Training in progress, epoch 46, checkpoint
Browse files- checkpoint-8812/README.md +9 -0
- checkpoint-8812/adapter_config.json +25 -0
- checkpoint-8812/adapter_model.safetensors +3 -0
- checkpoint-8812/added_tokens.json +5 -0
- checkpoint-8812/merges.txt +0 -0
- checkpoint-8812/optimizer.pt +3 -0
- checkpoint-8812/rng_state_0.pth +3 -0
- checkpoint-8812/rng_state_1.pth +3 -0
- checkpoint-8812/rng_state_2.pth +3 -0
- checkpoint-8812/rng_state_3.pth +3 -0
- checkpoint-8812/scheduler.pt +3 -0
- checkpoint-8812/special_tokens_map.json +14 -0
- checkpoint-8812/tokenizer.json +0 -0
- checkpoint-8812/tokenizer_config.json +43 -0
- checkpoint-8812/trainer_state.json +1072 -0
- checkpoint-8812/training_args.bin +3 -0
- checkpoint-8812/vocab.json +0 -0
checkpoint-8812/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-8812/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-8812/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ada98ecabb68c548fb776d987c48ed5bd7721e0f85050588685afa780266dc4
|
| 3 |
+
size 112130416
|
checkpoint-8812/added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
checkpoint-8812/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8812/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee1e009f1870d346807a3da21610326e8e89b1f59b376c26fe560542652e1bb5
|
| 3 |
+
size 224537202
|
checkpoint-8812/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fdefc10ff11f3d45ee1141074b80592836747f009d7e6c3e93156c99ccef0ae
|
| 3 |
+
size 15024
|
checkpoint-8812/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:592124eba4e01dff1d65f187e4cf2763c8981b948910b68f17b2fc41f38bcabf
|
| 3 |
+
size 15024
|
checkpoint-8812/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f74e987d07aa7f8fc96a5d1df7ec0b89eeaa2ac88710d2d486cdd0f3a5f55ae7
|
| 3 |
+
size 15024
|
checkpoint-8812/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e29f77c3d090220124009ba350619d4e11dd4fa338cda08055703effc505996f
|
| 3 |
+
size 15024
|
checkpoint-8812/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d689a8d9e93735fa1abf2168685b02d2777dcf659f290aa4e7d5834a36e3df77
|
| 3 |
+
size 1064
|
checkpoint-8812/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-8812/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8812/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-8812/trainer_state.json
ADDED
|
@@ -0,0 +1,1072 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 46.99733333333333,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8812,
|
| 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": 0.2409825623035431,
|
| 14 |
+
"learning_rate": 0.0001,
|
| 15 |
+
"loss": 1.7886,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.9973333333333333,
|
| 20 |
+
"eval_accuracy": 0.6061076233183856,
|
| 21 |
+
"eval_loss": 1.6901254653930664,
|
| 22 |
+
"eval_runtime": 5.5484,
|
| 23 |
+
"eval_samples_per_second": 90.116,
|
| 24 |
+
"eval_steps_per_second": 11.355,
|
| 25 |
+
"step": 187
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.0666666666666667,
|
| 29 |
+
"grad_norm": 0.2729445993900299,
|
| 30 |
+
"learning_rate": 0.0001,
|
| 31 |
+
"loss": 1.7283,
|
| 32 |
+
"step": 200
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.6,
|
| 36 |
+
"grad_norm": 0.37678101658821106,
|
| 37 |
+
"learning_rate": 0.0001,
|
| 38 |
+
"loss": 1.6544,
|
| 39 |
+
"step": 300
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.0,
|
| 43 |
+
"eval_accuracy": 0.607677130044843,
|
| 44 |
+
"eval_loss": 1.6766204833984375,
|
| 45 |
+
"eval_runtime": 6.4294,
|
| 46 |
+
"eval_samples_per_second": 77.768,
|
| 47 |
+
"eval_steps_per_second": 9.799,
|
| 48 |
+
"step": 375
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 2.1333333333333333,
|
| 52 |
+
"grad_norm": 0.4604090750217438,
|
| 53 |
+
"learning_rate": 0.0001,
|
| 54 |
+
"loss": 1.6338,
|
| 55 |
+
"step": 400
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 2.6666666666666665,
|
| 59 |
+
"grad_norm": 0.5606330633163452,
|
| 60 |
+
"learning_rate": 0.0001,
|
| 61 |
+
"loss": 1.5273,
|
| 62 |
+
"step": 500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.997333333333333,
|
| 66 |
+
"eval_accuracy": 0.6079910313901346,
|
| 67 |
+
"eval_loss": 1.6929064989089966,
|
| 68 |
+
"eval_runtime": 5.431,
|
| 69 |
+
"eval_samples_per_second": 92.063,
|
| 70 |
+
"eval_steps_per_second": 11.6,
|
| 71 |
+
"step": 562
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 3.2,
|
| 75 |
+
"grad_norm": 0.6363856196403503,
|
| 76 |
+
"learning_rate": 0.0001,
|
| 77 |
+
"loss": 1.4796,
