_exact_match": 17.0,
|
| 58 |
+
"eval_f1": 26.880952380952387,
|
| 59 |
+
"step": 529
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.1342155009451795,
|
| 63 |
+
"grad_norm": 0.5181360244750977,
|
| 64 |
+
"learning_rate": 5e-05,
|
| 65 |
+
"loss": 1.8217,
|
| 66 |
+
"step": 600
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.3232514177693762,
|
| 70 |
+
"grad_norm": 1.1348918676376343,
|
| 71 |
+
"learning_rate": 5e-05,
|
| 72 |
+
"loss": 1.7866,
|
| 73 |
+
"step": 700
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.5122873345935728,
|
| 77 |
+
"grad_norm": 0.661758303642273,
|
| 78 |
+
"learning_rate": 5e-05,
|
| 79 |
+
"loss": 1.7934,
|
| 80 |
+
"step": 800
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.7013232514177694,
|
| 84 |
+
"grad_norm": 0.5634772777557373,
|
| 85 |
+
"learning_rate": 5e-05,
|
| 86 |
+
"loss": 1.7731,
|
| 87 |
+
"step": 900
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.8903591682419658,
|
| 91 |
+
"grad_norm": 0.6698930263519287,
|
| 92 |
+
"learning_rate": 5e-05,
|
| 93 |
+
"loss": 1.7969,
|
| 94 |
+
"step": 1000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 2.0,
|
| 98 |
+
"eval_accuracy": 0.5751794871794872,
|
| 99 |
+
"eval_loss": 1.603736162185669,
|
| 100 |
+
"eval_runtime": 5.0986,
|
| 101 |
+
"eval_samples_per_second": 98.066,
|
| 102 |
+
"eval_steps_per_second": 12.356,
|
| 103 |
+
"step": 1058
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 2.0,
|
| 107 |
+
"eval_exact_match": 17.6,
|
| 108 |
+
"eval_f1": 27.218095238095238,
|
| 109 |
+
"step": 1058
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.0793950850661624,
|
| 113 |
+
"grad_norm": 0.6265193223953247,
|
| 114 |
+
"learning_rate": 5e-05,
|
| 115 |
+
"loss": 1.7416,
|
| 116 |
+
"step": 1100
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.268431001890359,
|
| 120 |
+
"grad_norm": 0.812364935874939,
|
| 121 |
+
"learning_rate": 5e-05,
|
| 122 |
+
"loss": 1.6957,
|
| 123 |
+
"step": 1200
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.4574669187145557,
|
| 127 |
+
"grad_norm": 1.0972926616668701,
|
| 128 |
+
"learning_rate": 5e-05,
|
| 129 |
+
"loss": 1.7033,
|
| 130 |
+
"step": 1300
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.6465028355387523,
|
| 134 |
+
"grad_norm": 1.0831658840179443,
|
| 135 |
+
"learning_rate": 5e-05,
|
| 136 |
+
"loss": 1.6935,
|
| 137 |
+
"step": 1400
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 2.835538752362949,
|
| 141 |
+
"grad_norm": 1.0022494792938232,
|
| 142 |
+
"learning_rate": 5e-05,
|
| 143 |
+
"loss": 1.6799,
|
| 144 |
+
"step": 1500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.0,
|
| 148 |
+
"eval_accuracy": 0.573025641025641,
|
| 149 |
+
"eval_loss": 1.6428505182266235,
|
| 150 |
+
"eval_runtime": 5.1488,
|
| 151 |
+
"eval_samples_per_second": 97.111,
|
| 152 |
+
"eval_steps_per_second": 12.236,
|
| 153 |
+
"step": 1587
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 3.0,
|
| 157 |
+
"eval_exact_match": 20.2,
|
| 158 |
+
"eval_f1": 27.93809523809523,
|
| 159 |
+
"step": 1587
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.0245746691871456,
|
| 163 |
+
"grad_norm": 0.8240587711334229,
|
| 164 |
+
"learning_rate": 5e-05,
|
| 165 |
+
"loss": 1.6618,
|
| 166 |
+
"step": 1600
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 3.213610586011342,
|
| 170 |
+
"grad_norm": 1.2994645833969116,
|
| 171 |
+
"learning_rate": 5e-05,
|
| 172 |
+
"loss": 1.5736,
|
| 173 |
+
"step": 1700
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.402646502835539,
|
| 177 |
+
"grad_norm": 1.0891159772872925,
|
| 178 |
+
"learning_rate": 5e-05,
|
| 179 |
+
"loss": 1.5798,
|
| 180 |
+
"step": 1800
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.5916824196597354,
|
| 184 |
+
"grad_norm": 1.3826475143432617,
|
| 185 |
+
"learning_rate": 5e-05,
|
| 186 |
+
"loss": 1.5957,
|
| 187 |
+
"step": 1900
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 3.780718336483932,
|
| 191 |
+
"grad_norm": 0.9901586174964905,
|
| 192 |
+
"learning_rate": 5e-05,
|
| 193 |
+
"loss": 1.6026,
|
| 194 |
+
"step": 2000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 3.9697542533081287,
|
| 198 |
+
"grad_norm": 1.0607813596725464,
|
| 199 |
+
"learning_rate": 5e-05,
|
| 200 |
