Commit
•
b131b21
1
Parent(s):
695daa0
Upload folder using huggingface_hub
Browse files- .DS_Store +0 -0
- README.md +20 -0
- adapter_config.json +21 -0
- adapter_model.bin +3 -0
- added_tokens.json +3 -0
- merges.txt +0 -0
- special_tokens_map.json +27 -0
- tokenizer.json +0 -0
- tokenizer_config.json +32 -0
- trainer_state.json +616 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.DS_Store
ADDED
|
Binary file (6.15 kB). View file
|
|
|
README.md
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- load_in_8bit: False
|
| 9 |
+
- load_in_4bit: True
|
| 10 |
+
- llm_int8_threshold: 6.0
|
| 11 |
+
- llm_int8_skip_modules: None
|
| 12 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 13 |
+
- llm_int8_has_fp16_weight: False
|
| 14 |
+
- bnb_4bit_quant_type: nf4
|
| 15 |
+
- bnb_4bit_use_double_quant: False
|
| 16 |
+
- bnb_4bit_compute_dtype: float16
|
| 17 |
+
### Framework versions
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- PEFT 0.4.0.dev0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "WizardLM/WizardCoder-15B-V1.0",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"layers_pattern": null,
|
| 8 |
+
"layers_to_transform": null,
|
| 9 |
+
"lora_alpha": 16,
|
| 10 |
+
"lora_dropout": 0.1,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 64,
|
| 14 |
+
"revision": null,
|
| 15 |
+
"target_modules": [
|
| 16 |
+
"c_proj",
|
| 17 |
+
"c_attn",
|
| 18 |
+
"c_fc"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c57bf08f3f6f772b59fbb37e7977cb3fdd5bed1615e2ce996d57fb8681400000
|
| 3 |
+
size 883539469
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 49152
|
| 3 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<fim_prefix>",
|
| 5 |
+
"<fim_middle>",
|
| 6 |
+
"<fim_suffix>",
|
| 7 |
+
"<fim_pad>",
|
| 8 |
+
"<filename>",
|
| 9 |
+
"<gh_stars>",
|
| 10 |
+
"<issue_start>",
|
| 11 |
+
"<issue_comment>",
|
| 12 |
+
"<issue_closed>",
|
| 13 |
+
"<jupyter_start>",
|
| 14 |
+
"<jupyter_text>",
|
| 15 |
+
"<jupyter_code>",
|
| 16 |
+
"<jupyter_output>",
|
| 17 |
+
"<empty_output>",
|
| 18 |
+
"<commit_before>",
|
| 19 |
+
"<commit_msg>",
|
| 20 |
+
"<commit_after>",
|
| 21 |
+
"<reponame>"
|
| 22 |
+
],
|
| 23 |
+
"bos_token": "<|endoftext|>",
|
| 24 |
+
"eos_token": "<|endoftext|>",
|
| 25 |
+
"pad_token": "[PAD]",
|
| 26 |
+
"unk_token": "<|endoftext|>"
|
| 27 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"additional_special_tokens": [
|
| 4 |
+
"<|endoftext|>",
|
| 5 |
+
"<fim_prefix>",
|
| 6 |
+
"<fim_middle>",
|
| 7 |
+
"<fim_suffix>",
|
| 8 |
+
"<fim_pad>",
|
| 9 |
+
"<filename>",
|
| 10 |
+
"<gh_stars>",
|
| 11 |
+
"<issue_start>",
|
| 12 |
+
"<issue_comment>",
|
| 13 |
+
"<issue_closed>",
|
| 14 |
+
"<jupyter_start>",
|
| 15 |
+
"<jupyter_text>",
|
| 16 |
+
"<jupyter_code>",
|
| 17 |
+
"<jupyter_output>",
|
| 18 |
+
"<empty_output>",
|
| 19 |
+
"<commit_before>",
|
| 20 |
+
"<commit_msg>",
|
| 21 |
+
"<commit_after>",
|
| 22 |
+
"<reponame>"
|
| 23 |
+
],
|
| 24 |
+
"bos_token": "<|endoftext|>",
|
| 25 |
+
"clean_up_tokenization_spaces": true,
|
| 26 |
+
"eos_token": "<|endoftext|>",
|
| 27 |
+
"model_max_length": 2048,
|
| 28 |
+
"padding_side": "right",
|
| 29 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 30 |
+
"unk_token": "<|endoftext|>",
|
| 31 |
+
"vocab_size": 49152
|
| 32 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,616 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
+
"global_step": 1000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.08,
|
| 12 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 13 |
+
"loss": 1.5005,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.16,
|
| 18 |
+
"learning_rate": 8.888888888888889e-05,
|
| 19 |
+
"loss": 1.2648,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.24,