|
| 78 |
+
"step": 600
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.7333333333333334,
|
| 82 |
+
"grad_norm": 0.5985731482505798,
|
| 83 |
+
"learning_rate": 0.0001,
|
| 84 |
+
"loss": 1.3871,
|
| 85 |
+
"step": 700
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 4.0,
|
| 89 |
+
"eval_accuracy": 0.606896860986547,
|
| 90 |
+
"eval_loss": 1.7257370948791504,
|
| 91 |
+
"eval_runtime": 5.8318,
|
| 92 |
+
"eval_samples_per_second": 85.737,
|
| 93 |
+
"eval_steps_per_second": 10.803,
|
| 94 |
+
"step": 750
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 4.266666666666667,
|
| 98 |
+
"grad_norm": 0.7769015431404114,
|
| 99 |
+
"learning_rate": 0.0001,
|
| 100 |
+
"loss": 1.3013,
|
| 101 |
+
"step": 800
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 4.8,
|
| 105 |
+
"grad_norm": 0.708043098449707,
|
| 106 |
+
"learning_rate": 0.0001,
|
| 107 |
+
"loss": 1.23,
|
| 108 |
+
"step": 900
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 4.997333333333334,
|
| 112 |
+
"eval_accuracy": 0.6061076233183856,
|
| 113 |
+
"eval_loss": 1.7812739610671997,
|
| 114 |
+
"eval_runtime": 5.9335,
|
| 115 |
+
"eval_samples_per_second": 84.267,
|
| 116 |
+
"eval_steps_per_second": 10.618,
|
| 117 |
+
"step": 937
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 5.333333333333333,
|
| 121 |
+
"grad_norm": 0.8580867648124695,
|
| 122 |
+
"learning_rate": 0.0001,
|
| 123 |
+
"loss": 1.1011,
|
| 124 |
+
"step": 1000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 5.866666666666667,
|
| 128 |
+
"grad_norm": 0.9232878684997559,
|
| 129 |
+
"learning_rate": 0.0001,
|
| 130 |
+
"loss": 1.0749,
|
| 131 |
+
"step": 1100
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 6.0,
|
| 135 |
+
"eval_accuracy": 0.6018026905829597,
|
| 136 |
+
"eval_loss": 1.877648949623108,
|
| 137 |
+
"eval_runtime": 6.474,
|
| 138 |
+
"eval_samples_per_second": 77.231,
|
| 139 |
+
"eval_steps_per_second": 9.731,
|
| 140 |
+
"step": 1125
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 6.4,
|
| 144 |
+
"grad_norm": 1.0364516973495483,
|
| 145 |
+
"learning_rate": 0.0001,
|
| 146 |
+
"loss": 0.9164,
|
| 147 |
+
"step": 1200
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 6.933333333333334,
|
| 151 |
+
"grad_norm": 1.0082701444625854,
|
| 152 |
+
"learning_rate": 0.0001,
|
| 153 |
+
"loss": 0.8957,
|
| 154 |
+
"step": 1300
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 6.997333333333334,
|
| 158 |
+
"eval_accuracy": 0.5997937219730942,
|
| 159 |
+
"eval_loss": 1.978247046470642,
|
| 160 |
+
"eval_runtime": 5.9491,
|
| 161 |
+
"eval_samples_per_second": 84.047,
|
| 162 |
+
"eval_steps_per_second": 10.59,
|
| 163 |
+
"step": 1312
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 7.466666666666667,
|
| 167 |
+
"grad_norm": 1.0375924110412598,
|
| 168 |
+
"learning_rate": 0.0001,
|
| 169 |
+
"loss": 0.7382,
|
| 170 |
+
"step": 1400
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 8.0,
|
| 174 |
+
"grad_norm": 1.115308403968811,
|
| 175 |
+
"learning_rate": 0.0001,
|
| 176 |
+
"loss": 0.729,
|
| 177 |
+
"step": 1500
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 8.0,
|
| 181 |
+
"eval_accuracy": 0.5965919282511211,
|
| 182 |
+
"eval_loss": 2.097362756729126,
|
| 183 |
+
"eval_runtime": 6.5905,
|
| 184 |
+
"eval_samples_per_second": 75.867,
|
| 185 |
+
"eval_steps_per_second": 9.559,
|
| 186 |
+
"step": 1500
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 8.533333333333333,
|
| 190 |
+
"grad_norm": 1.3251475095748901,
|
| 191 |
+
"learning_rate": 0.0001,
|
| 192 |
+
"loss": 0.5643,
|
| 193 |
+
"step": 1600
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 8.997333333333334,
|
| 197 |
+
"eval_accuracy": 0.5931300448430493,
|
| 198 |
+
"eval_loss": 2.2553179264068604,
|
| 199 |
+
"eval_runtime": 6.1864,
|
| 200 |
+
"eval_samples_per_second": 80.823,
|
| 201 |
+
"eval_steps_per_second": 10.184,
|
| 202 |
+
"step": 1687
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 9.066666666666666,
|
| 206 |
+
"grad_norm": 1.0753710269927979,
|
| 207 |
+
"learning_rate": 0.0001,
|
| 208 |
+
"loss": 0.5706,
|
| 209 |
+
"step": 1700
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 9.6,
|
| 213 |
+
"grad_norm": 1.5658849477767944,
|
| 214 |
+
"learning_rate": 0.0001,
|
| 215 |
+
"loss": 0.4538,
|
| 216 |
+
"step": 1800
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 10.0,
|
| 220 |
+
"eval_accuracy": 0.5900627802690583,
|
| 221 |
+
"eval_loss": 2.408897876739502,
|
| 222 |
+
"eval_runtime": 6.4582,