+
"loss": 1.6106,
|
| 201 |
+
"step": 2100
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 4.0,
|
| 205 |
+
"eval_accuracy": 0.5708717948717948,
|
| 206 |
+
"eval_loss": 1.7143596410751343,
|
| 207 |
+
"eval_runtime": 5.3942,
|
| 208 |
+
"eval_samples_per_second": 92.693,
|
| 209 |
+
"eval_steps_per_second": 11.679,
|
| 210 |
+
"step": 2116
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 4.0,
|
| 214 |
+
"eval_exact_match": 19.0,
|
| 215 |
+
"eval_f1": 27.71428571428571,
|
| 216 |
+
"step": 2116
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 4.158790170132325,
|
| 220 |
+
"grad_norm": 1.3189178705215454,
|
| 221 |
+
"learning_rate": 5e-05,
|
| 222 |
+
"loss": 1.5029,
|
| 223 |
+
"step": 2200
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 4.3478260869565215,
|
| 227 |
+
"grad_norm": 1.062267541885376,
|
| 228 |
+
"learning_rate": 5e-05,
|
| 229 |
+
"loss": 1.51,
|
| 230 |
+
"step": 2300
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 4.536862003780718,
|
| 234 |
+
"grad_norm": 1.3810843229293823,
|
| 235 |
+
"learning_rate": 5e-05,
|
| 236 |
+
"loss": 1.4867,
|
| 237 |
+
"step": 2400
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 4.725897920604915,
|
| 241 |
+
"grad_norm": 1.1991653442382812,
|
| 242 |
+
"learning_rate": 5e-05,
|
| 243 |
+
"loss": 1.501,
|
| 244 |
+
"step": 2500
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 4.914933837429111,
|
| 248 |
+
"grad_norm": 1.310654878616333,
|
| 249 |
+
"learning_rate": 5e-05,
|
| 250 |
+
"loss": 1.5034,
|
| 251 |
+
"step": 2600
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 5.0,
|
| 255 |
+
"eval_accuracy": 0.5681025641025641,
|
| 256 |
+
"eval_loss": 1.8328346014022827,
|
| 257 |
+
"eval_runtime": 5.7763,
|
| 258 |
+
"eval_samples_per_second": 86.561,
|
| 259 |
+
"eval_steps_per_second": 10.907,
|
| 260 |
+
"step": 2645
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 5.0,
|
| 264 |
+
"eval_exact_match": 18.8,
|
| 265 |
+
"eval_f1": 26.6015873015873,
|
| 266 |
+
"step": 2645
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 5.103969754253308,
|
| 270 |
+
"grad_norm": 1.1406631469726562,
|
| 271 |
+
"learning_rate": 5e-05,
|
| 272 |
+
"loss": 1.4605,
|
| 273 |
+
"step": 2700
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 5.293005671077505,
|
| 277 |
+
"grad_norm": 1.447221279144287,
|
| 278 |
+
"learning_rate": 5e-05,
|
| 279 |
+
"loss": 1.4204,
|
| 280 |
+
"step": 2800
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 5.482041587901701,
|
| 284 |
+
"grad_norm": 1.461799144744873,
|
| 285 |
+
"learning_rate": 5e-05,
|
| 286 |
+
"loss": 1.4233,
|
| 287 |
+
"step": 2900
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 5.671077504725898,
|
| 291 |
+
"grad_norm": 1.4184092283248901,
|
| 292 |
+
"learning_rate": 5e-05,
|
| 293 |
+
"loss": 1.4265,
|
| 294 |
+
"step": 3000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 5.8601134215500945,
|
| 298 |
+
"grad_norm": 0.9850455522537231,
|
| 299 |
+
"learning_rate": 5e-05,
|
| 300 |
+
"loss": 1.4139,
|
| 301 |
+
"step": 3100
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 6.0,
|
| 305 |
+
"eval_accuracy": 0.564974358974359,
|
| 306 |
+
"eval_loss": 1.931396484375,
|
| 307 |
+
"eval_runtime": 5.3358,
|
| 308 |
+
"eval_samples_per_second": 93.706,
|
| 309 |
+
"eval_steps_per_second": 11.807,
|
| 310 |
+
"step": 3174
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 6.0,
|
| 314 |
+
"eval_exact_match": 17.6,
|
| 315 |
+
"eval_f1": 25.464285714285715,
|
| 316 |
+
"step": 3174
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 6.049149338374291,
|
| 320 |
+
"grad_norm": 1.2274116277694702,
|
| 321 |
+
"learning_rate": 5e-05,
|
| 322 |
+
"loss": 1.4159,
|
| 323 |
+
"step": 3200
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 6.238185255198488,
|
| 327 |
+
"grad_norm": 1.2107988595962524,
|
| 328 |
+
"learning_rate": 5e-05,
|
| 329 |
+
"loss": 1.3579,
|
| 330 |
+
"step": 3300
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 6.427221172022684,
|
| 334 |
+
"grad_norm": 1.2965952157974243,
|
| 335 |
+
"learning_rate": 5e-05,
|
| 336 |
+
"loss": 1.3485,
|
| 337 |
+
"step": 3400
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 6.616257088846881,
|
| 341 |
+
"grad_norm": 1.3035151958465576,