|
| 24 |
+
"learning_rate": 0.00013333333333333334,
|
| 25 |
+
"loss": 0.8406,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.32,
|
| 30 |
+
"learning_rate": 0.00017777777777777779,
|
| 31 |
+
"loss": 0.496,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.4,
|
| 36 |
+
"learning_rate": 0.00019931271477663232,
|
| 37 |
+
"loss": 0.2602,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.48,
|
| 42 |
+
"learning_rate": 0.00019793814432989693,
|
| 43 |
+
"loss": 0.1365,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.56,
|
| 48 |
+
"learning_rate": 0.0001965635738831615,
|
| 49 |
+
"loss": 0.131,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.64,
|
| 54 |
+
"learning_rate": 0.00019518900343642613,
|
| 55 |
+
"loss": 0.1219,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.72,
|
| 60 |
+
"learning_rate": 0.00019381443298969073,
|
| 61 |
+
"loss": 0.1053,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.8,
|
| 66 |
+
"learning_rate": 0.00019243986254295533,
|
| 67 |
+
"loss": 0.1071,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.88,
|
| 72 |
+
"learning_rate": 0.00019106529209621996,
|
| 73 |
+
"loss": 0.0878,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.96,
|
| 78 |
+
"learning_rate": 0.00018969072164948454,
|
| 79 |
+
"loss": 0.0863,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.04,
|
| 84 |
+
"learning_rate": 0.00018831615120274914,
|
| 85 |
+
"loss": 0.0918,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.12,
|
| 90 |
+
"learning_rate": 0.00018694158075601377,
|
| 91 |
+
"loss": 0.0898,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.2,
|
| 96 |
+
"learning_rate": 0.00018556701030927837,
|
| 97 |
+
"loss": 0.0829,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.28,
|
| 102 |
+
"learning_rate": 0.00018419243986254294,
|
| 103 |
+
"loss": 0.0721,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.36,
|
| 108 |
+
"learning_rate": 0.00018281786941580757,
|
| 109 |
+
"loss": 0.0752,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.44,
|
| 114 |
+
"learning_rate": 0.00018144329896907217,
|
| 115 |
+
"loss": 0.0821,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.52,
|
| 120 |
+
"learning_rate": 0.00018006872852233677,
|
| 121 |
+
"loss": 0.0741,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.6,
|
| 126 |
+
"learning_rate": 0.0001786941580756014,
|
| 127 |
+
"loss": 0.0665,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.68,
|
| 132 |
+
"learning_rate": 0.00017731958762886598,
|
| 133 |
+
"loss": 0.0833,
|
| 134 |
+
"step": 210
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.76,
|
| 138 |
+
"learning_rate": 0.00017594501718213058,
|
| 139 |
+
"loss": 0.0726,
|
| 140 |
+
"step": 220
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.84,
|
| 144 |
+
"learning_rate": 0.0001745704467353952,
|
| 145 |
+
"loss": 0.0624,
|
| 146 |
+
"step": 230
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.92,
|
| 150 |
+
"learning_rate": 0.0001731958762886598,
|
| 151 |
+
"loss": 0.0716,
|
| 152 |
+
"step": 240
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.0,
|
| 156 |
+
"learning_rate": 0.00017182130584192438,
|
| 157 |
+
"loss": 0.0827,
|
| 158 |
+
"step": 250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.08,
|
| 162 |
+
"learning_rate": 0.000170446735395189,
|
| 163 |
+
"loss": 0.0506,
|
| 164 |
+
"step": 260
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.16,
|
| 168 |
+
"learning_rate": 0.00016907216494845361,
|
| 169 |
+
"loss": 0.0647,
|
| 170 |
+
"step": 270
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.24,
|
| 174 |
+
"learning_rate": 0.00016769759450171822,
|
| 175 |
+
"loss": 0.0614,
|
| 176 |
+
"step": 280
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.32,