|
| 223 |
+
"eval_samples_per_second": 77.422,
|
| 224 |
+
"eval_steps_per_second": 9.755,
|
| 225 |
+
"step": 1875
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 10.133333333333333,
|
| 229 |
+
"grad_norm": 1.6254231929779053,
|
| 230 |
+
"learning_rate": 0.0001,
|
| 231 |
+
"loss": 0.4286,
|
| 232 |
+
"step": 1900
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 10.666666666666666,
|
| 236 |
+
"grad_norm": 1.187232255935669,
|
| 237 |
+
"learning_rate": 0.0001,
|
| 238 |
+
"loss": 0.3563,
|
| 239 |
+
"step": 2000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 10.997333333333334,
|
| 243 |
+
"eval_accuracy": 0.588914798206278,
|
| 244 |
+
"eval_loss": 2.529802083969116,
|
| 245 |
+
"eval_runtime": 5.9806,
|
| 246 |
+
"eval_samples_per_second": 83.604,
|
| 247 |
+
"eval_steps_per_second": 10.534,
|
| 248 |
+
"step": 2062
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 11.2,
|
| 252 |
+
"grad_norm": 1.3838512897491455,
|
| 253 |
+
"learning_rate": 0.0001,
|
| 254 |
+
"loss": 0.3256,
|
| 255 |
+
"step": 2100
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 11.733333333333333,
|
| 259 |
+
"grad_norm": 1.249315619468689,
|
| 260 |
+
"learning_rate": 0.0001,
|
| 261 |
+
"loss": 0.2787,
|
| 262 |
+
"step": 2200
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 12.0,
|
| 266 |
+
"eval_accuracy": 0.5870582959641255,
|
| 267 |
+
"eval_loss": 2.684791088104248,
|
| 268 |
+
"eval_runtime": 5.7871,
|
| 269 |
+
"eval_samples_per_second": 86.399,
|
| 270 |
+
"eval_steps_per_second": 10.886,
|
| 271 |
+
"step": 2250
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 12.266666666666667,
|
| 275 |
+
"grad_norm": 1.163707971572876,
|
| 276 |
+
"learning_rate": 0.0001,
|
| 277 |
+
"loss": 0.2558,
|
| 278 |
+
"step": 2300
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 12.8,
|
| 282 |
+
"grad_norm": 1.092466950416565,
|
| 283 |
+
"learning_rate": 0.0001,
|
| 284 |
+
"loss": 0.2314,
|
| 285 |
+
"step": 2400
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 12.997333333333334,
|
| 289 |
+
"eval_accuracy": 0.5863408071748879,
|
| 290 |
+
"eval_loss": 2.7943203449249268,
|
| 291 |
+
"eval_runtime": 6.5027,
|
| 292 |
+
"eval_samples_per_second": 76.891,
|
| 293 |
+
"eval_steps_per_second": 9.688,
|
| 294 |
+
"step": 2437
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 13.333333333333334,
|
| 298 |
+
"grad_norm": 1.1065410375595093,
|
| 299 |
+
"learning_rate": 0.0001,
|
| 300 |
+
"loss": 0.2029,
|
| 301 |
+
"step": 2500
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 13.866666666666667,
|
| 305 |
+
"grad_norm": 1.1960605382919312,
|
| 306 |
+
"learning_rate": 0.0001,
|
| 307 |
+
"loss": 0.1923,
|
| 308 |
+
"step": 2600
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 14.0,
|
| 312 |
+
"eval_accuracy": 0.5856502242152466,
|
| 313 |
+
"eval_loss": 2.8624069690704346,
|
| 314 |
+
"eval_runtime": 5.5405,
|
| 315 |
+
"eval_samples_per_second": 90.244,
|
| 316 |
+
"eval_steps_per_second": 11.371,
|
| 317 |
+
"step": 2625
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 14.4,
|
| 321 |
+
"grad_norm": 1.014957070350647,
|
| 322 |
+
"learning_rate": 0.0001,
|
| 323 |
+
"loss": 0.1661,
|
| 324 |
+
"step": 2700
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 14.933333333333334,
|
| 328 |
+
"grad_norm": 1.2782268524169922,
|
| 329 |
+
"learning_rate": 0.0001,
|
| 330 |
+
"loss": 0.1687,
|
| 331 |
+
"step": 2800
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 14.997333333333334,
|
| 335 |
+
"eval_accuracy": 0.5847533632286995,
|
| 336 |
+
"eval_loss": 2.978261947631836,
|
| 337 |
+
"eval_runtime": 6.5241,
|
| 338 |
+
"eval_samples_per_second": 76.639,
|
| 339 |
+
"eval_steps_per_second": 9.656,
|
| 340 |
+
"step": 2812
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 15.466666666666667,
|
| 344 |
+
"grad_norm": 1.0024491548538208,
|
| 345 |
+
"learning_rate": 0.0001,
|
| 346 |
+
"loss": 0.1464,
|
| 347 |
+
"step": 2900
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 16.0,
|
| 351 |
+
"grad_norm": 0.9853018522262573,
|
| 352 |
+
"learning_rate": 0.0001,
|
| 353 |
+
"loss": 0.1514,
|
| 354 |
+
"step": 3000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 16.0,
|
| 358 |
+
"eval_accuracy": 0.5849865470852018,
|
| 359 |
+
"eval_loss": 3.0238428115844727,
|
| 360 |
+
"eval_runtime": 5.8457,
|
| 361 |
+
"eval_samples_per_second": 85.533,
|
| 362 |
+
"eval_steps_per_second": 10.777,
|
| 363 |
+
"step": 3000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 16.533333333333335,