|
| 342 |
+
"learning_rate": 5e-05,
|
| 343 |
+
"loss": 1.36,
|
| 344 |
+
"step": 3500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 6.805293005671078,
|
| 348 |
+
"grad_norm": 1.1840296983718872,
|
| 349 |
+
"learning_rate": 5e-05,
|
| 350 |
+
"loss": 1.3599,
|
| 351 |
+
"step": 3600
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 6.994328922495274,
|
| 355 |
+
"grad_norm": 1.780287265777588,
|
| 356 |
+
"learning_rate": 5e-05,
|
| 357 |
+
"loss": 1.355,
|
| 358 |
+
"step": 3700
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 7.0,
|
| 362 |
+
"eval_accuracy": 0.565076923076923,
|
| 363 |
+
"eval_loss": 1.9659509658813477,
|
| 364 |
+
"eval_runtime": 5.3127,
|
| 365 |
+
"eval_samples_per_second": 94.114,
|
| 366 |
+
"eval_steps_per_second": 11.858,
|
| 367 |
+
"step": 3703
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 7.0,
|
| 371 |
+
"eval_exact_match": 18.0,
|
| 372 |
+
"eval_f1": 26.546666666666663,
|
| 373 |
+
"step": 3703
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 7.183364839319471,
|
| 377 |
+
"grad_norm": 1.1608421802520752,
|
| 378 |
+
"learning_rate": 5e-05,
|
| 379 |
+
"loss": 1.298,
|
| 380 |
+
"step": 3800
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 7.3724007561436675,
|
| 384 |
+
"grad_norm": 1.083270788192749,
|
| 385 |
+
"learning_rate": 5e-05,
|
| 386 |
+
"loss": 1.3088,
|
| 387 |
+
"step": 3900
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 7.561436672967864,
|
| 391 |
+
"grad_norm": 1.3489899635314941,
|
| 392 |
+
"learning_rate": 5e-05,
|
| 393 |
+
"loss": 1.299,
|
| 394 |
+
"step": 4000
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 7.750472589792061,
|
| 398 |
+
"grad_norm": 1.1663447618484497,
|
| 399 |
+
"learning_rate": 5e-05,
|
| 400 |
+
"loss": 1.2841,
|
| 401 |
+
"step": 4100
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 7.939508506616257,
|
| 405 |
+
"grad_norm": 1.9308583736419678,
|
| 406 |
+
"learning_rate": 5e-05,
|
| 407 |
+
"loss": 1.314,
|
| 408 |
+
"step": 4200
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 8.0,
|
| 412 |
+
"eval_accuracy": 0.5616923076923077,
|
| 413 |
+
"eval_loss": 2.1164443492889404,
|
| 414 |
+
"eval_runtime": 5.2165,
|
| 415 |
+
"eval_samples_per_second": 95.85,
|
| 416 |
+
"eval_steps_per_second": 12.077,
|
| 417 |
+
"step": 4232
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 8.0,
|
| 421 |
+
"eval_exact_match": 17.0,
|
| 422 |
+
"eval_f1": 24.659841269841277,
|
| 423 |
+
"step": 4232
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 8.128544423440454,
|
| 427 |
+
"grad_norm": 1.109632134437561,
|
| 428 |
+
"learning_rate": 5e-05,
|
| 429 |
+
"loss": 1.2558,
|
| 430 |
+
"step": 4300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 8.31758034026465,
|
| 434 |
+
"grad_norm": 1.1132491827011108,
|
| 435 |
+
"learning_rate": 5e-05,
|
| 436 |
+
"loss": 1.2264,
|
| 437 |
+
"step": 4400
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 8.506616257088847,
|
| 441 |
+
"grad_norm": 1.1017369031906128,
|
| 442 |
+
"learning_rate": 5e-05,
|
| 443 |
+
"loss": 1.2649,
|
| 444 |
+
"step": 4500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 8.695652173913043,
|
| 448 |
+
"grad_norm": 1.0874963998794556,
|
| 449 |
+
"learning_rate": 5e-05,
|
| 450 |
+
"loss": 1.2512,
|
| 451 |
+
"step": 4600
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 8.88468809073724,
|
| 455 |
+
"grad_norm": 1.2617064714431763,
|
| 456 |
+
"learning_rate": 5e-05,
|
| 457 |
+
"loss": 1.261,
|
| 458 |
+
"step": 4700
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 9.0,
|
| 462 |
+
"eval_accuracy": 0.5622051282051282,
|
| 463 |
+
"eval_loss": 2.1635327339172363,
|
| 464 |
+
"eval_runtime": 5.0832,
|
| 465 |
+
"eval_samples_per_second": 98.363,
|
| 466 |
+
"eval_steps_per_second": 12.394,
|
| 467 |
+
"step": 4761
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 9.0,
|
| 471 |
+
"eval_exact_match": 17.8,
|
| 472 |
+
"eval_f1": 25.451428571428576,
|
| 473 |
+
"step": 4761
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 9.073724007561436,
|
| 477 |
+
"grad_norm": 1.2258027791976929,
|
| 478 |
+
"learning_rate": 5e-05,
|
| 479 |
+
"loss": 1.2298,
|
| 480 |
+
"step": 4800
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 9.262759924385634,