|
| 180 |
+
"learning_rate": 0.00016632302405498285,
|
| 181 |
+
"loss": 0.0528,
|
| 182 |
+
"step": 290
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.4,
|
| 186 |
+
"learning_rate": 0.00016494845360824742,
|
| 187 |
+
"loss": 0.0514,
|
| 188 |
+
"step": 300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.48,
|
| 192 |
+
"learning_rate": 0.00016357388316151202,
|
| 193 |
+
"loss": 0.0635,
|
| 194 |
+
"step": 310
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.56,
|
| 198 |
+
"learning_rate": 0.00016219931271477665,
|
| 199 |
+
"loss": 0.0552,
|
| 200 |
+
"step": 320
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.64,
|
| 204 |
+
"learning_rate": 0.00016082474226804125,
|
| 205 |
+
"loss": 0.06,
|
| 206 |
+
"step": 330
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.72,
|
| 210 |
+
"learning_rate": 0.00015945017182130585,
|
| 211 |
+
"loss": 0.0611,
|
| 212 |
+
"step": 340
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.8,
|
| 216 |
+
"learning_rate": 0.00015807560137457046,
|
| 217 |
+
"loss": 0.0667,
|
| 218 |
+
"step": 350
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.88,
|
| 222 |
+
"learning_rate": 0.00015670103092783506,
|
| 223 |
+
"loss": 0.0669,
|
| 224 |
+
"step": 360
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.96,
|
| 228 |
+
"learning_rate": 0.00015532646048109966,
|
| 229 |
+
"loss": 0.0589,
|
| 230 |
+
"step": 370
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.04,
|
| 234 |
+
"learning_rate": 0.0001539518900343643,
|
| 235 |
+
"loss": 0.0516,
|
| 236 |
+
"step": 380
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.12,
|
| 240 |
+
"learning_rate": 0.00015257731958762886,
|
| 241 |
+
"loss": 0.0415,
|
| 242 |
+
"step": 390
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.2,
|
| 246 |
+
"learning_rate": 0.00015120274914089346,
|
| 247 |
+
"loss": 0.043,
|
| 248 |
+
"step": 400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.28,
|
| 252 |
+
"learning_rate": 0.0001498281786941581,
|
| 253 |
+
"loss": 0.0449,
|
| 254 |
+
"step": 410
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.36,
|
| 258 |
+
"learning_rate": 0.0001484536082474227,
|
| 259 |
+
"loss": 0.0467,
|
| 260 |
+
"step": 420
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.44,
|
| 264 |
+
"learning_rate": 0.0001470790378006873,
|
| 265 |
+
"loss": 0.0442,
|
| 266 |
+
"step": 430
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.52,
|
| 270 |
+
"learning_rate": 0.0001457044673539519,
|
| 271 |
+
"loss": 0.0501,
|
| 272 |
+
"step": 440
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.6,
|
| 276 |
+
"learning_rate": 0.0001443298969072165,
|
| 277 |
+
"loss": 0.0468,
|
| 278 |
+
"step": 450
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.68,
|
| 282 |
+
"learning_rate": 0.0001429553264604811,
|
| 283 |
+
"loss": 0.0503,
|
| 284 |
+
"step": 460
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.76,
|
| 288 |
+
"learning_rate": 0.00014158075601374573,
|
| 289 |
+
"loss": 0.0503,
|
| 290 |
+
"step": 470
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.84,
|
| 294 |
+
"learning_rate": 0.0001402061855670103,
|
| 295 |
+
"loss": 0.0477,
|
| 296 |
+
"step": 480
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.92,
|
| 300 |
+
"learning_rate": 0.0001388316151202749,
|
| 301 |
+
"loss": 0.0467,
|
| 302 |
+
"step": 490
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 4.0,
|
| 306 |
+
"learning_rate": 0.00013745704467353953,
|
| 307 |
+
"loss": 0.0525,
|
| 308 |
+
"step": 500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.08,
|
| 312 |
+
"learning_rate": 0.00013608247422680414,
|
| 313 |
+
"loss": 0.0434,
|
| 314 |
+
"step": 510
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 4.16,