|
| 367 |
+
"grad_norm": 1.2373902797698975,
|
| 368 |
+
"learning_rate": 0.0001,
|
| 369 |
+
"loss": 0.1282,
|
| 370 |
+
"step": 3100
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 16.997333333333334,
|
| 374 |
+
"eval_accuracy": 0.5841614349775784,
|
| 375 |
+
"eval_loss": 3.091371774673462,
|
| 376 |
+
"eval_runtime": 5.5018,
|
| 377 |
+
"eval_samples_per_second": 90.879,
|
| 378 |
+
"eval_steps_per_second": 11.451,
|
| 379 |
+
"step": 3187
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 17.066666666666666,
|
| 383 |
+
"grad_norm": 0.9496106505393982,
|
| 384 |
+
"learning_rate": 0.0001,
|
| 385 |
+
"loss": 0.1358,
|
| 386 |
+
"step": 3200
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 17.6,
|
| 390 |
+
"grad_norm": 1.0109747648239136,
|
| 391 |
+
"learning_rate": 0.0001,
|
| 392 |
+
"loss": 0.121,
|
| 393 |
+
"step": 3300
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 18.0,
|
| 397 |
+
"eval_accuracy": 0.5847982062780269,
|
| 398 |
+
"eval_loss": 3.143228530883789,
|
| 399 |
+
"eval_runtime": 5.4395,
|
| 400 |
+
"eval_samples_per_second": 91.919,
|
| 401 |
+
"eval_steps_per_second": 11.582,
|
| 402 |
+
"step": 3375
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 18.133333333333333,
|
| 406 |
+
"grad_norm": 0.9266707301139832,
|
| 407 |
+
"learning_rate": 0.0001,
|
| 408 |
+
"loss": 0.1262,
|
| 409 |
+
"step": 3400
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 18.666666666666668,
|
| 413 |
+
"grad_norm": 1.026375651359558,
|
| 414 |
+
"learning_rate": 0.0001,
|
| 415 |
+
"loss": 0.1164,
|
| 416 |
+
"step": 3500
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 18.997333333333334,
|
| 420 |
+
"eval_accuracy": 0.5847533632286995,
|
| 421 |
+
"eval_loss": 3.231442451477051,
|
| 422 |
+
"eval_runtime": 6.4528,
|
| 423 |
+
"eval_samples_per_second": 77.486,
|
| 424 |
+
"eval_steps_per_second": 9.763,
|
| 425 |
+
"step": 3562
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 19.2,
|
| 429 |
+
"grad_norm": 0.9512910842895508,
|
| 430 |
+
"learning_rate": 0.0001,
|
| 431 |
+
"loss": 0.1153,
|
| 432 |
+
"step": 3600
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 19.733333333333334,
|
| 436 |
+
"grad_norm": 1.1021068096160889,
|
| 437 |
+
"learning_rate": 0.0001,
|
| 438 |
+
"loss": 0.1103,
|
| 439 |
+
"step": 3700
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 20.0,
|
| 443 |
+
"eval_accuracy": 0.5843946188340807,
|
| 444 |
+
"eval_loss": 3.278094530105591,
|
| 445 |
+
"eval_runtime": 6.151,
|
| 446 |
+
"eval_samples_per_second": 81.288,
|
| 447 |
+
"eval_steps_per_second": 10.242,
|
| 448 |
+
"step": 3750
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 20.266666666666666,
|
| 452 |
+
"grad_norm": 0.7233396768569946,
|
| 453 |
+
"learning_rate": 0.0001,
|
| 454 |
+
"loss": 0.1076,
|
| 455 |
+
"step": 3800
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 20.8,
|
| 459 |
+
"grad_norm": 0.8059793710708618,
|
| 460 |
+
"learning_rate": 0.0001,
|
| 461 |
+
"loss": 0.1077,
|
| 462 |
+
"step": 3900
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 20.997333333333334,
|
| 466 |
+
"eval_accuracy": 0.5842062780269058,
|
| 467 |
+
"eval_loss": 3.2767584323883057,
|
| 468 |
+
"eval_runtime": 6.2046,
|
| 469 |
+
"eval_samples_per_second": 80.586,
|
| 470 |
+
"eval_steps_per_second": 10.154,
|
| 471 |
+
"step": 3937
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 21.333333333333332,
|
| 475 |
+
"grad_norm": 0.4895855784416199,
|
| 476 |
+
"learning_rate": 0.0001,
|
| 477 |
+
"loss": 0.1029,
|
| 478 |
+
"step": 4000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 21.866666666666667,
|
| 482 |
+
"grad_norm": 1.0620789527893066,
|
| 483 |
+
"learning_rate": 0.0001,
|
| 484 |
+
"loss": 0.1053,
|
| 485 |
+
"step": 4100
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 22.0,
|
| 489 |
+
"eval_accuracy": 0.58447533632287,
|
| 490 |
+
"eval_loss": 3.31538724899292,
|
| 491 |
+
"eval_runtime": 5.8193,
|
| 492 |
+
"eval_samples_per_second": 85.921,
|
| 493 |
+
"eval_steps_per_second": 10.826,
|
| 494 |
+
"step": 4125
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 22.4,
|
| 498 |
+
"grad_norm": 0.9283909201622009,
|
| 499 |
+
"learning_rate": 0.0001,
|
| 500 |
+
"loss": 0.099,
|
| 501 |
+
"step": 4200
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 22.933333333333334,
|
| 505 |
+
"grad_norm": 0.6225098371505737,
|
| 506 |
+
"learning_rate": 0.0001,
|
| 507 |
+
"loss": 0.1025,
|
| 508 |
+
"step": 4300