|
| 484 |
+
"grad_norm": 1.8261148929595947,
|
| 485 |
+
"learning_rate": 5e-05,
|
| 486 |
+
"loss": 1.1748,
|
| 487 |
+
"step": 4900
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 9.45179584120983,
|
| 491 |
+
"grad_norm": 1.1221072673797607,
|
| 492 |
+
"learning_rate": 5e-05,
|
| 493 |
+
"loss": 1.19,
|
| 494 |
+
"step": 5000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 9.640831758034027,
|
| 498 |
+
"grad_norm": 1.3320170640945435,
|
| 499 |
+
"learning_rate": 5e-05,
|
| 500 |
+
"loss": 1.1932,
|
| 501 |
+
"step": 5100
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 9.829867674858223,
|
| 505 |
+
"grad_norm": 1.194077730178833,
|
| 506 |
+
"learning_rate": 5e-05,
|
| 507 |
+
"loss": 1.217,
|
| 508 |
+
"step": 5200
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 10.0,
|
| 512 |
+
"eval_accuracy": 0.5612820512820513,
|
| 513 |
+
"eval_loss": 2.244041919708252,
|
| 514 |
+
"eval_runtime": 5.1606,
|
| 515 |
+
"eval_samples_per_second": 96.889,
|
| 516 |
+
"eval_steps_per_second": 12.208,
|
| 517 |
+
"step": 5290
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 10.0,
|
| 521 |
+
"eval_exact_match": 18.4,
|
| 522 |
+
"eval_f1": 26.067662337662348,
|
| 523 |
+
"step": 5290
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 10.01890359168242,
|
| 527 |
+
"grad_norm": 1.1352814435958862,
|
| 528 |
+
"learning_rate": 5e-05,
|
| 529 |
+
"loss": 1.2093,
|
| 530 |
+
"step": 5300
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 10.207939508506616,
|
| 534 |
+
"grad_norm": 1.2741838693618774,
|
| 535 |
+
"learning_rate": 5e-05,
|
| 536 |
+
"loss": 1.1467,
|
| 537 |
+
"step": 5400
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 10.396975425330814,
|
| 541 |
+
"grad_norm": 1.6901249885559082,
|
| 542 |
+
"learning_rate": 5e-05,
|
| 543 |
+
"loss": 1.1288,
|
| 544 |
+
"step": 5500
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 10.58601134215501,
|
| 548 |
+
"grad_norm": 1.1944465637207031,
|
| 549 |
+
"learning_rate": 5e-05,
|
| 550 |
+
"loss": 1.1399,
|
| 551 |
+
"step": 5600
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 10.775047258979207,
|
| 555 |
+
"grad_norm": 1.2234572172164917,
|
| 556 |
+
"learning_rate": 5e-05,
|
| 557 |
+
"loss": 1.1678,
|
| 558 |
+
"step": 5700
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 10.964083175803403,
|
| 562 |
+
"grad_norm": 1.2781612873077393,
|
| 563 |
+
"learning_rate": 5e-05,
|
| 564 |
+
"loss": 1.146,
|
| 565 |
+
"step": 5800
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 11.0,
|
| 569 |
+
"eval_accuracy": 0.5618461538461539,
|
| 570 |
+
"eval_loss": 2.296630859375,
|
| 571 |
+
"eval_runtime": 5.1078,
|
| 572 |
+
"eval_samples_per_second": 97.889,
|
| 573 |
+
"eval_steps_per_second": 12.334,
|
| 574 |
+
"step": 5819
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 11.0,
|
| 578 |
+
"eval_exact_match": 16.8,
|
| 579 |
+
"eval_f1": 23.63305916305917,
|
| 580 |
+
"step": 5819
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 11.1531190926276,
|
| 584 |
+
"grad_norm": 1.138975739479065,
|
| 585 |
+
"learning_rate": 5e-05,
|
| 586 |
+
"loss": 1.0842,
|
| 587 |
+
"step": 5900
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 11.342155009451796,
|
| 591 |
+
"grad_norm": 1.727989912033081,
|
| 592 |
+
"learning_rate": 5e-05,
|
| 593 |
+
"loss": 1.0806,
|
| 594 |
+
"step": 6000
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 11.531190926275993,
|
| 598 |
+
"grad_norm": 1.3104358911514282,
|
| 599 |
+
"learning_rate": 5e-05,
|
| 600 |
+
"loss": 1.0953,
|
| 601 |
+
"step": 6100
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 11.720226843100189,
|
| 605 |
+
"grad_norm": 1.3629850149154663,
|
| 606 |
+
"learning_rate": 5e-05,
|
| 607 |
+
"loss": 1.0945,
|
| 608 |
+
"step": 6200
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 11.909262759924385,
|
| 612 |
+
"grad_norm": 1.3276056051254272,
|
| 613 |
+
"learning_rate": 5e-05,
|
| 614 |
+
"loss": 1.1069,
|
| 615 |
+
"step": 6300
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 12.0,
|
| 619 |
+
"eval_accuracy": 0.562,
|
| 620 |
+
"eval_loss": 2.3118155002593994,
|
| 621 |
+
"eval_runtime": 5.3837,
|
| 622 |
+
"eval_samples_per_second": 92.873,
|
| 623 |
+
"eval_steps_per_second": 11.702,