|
| 318 |
+
"learning_rate": 0.00013470790378006874,
|
| 319 |
+
"loss": 0.0371,
|
| 320 |
+
"step": 520
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 4.24,
|
| 324 |
+
"learning_rate": 0.00013333333333333334,
|
| 325 |
+
"loss": 0.0393,
|
| 326 |
+
"step": 530
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 4.32,
|
| 330 |
+
"learning_rate": 0.00013195876288659794,
|
| 331 |
+
"loss": 0.0378,
|
| 332 |
+
"step": 540
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.4,
|
| 336 |
+
"learning_rate": 0.00013058419243986254,
|
| 337 |
+
"loss": 0.0358,
|
| 338 |
+
"step": 550
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.48,
|
| 342 |
+
"learning_rate": 0.00012920962199312717,
|
| 343 |
+
"loss": 0.04,
|
| 344 |
+
"step": 560
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.56,
|
| 348 |
+
"learning_rate": 0.00012783505154639175,
|
| 349 |
+
"loss": 0.0355,
|
| 350 |
+
"step": 570
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.64,
|
| 354 |
+
"learning_rate": 0.00012646048109965635,
|
| 355 |
+
"loss": 0.0424,
|
| 356 |
+
"step": 580
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 4.72,
|
| 360 |
+
"learning_rate": 0.00012508591065292098,
|
| 361 |
+
"loss": 0.0411,
|
| 362 |
+
"step": 590
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 4.8,
|
| 366 |
+
"learning_rate": 0.00012371134020618558,
|
| 367 |
+
"loss": 0.0374,
|
| 368 |
+
"step": 600
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.88,
|
| 372 |
+
"learning_rate": 0.00012233676975945018,
|
| 373 |
+
"loss": 0.0402,
|
| 374 |
+
"step": 610
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.96,
|
| 378 |
+
"learning_rate": 0.00012096219931271477,
|
| 379 |
+
"loss": 0.0417,
|
| 380 |
+
"step": 620
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 5.04,
|
| 384 |
+
"learning_rate": 0.00011958762886597938,
|
| 385 |
+
"loss": 0.0353,
|
| 386 |
+
"step": 630
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 5.12,
|
| 390 |
+
"learning_rate": 0.000118213058419244,
|
| 391 |
+
"loss": 0.0328,
|
| 392 |
+
"step": 640
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 5.2,
|
| 396 |
+
"learning_rate": 0.0001168384879725086,
|
| 397 |
+
"loss": 0.0356,
|
| 398 |
+
"step": 650
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 5.28,
|
| 402 |
+
"learning_rate": 0.00011546391752577319,
|
| 403 |
+
"loss": 0.0354,
|
| 404 |
+
"step": 660
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 5.36,
|
| 408 |
+
"learning_rate": 0.0001140893470790378,
|
| 409 |
+
"loss": 0.0326,
|
| 410 |
+
"step": 670
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 5.44,
|
| 414 |
+
"learning_rate": 0.0001127147766323024,
|
| 415 |
+
"loss": 0.0358,
|
| 416 |
+
"step": 680
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 5.52,
|
| 420 |
+
"learning_rate": 0.00011134020618556702,
|
| 421 |
+
"loss": 0.0355,
|
| 422 |
+
"step": 690
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 5.6,
|
| 426 |
+
"learning_rate": 0.00010996563573883164,
|
| 427 |
+
"loss": 0.0342,
|
| 428 |
+
"step": 700
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 5.68,
|
| 432 |
+
"learning_rate": 0.00010859106529209621,
|
| 433 |
+
"loss": 0.0335,
|
| 434 |
+
"step": 710
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 5.76,
|
| 438 |
+
"learning_rate": 0.00010721649484536083,
|
| 439 |
+
"loss": 0.0362,
|
| 440 |
+
"step": 720
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 5.84,
|
| 444 |
+
"learning_rate": 0.00010584192439862544,
|
| 445 |
+
"loss": 0.0343,
|
| 446 |
+
"step": 730
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 5.92,
|
| 450 |
+
"learning_rate": 0.00010446735395189004,
|
| 451 |
+
"loss": 0.0329,
|
| 452 |
+
"step": 740