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 22.997333333333334,
|
| 512 |
+
"eval_accuracy": 0.5845829596412556,
|
| 513 |
+
"eval_loss": 3.316826343536377,
|
| 514 |
+
"eval_runtime": 6.28,
|
| 515 |
+
"eval_samples_per_second": 79.618,
|
| 516 |
+
"eval_steps_per_second": 10.032,
|
| 517 |
+
"step": 4312
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 23.466666666666665,
|
| 521 |
+
"grad_norm": 0.7798640131950378,
|
| 522 |
+
"learning_rate": 0.0001,
|
| 523 |
+
"loss": 0.0971,
|
| 524 |
+
"step": 4400
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 24.0,
|
| 528 |
+
"grad_norm": 0.9243062734603882,
|
| 529 |
+
"learning_rate": 0.0001,
|
| 530 |
+
"loss": 0.1019,
|
| 531 |
+
"step": 4500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 24.0,
|
| 535 |
+
"eval_accuracy": 0.5838744394618834,
|
| 536 |
+
"eval_loss": 3.3672451972961426,
|
| 537 |
+
"eval_runtime": 6.2482,
|
| 538 |
+
"eval_samples_per_second": 80.024,
|
| 539 |
+
"eval_steps_per_second": 10.083,
|
| 540 |
+
"step": 4500
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 24.533333333333335,
|
| 544 |
+
"grad_norm": 0.5875428915023804,
|
| 545 |
+
"learning_rate": 0.0001,
|
| 546 |
+
"loss": 0.0957,
|
| 547 |
+
"step": 4600
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 24.997333333333334,
|
| 551 |
+
"eval_accuracy": 0.5842780269058296,
|
| 552 |
+
"eval_loss": 3.3244740962982178,
|
| 553 |
+
"eval_runtime": 5.7909,
|
| 554 |
+
"eval_samples_per_second": 86.343,
|
| 555 |
+
"eval_steps_per_second": 10.879,
|
| 556 |
+
"step": 4687
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 25.066666666666666,
|
| 560 |
+
"grad_norm": 0.5470825433731079,
|
| 561 |
+
"learning_rate": 0.0001,
|
| 562 |
+
"loss": 0.1009,
|
| 563 |
+
"step": 4700
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 25.6,
|
| 567 |
+
"grad_norm": 0.5594859719276428,
|
| 568 |
+
"learning_rate": 0.0001,
|
| 569 |
+
"loss": 0.0973,
|
| 570 |
+
"step": 4800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 26.0,
|
| 574 |
+
"eval_accuracy": 0.584627802690583,
|
| 575 |
+
"eval_loss": 3.345505475997925,
|
| 576 |
+
"eval_runtime": 5.4801,
|
| 577 |
+
"eval_samples_per_second": 91.239,
|
| 578 |
+
"eval_steps_per_second": 11.496,
|
| 579 |
+
"step": 4875
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 26.133333333333333,
|
| 583 |
+
"grad_norm": 0.7405847311019897,
|
| 584 |
+
"learning_rate": 0.0001,
|
| 585 |
+
"loss": 0.1007,
|
| 586 |
+
"step": 4900
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 26.666666666666668,
|
| 590 |
+
"grad_norm": 0.7365854978561401,
|
| 591 |
+
"learning_rate": 0.0001,
|
| 592 |
+
"loss": 0.0976,
|
| 593 |
+
"step": 5000
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 26.997333333333334,
|
| 597 |
+
"eval_accuracy": 0.5831390134529147,
|
| 598 |
+
"eval_loss": 3.374565839767456,
|
| 599 |
+
"eval_runtime": 5.5219,
|
| 600 |
+
"eval_samples_per_second": 90.549,
|
| 601 |
+
"eval_steps_per_second": 11.409,
|
| 602 |
+
"step": 5062
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 27.2,
|
| 606 |
+
"grad_norm": 0.7343279123306274,
|
| 607 |
+
"learning_rate": 0.0001,
|
| 608 |
+
"loss": 0.0986,
|
| 609 |
+
"step": 5100
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 27.733333333333334,
|
| 613 |
+
"grad_norm": 0.73392653465271,
|
| 614 |
+
"learning_rate": 0.0001,
|
| 615 |
+
"loss": 0.0956,
|
| 616 |
+
"step": 5200
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 28.0,
|
| 620 |
+
"eval_accuracy": 0.5836412556053812,
|
| 621 |
+
"eval_loss": 3.345768928527832,
|
| 622 |
+
"eval_runtime": 6.4622,
|
| 623 |
+
"eval_samples_per_second": 77.373,
|
| 624 |
+
"eval_steps_per_second": 9.749,
|
| 625 |
+
"step": 5250
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 28.266666666666666,
|
| 629 |
+
"grad_norm": 0.6106265783309937,
|
| 630 |
+
"learning_rate": 0.0001,
|
| 631 |
+
"loss": 0.0953,
|
| 632 |
+
"step": 5300
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 28.8,
|
| 636 |
+
"grad_norm": 0.8447858691215515,
|
| 637 |
+
"learning_rate": 0.0001,
|
| 638 |
+
"loss": 0.0963,
|
| 639 |
+
"step": 5400
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 28.997333333333334,
|
| 643 |
+
"eval_accuracy": 0.5845112107623318,
|
| 644 |
+
"eval_loss": 3.388141632080078,
|
| 645 |
+
"eval_runtime": 5.8659,
|
| 646 |
+
"eval_samples_per_second": 85.239,
|
| 647 |
+
"eval_steps_per_second": 10.74,
|
| 648 |
+
"step": 5437
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 29.333333333333332,