|
| 624 |
+
"step": 6348
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 12.0,
|
| 628 |
+
"eval_exact_match": 17.4,
|
| 629 |
+
"eval_f1": 24.43924963924964,
|
| 630 |
+
"step": 6348
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 12.098298676748582,
|
| 634 |
+
"grad_norm": 1.2608078718185425,
|
| 635 |
+
"learning_rate": 5e-05,
|
| 636 |
+
"loss": 1.0418,
|
| 637 |
+
"step": 6400
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 12.287334593572778,
|
| 641 |
+
"grad_norm": 1.4456945657730103,
|
| 642 |
+
"learning_rate": 5e-05,
|
| 643 |
+
"loss": 1.0258,
|
| 644 |
+
"step": 6500
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 12.476370510396976,
|
| 648 |
+
"grad_norm": 1.4195287227630615,
|
| 649 |
+
"learning_rate": 5e-05,
|
| 650 |
+
"loss": 1.0255,
|
| 651 |
+
"step": 6600
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 12.665406427221171,
|
| 655 |
+
"grad_norm": 1.2595598697662354,
|
| 656 |
+
"learning_rate": 5e-05,
|
| 657 |
+
"loss": 1.0511,
|
| 658 |
+
"step": 6700
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 12.854442344045369,
|
| 662 |
+
"grad_norm": 1.5901292562484741,
|
| 663 |
+
"learning_rate": 5e-05,
|
| 664 |
+
"loss": 1.045,
|
| 665 |
+
"step": 6800
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 13.0,
|
| 669 |
+
"eval_accuracy": 0.5614871794871795,
|
| 670 |
+
"eval_loss": 2.3580987453460693,
|
| 671 |
+
"eval_runtime": 5.3496,
|
| 672 |
+
"eval_samples_per_second": 93.466,
|
| 673 |
+
"eval_steps_per_second": 11.777,
|
| 674 |
+
"step": 6877
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 13.0,
|
| 678 |
+
"eval_exact_match": 17.2,
|
| 679 |
+
"eval_f1": 24.350995670995676,
|
| 680 |
+
"step": 6877
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 13.043478260869565,
|
| 684 |
+
"grad_norm": 1.471511721611023,
|
| 685 |
+
"learning_rate": 5e-05,
|
| 686 |
+
"loss": 1.0404,
|
| 687 |
+
"step": 6900
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 13.232514177693762,
|
| 691 |
+
"grad_norm": 1.2928757667541504,
|
| 692 |
+
"learning_rate": 5e-05,
|
| 693 |
+
"loss": 0.9573,
|
| 694 |
+
"step": 7000
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 13.421550094517958,
|
| 698 |
+
"grad_norm": 1.5545622110366821,
|
| 699 |
+
"learning_rate": 5e-05,
|
| 700 |
+
"loss": 0.9583,
|
| 701 |
+
"step": 7100
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 13.610586011342155,
|
| 705 |
+
"grad_norm": 1.6132512092590332,
|
| 706 |
+
"learning_rate": 5e-05,
|
| 707 |
+
"loss": 0.981,
|
| 708 |
+
"step": 7200
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 13.799621928166351,
|
| 712 |
+
"grad_norm": 1.7548742294311523,
|
| 713 |
+
"learning_rate": 5e-05,
|
| 714 |
+
"loss": 0.9999,
|
| 715 |
+
"step": 7300
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 13.988657844990549,
|
| 719 |
+
"grad_norm": 1.4219907522201538,
|
| 720 |
+
"learning_rate": 5e-05,
|
| 721 |
+
"loss": 1.0028,
|
| 722 |
+
"step": 7400
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 14.0,
|
| 726 |
+
"eval_accuracy": 0.5618974358974359,
|
| 727 |
+
"eval_loss": 2.413728952407837,
|
| 728 |
+
"eval_runtime": 5.0464,
|
| 729 |
+
"eval_samples_per_second": 99.08,
|
| 730 |
+
"eval_steps_per_second": 12.484,
|
| 731 |
+
"step": 7406
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 14.0,
|
| 735 |
+
"eval_exact_match": 16.6,
|
| 736 |
+
"eval_f1": 24.201789321789327,
|
| 737 |
+
"step": 7406
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 14.177693761814744,
|
| 741 |
+
"grad_norm": 1.5799965858459473,
|
| 742 |
+
"learning_rate": 5e-05,
|
| 743 |
+
"loss": 0.9096,
|
| 744 |
+
"step": 7500
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 14.366729678638942,
|
| 748 |
+
"grad_norm": 1.5961594581604004,
|
| 749 |
+
"learning_rate": 5e-05,
|
| 750 |
+
"loss": 0.9075,
|
| 751 |
+
"step": 7600
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 14.555765595463138,
|
| 755 |
+
"grad_norm": 1.5756512880325317,
|
| 756 |
+
"learning_rate": 5e-05,
|
| 757 |
+
"loss": 0.9222,
|
| 758 |
+
"step": 7700
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 14.744801512287335,
|
| 762 |
+
"grad_norm": 1.515251636505127,
|
| 763 |
+
"learning_rate": 5e-05,
|
| 764 |
+
"loss": 0.9445,
|
| 765 |
+