|
| 652 |
+
"grad_norm": 0.670528769493103,
|
| 653 |
+
"learning_rate": 0.0001,
|
| 654 |
+
"loss": 0.094,
|
| 655 |
+
"step": 5500
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 29.866666666666667,
|
| 659 |
+
"grad_norm": 0.5652866959571838,
|
| 660 |
+
"learning_rate": 0.0001,
|
| 661 |
+
"loss": 0.0951,
|
| 662 |
+
"step": 5600
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 30.0,
|
| 666 |
+
"eval_accuracy": 0.5842242152466368,
|
| 667 |
+
"eval_loss": 3.4071028232574463,
|
| 668 |
+
"eval_runtime": 5.914,
|
| 669 |
+
"eval_samples_per_second": 84.546,
|
| 670 |
+
"eval_steps_per_second": 10.653,
|
| 671 |
+
"step": 5625
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 30.4,
|
| 675 |
+
"grad_norm": 0.44825807213783264,
|
| 676 |
+
"learning_rate": 0.0001,
|
| 677 |
+
"loss": 0.0904,
|
| 678 |
+
"step": 5700
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 30.933333333333334,
|
| 682 |
+
"grad_norm": 0.8034001588821411,
|
| 683 |
+
"learning_rate": 0.0001,
|
| 684 |
+
"loss": 0.0932,
|
| 685 |
+
"step": 5800
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 30.997333333333334,
|
| 689 |
+
"eval_accuracy": 0.5836502242152466,
|
| 690 |
+
"eval_loss": 3.4573781490325928,
|
| 691 |
+
"eval_runtime": 5.4773,
|
| 692 |
+
"eval_samples_per_second": 91.286,
|
| 693 |
+
"eval_steps_per_second": 11.502,
|
| 694 |
+
"step": 5812
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 31.466666666666665,
|
| 698 |
+
"grad_norm": 0.9231824278831482,
|
| 699 |
+
"learning_rate": 0.0001,
|
| 700 |
+
"loss": 0.0883,
|
| 701 |
+
"step": 5900
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 32.0,
|
| 705 |
+
"grad_norm": 0.6104317903518677,
|
| 706 |
+
"learning_rate": 0.0001,
|
| 707 |
+
"loss": 0.0932,
|
| 708 |
+
"step": 6000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 32.0,
|
| 712 |
+
"eval_accuracy": 0.5840896860986547,
|
| 713 |
+
"eval_loss": 3.44976806640625,
|
| 714 |
+
"eval_runtime": 6.1617,
|
| 715 |
+
"eval_samples_per_second": 81.147,
|
| 716 |
+
"eval_steps_per_second": 10.225,
|
| 717 |
+
"step": 6000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 32.53333333333333,
|
| 721 |
+
"grad_norm": 0.5761642456054688,
|
| 722 |
+
"learning_rate": 0.0001,
|
| 723 |
+
"loss": 0.0876,
|
| 724 |
+
"step": 6100
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 32.99733333333333,
|
| 728 |
+
"eval_accuracy": 0.5829865470852018,
|
| 729 |
+
"eval_loss": 3.4677207469940186,
|
| 730 |
+
"eval_runtime": 6.2914,
|
| 731 |
+
"eval_samples_per_second": 79.474,
|
| 732 |
+
"eval_steps_per_second": 10.014,
|
| 733 |
+
"step": 6187
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 33.06666666666667,
|
| 737 |
+
"grad_norm": 0.5899339318275452,
|
| 738 |
+
"learning_rate": 0.0001,
|
| 739 |
+
"loss": 0.0916,
|
| 740 |
+
"step": 6200
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 33.6,
|
| 744 |
+
"grad_norm": 0.571556031703949,
|
| 745 |
+
"learning_rate": 0.0001,
|
| 746 |
+
"loss": 0.0888,
|
| 747 |
+
"step": 6300
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 34.0,
|
| 751 |
+
"eval_accuracy": 0.5835156950672645,
|
| 752 |
+
"eval_loss": 3.469017505645752,
|
| 753 |
+
"eval_runtime": 6.145,
|
| 754 |
+
"eval_samples_per_second": 81.367,
|
| 755 |
+
"eval_steps_per_second": 10.252,
|
| 756 |
+
"step": 6375
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 34.13333333333333,
|
| 760 |
+
"grad_norm": 0.65375155210495,
|
| 761 |
+
"learning_rate": 0.0001,
|
| 762 |
+
"loss": 0.0901,
|
| 763 |
+
"step": 6400
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 34.666666666666664,
|
| 767 |
+
"grad_norm": 0.6190968155860901,
|
| 768 |
+
"learning_rate": 0.0001,
|
| 769 |
+
"loss": 0.0887,
|
| 770 |
+
"step": 6500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 34.99733333333333,
|
| 774 |
+
"eval_accuracy": 0.5831031390134529,
|
| 775 |
+
"eval_loss": 3.448068141937256,
|
| 776 |
+
"eval_runtime": 6.4843,
|
| 777 |
+
"eval_samples_per_second": 77.109,
|
| 778 |
+
"eval_steps_per_second": 9.716,
|
| 779 |
+
"step": 6562
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 35.2,
|
| 783 |
+
"grad_norm": 0.9301517009735107,
|
| 784 |
+
"learning_rate": 0.0001,
|
| 785 |
+
"loss": 0.0899,
|
| 786 |
+
"step": 6600
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 35.733333333333334,
|
| 790 |
+
"grad_norm": 0.7078553438186646,
|
| 791 |
+
"learning_rate": 0.0001,
|
| 792 |
+
"loss": 0.0883,
|
| 793 |
+
"step": 6700
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 36.0,
|
| 797 |
+
"eval_accuracy": 0.5839282511210763,
|
| 798 |
+
"eval_loss": 3.4745078086853027,
|
| 799 |
+
"eval_runtime": 5.5493,
|
| 800 |
+
"eval_samples_per_second": 90.101,
|
| 801 |
+
"eval_steps_per_second": 11.353,
|
| 802 |
+
"step": 6750
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 36.266666666666666,
|
| 806 |
+
"grad_norm": 0.6631983518600464,
|
| 807 |
+
"learning_rate": 0.0001,
|
| 808 |
+
"loss": 0.0884,
|
| 809 |
+
"step": 6800
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 36.8,
|
| 813 |
+
"grad_norm": 0.7493350505828857,
|
| 814 |
+
"learning_rate": 0.0001,
|
| 815 |
+
"loss": 0.0893,
|
| 816 |
+
"step": 6900
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 36.99733333333333,
|
| 820 |
+
"eval_accuracy": 0.5831031390134529,
|
| 821 |
+
"eval_loss": 3.4574029445648193,
|
| 822 |
+
"eval_runtime": 6.1633,
|
| 823 |
+
"eval_samples_per_second": 81.125,
|
| 824 |
+
"eval_steps_per_second": 10.222,
|
| 825 |
+
"step": 6937
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 37.333333333333336,
|
| 829 |
+
"grad_norm": 0.6909760236740112,
|
| 830 |
+
"learning_rate": 0.0001,
|
| 831 |
+
"loss": 0.0894,
|
| 832 |
+
"step": 7000
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 37.86666666666667,
|
| 836 |
+
"grad_norm": 0.8321955800056458,
|
| 837 |
+
"learning_rate": 0.0001,
|
| 838 |
+
"loss": 0.0903,
|
| 839 |
+
"step": 7100
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 38.0,
|
| 843 |
+
"eval_accuracy": 0.583829596412556,
|
| 844 |
+
"eval_loss": 3.4798455238342285,
|
| 845 |
+
"eval_runtime": 5.4728,
|
| 846 |
+
"eval_samples_per_second": 91.36,
|
| 847 |
+
"eval_steps_per_second": 11.511,
|
| 848 |
+
"step": 7125
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 38.4,
|
| 852 |
+
"grad_norm": 0.47543054819107056,
|
| 853 |
+
"learning_rate": 0.0001,
|
| 854 |
+
"loss": 0.0878,
|
| 855 |
+
"step": 7200
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 38.93333333333333,
|
| 859 |
+
"grad_norm": 0.6321227550506592,
|
| 860 |
+
"learning_rate": 0.0001,
|
| 861 |
+
"loss": 0.0902,
|
| 862 |
+
"step": 7300
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 38.99733333333333,
|
| 866 |
+
"eval_accuracy": 0.5838116591928251,
|
| 867 |
+
"eval_loss": 3.486259937286377,
|
| 868 |
+
"eval_runtime": 6.285,
|
| 869 |
+
"eval_samples_per_second": 79.555,
|
| 870 |
+
"eval_steps_per_second": 10.024,
|
| 871 |
+
"step": 7312
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 39.46666666666667,
|
| 875 |
+
"grad_norm": 0.5080650448799133,
|
| 876 |
+
"learning_rate": 0.0001,
|
| 877 |
+
"loss": 0.0854,
|
| 878 |
+
"step": 7400
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 40.0,
|
| 882 |
+
"grad_norm": 0.5988374948501587,
|
| 883 |
+
"learning_rate": 0.0001,
|
| 884 |
+
"loss": 0.0896,
|
| 885 |
+
"step": 7500
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 40.0,
|
| 889 |
+
"eval_accuracy": 0.5838565022421525,
|
| 890 |
+
"eval_loss": 3.4676125049591064,
|
| 891 |
+
"eval_runtime": 6.575,
|
| 892 |
+
"eval_samples_per_second": 76.046,
|
| 893 |
+
"eval_steps_per_second": 9.582,
|
| 894 |
+
"step": 7500
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 40.53333333333333,
|
| 898 |
+
"grad_norm": 0.4248475134372711,
|
| 899 |
+
"learning_rate": 0.0001,
|
| 900 |
+
"loss": 0.0841,
|
| 901 |
+
"step": 7600
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 40.99733333333333,
|
| 905 |
+
"eval_accuracy": 0.5837309417040358,
|
| 906 |
+
"eval_loss": 3.515667200088501,
|
| 907 |
+
"eval_runtime": 6.2502,
|
| 908 |
+
"eval_samples_per_second": 79.997,
|
| 909 |
+
"eval_steps_per_second": 10.08,
|
| 910 |
+
"step": 7687
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 41.06666666666667,
|
| 914 |
+
"grad_norm": 0.3535381555557251,
|
| 915 |
+
"learning_rate": 0.0001,
|
| 916 |
+
"loss": 0.0876,
|
| 917 |
+
"step": 7700
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 41.6,
|
| 921 |
+
"grad_norm": 0.6824341416358948,
|
| 922 |
+
"learning_rate": 0.0001,
|
| 923 |
+
"loss": 0.0844,
|
| 924 |
+
"step": 7800
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 42.0,
|
| 928 |
+
"eval_accuracy": 0.5832914798206278,
|
| 929 |
+
"eval_loss": 3.517089605331421,
|
| 930 |
+
"eval_runtime": 6.5335,
|
| 931 |
+
"eval_samples_per_second": 76.529,
|
| 932 |
+
"eval_steps_per_second": 9.643,
|
| 933 |
+
"step": 7875
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 42.13333333333333,
|
| 937 |
+
"grad_norm": 0.5794711112976074,