"step": 7800
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 14.93383742911153,
|
| 769 |
+
"grad_norm": 2.6804299354553223,
|
| 770 |
+
"learning_rate": 5e-05,
|
| 771 |
+
"loss": 0.9153,
|
| 772 |
+
"step": 7900
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 15.0,
|
| 776 |
+
"eval_accuracy": 0.5596923076923077,
|
| 777 |
+
"eval_loss": 2.4756176471710205,
|
| 778 |
+
"eval_runtime": 5.1956,
|
| 779 |
+
"eval_samples_per_second": 96.236,
|
| 780 |
+
"eval_steps_per_second": 12.126,
|
| 781 |
+
"step": 7935
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 15.0,
|
| 785 |
+
"eval_exact_match": 16.8,
|
| 786 |
+
"eval_f1": 24.146709956709966,
|
| 787 |
+
"step": 7935
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 15.122873345935728,
|
| 791 |
+
"grad_norm": 1.7786214351654053,
|
| 792 |
+
"learning_rate": 5e-05,
|
| 793 |
+
"loss": 0.8874,
|
| 794 |
+
"step": 8000
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 15.311909262759924,
|
| 798 |
+
"grad_norm": 1.709060788154602,
|
| 799 |
+
"learning_rate": 5e-05,
|
| 800 |
+
"loss": 0.8538,
|
| 801 |
+
"step": 8100
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 15.500945179584122,
|
| 805 |
+
"grad_norm": 2.3245434761047363,
|
| 806 |
+
"learning_rate": 5e-05,
|
| 807 |
+
"loss": 0.8591,
|
| 808 |
+
"step": 8200
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 15.689981096408317,
|
| 812 |
+
"grad_norm": 1.6101887226104736,
|
| 813 |
+
"learning_rate": 5e-05,
|
| 814 |
+
"loss": 0.8593,
|
| 815 |
+
"step": 8300
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 15.879017013232515,
|
| 819 |
+
"grad_norm": 1.5917792320251465,
|
| 820 |
+
"learning_rate": 5e-05,
|
| 821 |
+
"loss": 0.8748,
|
| 822 |
+
"step": 8400
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 16.0,
|
| 826 |
+
"eval_accuracy": 0.5604615384615385,
|
| 827 |
+
"eval_loss": 2.4434447288513184,
|
| 828 |
+
"eval_runtime": 5.1072,
|
| 829 |
+
"eval_samples_per_second": 97.901,
|
| 830 |
+
"eval_steps_per_second": 12.336,
|
| 831 |
+
"step": 8464
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 16.0,
|
| 835 |
+
"eval_exact_match": 15.6,
|
| 836 |
+
"eval_f1": 22.917027417027416,
|
| 837 |
+
"step": 8464
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 16.068052930056712,
|
| 841 |
+
"grad_norm": 1.6529980897903442,
|
| 842 |
+
"learning_rate": 5e-05,
|
| 843 |
+
"loss": 0.8413,
|
| 844 |
+
"step": 8500
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 16.257088846880908,
|
| 848 |
+
"grad_norm": 1.931520938873291,
|
| 849 |
+
"learning_rate": 5e-05,
|
| 850 |
+
"loss": 0.7863,
|
| 851 |
+
"step": 8600
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 16.446124763705104,
|
| 855 |
+
"grad_norm": 1.8401894569396973,
|
| 856 |
+
"learning_rate": 5e-05,
|
| 857 |
+
"loss": 0.799,
|
| 858 |
+
"step": 8700
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 16.6351606805293,
|
| 862 |
+
"grad_norm": 1.7952015399932861,
|
| 863 |
+
"learning_rate": 5e-05,
|
| 864 |
+
"loss": 0.8238,
|
| 865 |
+
"step": 8800
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 16.8241965973535,
|
| 869 |
+
"grad_norm": 1.8028634786605835,
|
| 870 |
+
"learning_rate": 5e-05,
|
| 871 |
+
"loss": 0.807,
|
| 872 |
+
"step": 8900
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 17.0,
|
| 876 |
+
"eval_accuracy": 0.5606153846153846,
|
| 877 |
+
"eval_loss": 2.4520959854125977,
|
| 878 |
+
"eval_runtime": 5.1769,
|
| 879 |
+
"eval_samples_per_second": 96.584,
|
| 880 |
+
"eval_steps_per_second": 12.17,
|
| 881 |
+
"step": 8993
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 17.0,
|
| 885 |
+
"eval_exact_match": 17.4,
|
| 886 |
+
"eval_f1": 25.104011544011545,
|
| 887 |
+
"step": 8993
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 17.013232514177695,
|
| 891 |
+
"grad_norm": 1.7197688817977905,
|
| 892 |
+
"learning_rate": 5e-05,
|
| 893 |
+
"loss": 0.8249,
|
| 894 |
+
"step": 9000
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 17.20226843100189,
|
| 898 |
+
"grad_norm": 1.768463134765625,
|
| 899 |
+
"learning_rate": 5e-05,
|
| 900 |
+
"loss": 0.7304,
|
| 901 |
+
"step": 9100
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 17.391304347826086,
|
| 905 |
+
"grad_norm": 1.9696024656295776,
|
| 906 |
+
"learning_rate": 5e-05,
|
| 907 |
+
"loss": 0.7445,
|
| 908 |
+
"step": 9200
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 17.58034026465028,
|
| 912 |
+
"grad_norm": 2.093703269958496,
|
| 913 |
+
"learning_rate": 5e-05,
|
| 914 |
+
"loss": 0.755,
|
| 915 |
+
"step": 9300
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 17.76937618147448,
|
| 919 |
+
"grad_norm": 1.909550666809082,
|
| 920 |
+
"learning_rate": 5e-05,
|
| 921 |
+
"loss": 0.7698,
|
| 922 |
+
"step": 9400
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 17.958412098298677,
|
| 926 |
+
"grad_norm": 1.6835806369781494,
|
| 927 |
+
"learning_rate": 5e-05,
|
| 928 |
+
"loss": 0.7711,
|
| 929 |
+
"step": 9500
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 18.0,
|
| 933 |
+
"eval_accuracy": 0.5603589743589743,
|
| 934 |
+
"eval_loss": 2.473491668701172,
|
| 935 |
+
"eval_runtime": 5.4257,
|
| 936 |
+
"eval_samples_per_second": 92.155,
|
| 937 |
+
"eval_steps_per_second": 11.611,
|
| 938 |
+
"step": 9522
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 18.0,
|
| 942 |
+
"eval_exact_match": 17.0,
|
| 943 |
+
"eval_f1": 24.074487734487732,
|
| 944 |
+
"step": 9522
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 18.147448015122873,
|
| 948 |
+
"grad_norm": 2.0483736991882324,
|
| 949 |
+
"learning_rate": 5e-05,
|
| 950 |
+
"loss": 0.7048,
|
| 951 |
+
"step": 9600
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 18.33648393194707,
|
| 955 |
+
"grad_norm": 1.987457275390625,
|
| 956 |
+
"learning_rate": 5e-05,
|
| 957 |
+
"loss": 0.6863,
|
| 958 |
+
"step": 9700
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 18.525519848771268,
|
| 962 |
+
"grad_norm": 2.1744563579559326,
|
| 963 |
+
"learning_rate": 5e-05,
|
| 964 |
+
"loss": 0.7045,
|
| 965 |
+
"step": 9800
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 18.714555765595463,
|
| 969 |
+
"grad_norm": 1.9871633052825928,
|
| 970 |
+
"learning_rate": 5e-05,
|
| 971 |
+
"loss": 0.7076,
|
| 972 |
+
"step": 9900
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 18.90359168241966,
|
| 976 |
+
"grad_norm": 1.8895001411437988,
|
| 977 |
+
"learning_rate": 5e-05,
|
| 978 |
+
"loss": 0.7202,
|
| 979 |
+
"step": 10000
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 19.0,
|
| 983 |
+
"eval_accuracy": 0.5601538461538461,
|
| 984 |
+
"eval_loss": 2.5168700218200684,
|
| 985 |
+
"eval_runtime": 5.0434,
|
| 986 |
+
"eval_samples_per_second": 99.14,
|
| 987 |
+
"eval_steps_per_second": 12.492,
|
| 988 |
+
"step": 10051
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 19.0,
|
| 992 |
+
"eval_exact_match": 17.2,
|
| 993 |
+
"eval_f1": 24.260360750360757,
|
| 994 |
+
"step": 10051
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 19.092627599243855,
|
| 998 |
+
"grad_norm": 1.7914209365844727,
|
| 999 |
+
"learning_rate": 5e-05,
|
| 1000 |
+
"loss": 0.6728,
|
| 1001 |
+
"step": 10100
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 19.281663516068054,
|
| 1005 |
+
"grad_norm": 2.198495388031006,
|
| 1006 |
+
"learning_rate": 5e-05,
|
| 1007 |
+
"loss": 0.6241,
|
| 1008 |
+
"step": 10200
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 19.47069943289225,
|
| 1012 |
+
"grad_norm": 1.81365966796875,
|
| 1013 |
+
"learning_rate": 5e-05,
|
| 1014 |
+
"loss": 0.6558,
|
| 1015 |
+
"step": 10300
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 19.659735349716446,
|
| 1019 |
+
"grad_norm": 1.6571800708770752,
|
| 1020 |
+
"learning_rate": 5e-05,
|
| 1021 |
+
"loss": 0.6652,
|
| 1022 |
+
"step": 10400
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 19.84877126654064,
|
| 1026 |
+
"grad_norm": 1.6469954252243042,
|
| 1027 |
+
"learning_rate": 5e-05,
|
| 1028 |
+
"loss": 0.6637,
|
| 1029 |
+
"step": 10500
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 20.0,
|
| 1033 |
+
"eval_accuracy": 0.5596410256410257,
|
| 1034 |
+
"eval_loss": 2.516073703765869,
|
| 1035 |
+
"eval_runtime": 5.8234,
|
| 1036 |
+
"eval_samples_per_second": 85.86,
|
| 1037 |
+
"eval_steps_per_second": 10.818,
|
| 1038 |
+
"step": 10580
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 20.0,
|
| 1042 |
+
"eval_exact_match": 17.6,
|
| 1043 |
+
"eval_f1": 25.225079365079367,
|
| 1044 |
+
"step": 10580