|
| 938 |
+
"learning_rate": 0.0001,
|
| 939 |
+
"loss": 0.0858,
|
| 940 |
+
"step": 7900
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 42.666666666666664,
|
| 944 |
+
"grad_norm": 0.7291499376296997,
|
| 945 |
+
"learning_rate": 0.0001,
|
| 946 |
+
"loss": 0.0838,
|
| 947 |
+
"step": 8000
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 42.99733333333333,
|
| 951 |
+
"eval_accuracy": 0.5831300448430493,
|
| 952 |
+
"eval_loss": 3.5575757026672363,
|
| 953 |
+
"eval_runtime": 5.5324,
|
| 954 |
+
"eval_samples_per_second": 90.377,
|
| 955 |
+
"eval_steps_per_second": 11.387,
|
| 956 |
+
"step": 8062
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 43.2,
|
| 960 |
+
"grad_norm": 0.5227051973342896,
|
| 961 |
+
"learning_rate": 0.0001,
|
| 962 |
+
"loss": 0.0856,
|
| 963 |
+
"step": 8100
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 43.733333333333334,
|
| 967 |
+
"grad_norm": 0.49097922444343567,
|
| 968 |
+
"learning_rate": 0.0001,
|
| 969 |
+
"loss": 0.0854,
|
| 970 |
+
"step": 8200
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 44.0,
|
| 974 |
+
"eval_accuracy": 0.5837937219730942,
|
| 975 |
+
"eval_loss": 3.5440053939819336,
|
| 976 |
+
"eval_runtime": 6.5256,
|
| 977 |
+
"eval_samples_per_second": 76.622,
|
| 978 |
+
"eval_steps_per_second": 9.654,
|
| 979 |
+
"step": 8250
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 44.266666666666666,
|
| 983 |
+
"grad_norm": 0.3847533166408539,
|
| 984 |
+
"learning_rate": 0.0001,
|
| 985 |
+
"loss": 0.0849,
|
| 986 |
+
"step": 8300
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 44.8,
|
| 990 |
+
"grad_norm": 0.6862115859985352,
|
| 991 |
+
"learning_rate": 0.0001,
|
| 992 |
+
"loss": 0.085,
|
| 993 |
+
"step": 8400
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 44.99733333333333,
|
| 997 |
+
"eval_accuracy": 0.5842062780269058,
|
| 998 |
+
"eval_loss": 3.4776952266693115,
|
| 999 |
+
"eval_runtime": 5.4406,
|
| 1000 |
+
"eval_samples_per_second": 91.902,
|
| 1001 |
+
"eval_steps_per_second": 11.58,
|
| 1002 |
+
"step": 8437
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 45.333333333333336,
|
| 1006 |
+
"grad_norm": 0.6308585405349731,
|
| 1007 |
+
"learning_rate": 0.0001,
|
| 1008 |
+
"loss": 0.0848,
|
| 1009 |
+
"step": 8500
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 45.86666666666667,
|
| 1013 |
+
"grad_norm": 0.539695143699646,
|
| 1014 |
+
"learning_rate": 0.0001,
|
| 1015 |
+
"loss": 0.0863,
|
| 1016 |
+
"step": 8600
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 46.0,
|
| 1020 |
+
"eval_accuracy": 0.5831748878923767,
|
| 1021 |
+
"eval_loss": 3.4933485984802246,
|
| 1022 |
+
"eval_runtime": 6.195,
|
| 1023 |
+
"eval_samples_per_second": 80.71,
|
| 1024 |
+
"eval_steps_per_second": 10.17,
|
| 1025 |
+
"step": 8625
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 46.4,
|
| 1029 |
+
"grad_norm": 0.5608128309249878,
|
| 1030 |
+
"learning_rate": 0.0001,
|
| 1031 |
+
"loss": 0.0845,
|
| 1032 |
+
"step": 8700
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 46.93333333333333,
|
| 1036 |
+
"grad_norm": 0.7052953839302063,
|
| 1037 |
+
"learning_rate": 0.0001,
|
| 1038 |
+
"loss": 0.0875,
|
| 1039 |
+
"step": 8800
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 46.99733333333333,
|
| 1043 |
+
"eval_accuracy": 0.5840717488789238,
|
| 1044 |
+
"eval_loss": 3.528217315673828,
|
| 1045 |
+
"eval_runtime": 5.4754,
|
| 1046 |
+
"eval_samples_per_second": 91.317,
|
| 1047 |
+
"eval_steps_per_second": 11.506,
|
| 1048 |
+
"step": 8812
|
| 1049 |
+
}
|
| 1050 |
+
],
|
| 1051 |
+
"logging_steps": 100,
|
| 1052 |
+
"max_steps": 9350,
|
| 1053 |
+
"num_input_tokens_seen": 0,
|
| 1054 |
+
"num_train_epochs": 50,
|
| 1055 |
+
"save_steps": 500,
|
| 1056 |
+
"stateful_callbacks": {
|
| 1057 |
+
"TrainerControl": {
|
| 1058 |
+
"args": {
|
| 1059 |
+
"should_epoch_stop": false,
|
| 1060 |
+
"should_evaluate": false,
|
| 1061 |
+
"should_log": false,
|
| 1062 |
+
"should_save": true,
|
| 1063 |
+
"should_training_stop": false
|
| 1064 |
+
},
|
| 1065 |
+
"attributes": {}
|
| 1066 |
+
}
|
| 1067 |
+
},
|
| 1068 |
+
"total_flos": 8.876676458920018e+17,
|
| 1069 |
+
"train_batch_size": 1,
|
| 1070 |
+
"trial_name": null,
|
| 1071 |
+
"trial_params": null
|
| 1072 |
+
}
|
checkpoint-8812/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a48e2910c0614efc83f1cdab0e18284ec3fdf02b7a0946bdd13c56e7e15f701
|
| 3 |
+
size 5304
|
checkpoint-8812/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|