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 20.03780718336484,
|
| 1048 |
+
"grad_norm": 1.7114077806472778,
|
| 1049 |
+
"learning_rate": 5e-05,
|
| 1050 |
+
"loss": 0.66,
|
| 1051 |
+
"step": 10600
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 20.226843100189036,
|
| 1055 |
+
"grad_norm": 1.9962202310562134,
|
| 1056 |
+
"learning_rate": 5e-05,
|
| 1057 |
+
"loss": 0.5938,
|
| 1058 |
+
"step": 10700
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 20.415879017013232,
|
| 1062 |
+
"grad_norm": 2.397592067718506,
|
| 1063 |
+
"learning_rate": 5e-05,
|
| 1064 |
+
"loss": 0.6042,
|
| 1065 |
+
"step": 10800
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 20.604914933837428,
|
| 1069 |
+
"grad_norm": 2.0724213123321533,
|
| 1070 |
+
"learning_rate": 5e-05,
|
| 1071 |
+
"loss": 0.6124,
|
| 1072 |
+
"step": 10900
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 20.793950850661627,
|
| 1076 |
+
"grad_norm": 1.9385457038879395,
|
| 1077 |
+
"learning_rate": 5e-05,
|
| 1078 |
+
"loss": 0.6078,
|
| 1079 |
+
"step": 11000
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 20.982986767485823,
|
| 1083 |
+
"grad_norm": 2.034963607788086,
|
| 1084 |
+
"learning_rate": 5e-05,
|
| 1085 |
+
"loss": 0.6257,
|
| 1086 |
+
"step": 11100
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 21.0,
|
| 1090 |
+
"eval_accuracy": 0.5597948717948718,
|
| 1091 |
+
"eval_loss": 2.5497183799743652,
|
| 1092 |
+
"eval_runtime": 5.0442,
|
| 1093 |
+
"eval_samples_per_second": 99.123,
|
| 1094 |
+
"eval_steps_per_second": 12.489,
|
| 1095 |
+
"step": 11109
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 21.0,
|
| 1099 |
+
"eval_exact_match": 17.4,
|
| 1100 |
+
"eval_f1": 24.755238095238095,
|
| 1101 |
+
"step": 11109
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 21.17202268431002,
|
| 1105 |
+
"grad_norm": 1.9768177270889282,
|
| 1106 |
+
"learning_rate": 5e-05,
|
| 1107 |
+
"loss": 0.5458,
|
| 1108 |
+
"step": 11200
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 21.361058601134214,
|
| 1112 |
+
"grad_norm": 2.14420747756958,
|
| 1113 |
+
"learning_rate": 5e-05,
|
| 1114 |
+
"loss": 0.558,
|
| 1115 |
+
"step": 11300
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 21.550094517958414,
|
| 1119 |
+
"grad_norm": 2.5267951488494873,
|
| 1120 |
+
"learning_rate": 5e-05,
|
| 1121 |
+
"loss": 0.5646,
|
| 1122 |
+
"step": 11400
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 21.73913043478261,
|
| 1126 |
+
"grad_norm": 2.114386558532715,
|
| 1127 |
+
"learning_rate": 5e-05,
|
| 1128 |
+
"loss": 0.572,
|
| 1129 |
+
"step": 11500
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 21.928166351606805,
|
| 1133 |
+
"grad_norm": 2.424217700958252,
|
| 1134 |
+
"learning_rate": 5e-05,
|
| 1135 |
+
"loss": 0.5928,
|
| 1136 |
+
"step": 11600
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 22.0,
|
| 1140 |
+
"eval_accuracy": 0.5593846153846154,
|
| 1141 |
+
"eval_loss": 2.579535722732544,
|
| 1142 |
+
"eval_runtime": 5.7849,
|
| 1143 |
+
"eval_samples_per_second": 86.433,
|
| 1144 |
+
"eval_steps_per_second": 10.89,
|
| 1145 |
+
"step": 11638
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 22.0,
|
| 1149 |
+
"eval_exact_match": 16.8,
|
| 1150 |
+
"eval_f1": 23.666507936507937,
|
| 1151 |
+
"step": 11638
|
| 1152 |
+
}
|
| 1153 |
+
],
|
| 1154 |
+
"logging_steps": 100,
|
| 1155 |
+
"max_steps": 26450,
|
| 1156 |
+
"num_input_tokens_seen": 0,
|
| 1157 |
+
"num_train_epochs": 50,
|
| 1158 |
+
"save_steps": 500,
|
| 1159 |
+
"stateful_callbacks": {
|
| 1160 |
+
"TrainerControl": {
|
| 1161 |
+
"args": {
|
| 1162 |
+
"should_epoch_stop": false,
|
| 1163 |
+
"should_evaluate": false,
|
| 1164 |
+
"should_log": false,
|
| 1165 |
+
"should_save": true,
|
| 1166 |
+
"should_training_stop": false
|
| 1167 |
+
},
|
| 1168 |
+
"attributes": {}
|
| 1169 |
+
}
|
| 1170 |
+
},
|
| 1171 |
+
"total_flos": 7.169435655733248e+17,
|
| 1172 |
+
"train_batch_size": 1,
|
| 1173 |
+
"trial_name": null,
|
| 1174 |
+
"trial_params": null
|
| 1175 |
+
}
|
checkpoint-11638/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f01d18f717251d8791982fc93ed5352f2d247add98e1102e2a52cc0a32128bb7
|
| 3 |
+
size 5304
|
checkpoint-11638/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|