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 6.0,
|
| 456 |
+
"learning_rate": 0.00010309278350515463,
|
| 457 |
+
"loss": 0.0313,
|
| 458 |
+
"step": 750
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 6.08,
|
| 462 |
+
"learning_rate": 0.00010171821305841925,
|
| 463 |
+
"loss": 0.028,
|
| 464 |
+
"step": 760
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 6.16,
|
| 468 |
+
"learning_rate": 0.00010034364261168385,
|
| 469 |
+
"loss": 0.0317,
|
| 470 |
+
"step": 770
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 6.24,
|
| 474 |
+
"learning_rate": 9.896907216494846e-05,
|
| 475 |
+
"loss": 0.029,
|
| 476 |
+
"step": 780
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 6.32,
|
| 480 |
+
"learning_rate": 9.759450171821306e-05,
|
| 481 |
+
"loss": 0.0288,
|
| 482 |
+
"step": 790
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 6.4,
|
| 486 |
+
"learning_rate": 9.621993127147767e-05,
|
| 487 |
+
"loss": 0.0281,
|
| 488 |
+
"step": 800
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 6.48,
|
| 492 |
+
"learning_rate": 9.484536082474227e-05,
|
| 493 |
+
"loss": 0.0309,
|
| 494 |
+
"step": 810
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 6.56,
|
| 498 |
+
"learning_rate": 9.347079037800688e-05,
|
| 499 |
+
"loss": 0.0334,
|
| 500 |
+
"step": 820
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 6.64,
|
| 504 |
+
"learning_rate": 9.209621993127147e-05,
|
| 505 |
+
"loss": 0.0292,
|
| 506 |
+
"step": 830
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 6.72,
|
| 510 |
+
"learning_rate": 9.072164948453609e-05,
|
| 511 |
+
"loss": 0.0331,
|
| 512 |
+
"step": 840
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 6.8,
|
| 516 |
+
"learning_rate": 8.93470790378007e-05,
|
| 517 |
+
"loss": 0.0304,
|
| 518 |
+
"step": 850
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 6.88,
|
| 522 |
+
"learning_rate": 8.797250859106529e-05,
|
| 523 |
+
"loss": 0.0308,
|
| 524 |
+
"step": 860
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 6.96,
|
| 528 |
+
"learning_rate": 8.65979381443299e-05,
|
| 529 |
+
"loss": 0.0318,
|
| 530 |
+
"step": 870
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 7.04,
|
| 534 |
+
"learning_rate": 8.52233676975945e-05,
|
| 535 |
+
"loss": 0.0257,
|
| 536 |
+
"step": 880
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 7.12,
|
| 540 |
+
"learning_rate": 8.384879725085911e-05,
|
| 541 |
+
"loss": 0.0266,
|
| 542 |
+
"step": 890
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 7.2,
|
| 546 |
+
"learning_rate": 8.247422680412371e-05,
|
| 547 |
+
"loss": 0.0251,
|
| 548 |
+
"step": 900
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 7.28,
|
| 552 |
+
"learning_rate": 8.109965635738833e-05,
|
| 553 |
+
"loss": 0.0269,
|
| 554 |
+
"step": 910
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 7.36,
|
| 558 |
+
"learning_rate": 7.972508591065293e-05,
|
| 559 |
+
"loss": 0.0296,
|
| 560 |
+
"step": 920
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 7.44,
|
| 564 |
+
"learning_rate": 7.835051546391753e-05,
|
| 565 |
+
"loss": 0.0285,
|
| 566 |
+
"step": 930
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 7.52,
|
| 570 |
+
"learning_rate": 7.697594501718214e-05,
|
| 571 |
+
"loss": 0.0286,
|
| 572 |
+
"step": 940
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 7.6,
|
| 576 |
+
"learning_rate": 7.560137457044673e-05,
|
| 577 |
+
"loss": 0.024,
|
| 578 |
+
"step": 950
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 7.68,
|
| 582 |
+
"learning_rate": 7.422680412371135e-05,
|
| 583 |
+
"loss": 0.0267,
|
| 584 |
+
"step": 960
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 7.76,
|
| 588 |
+
"learning_rate": 7.285223367697595e-05,
|
| 589 |
+
"loss": 0.0296,
|
| 590 |
+
"step": 970
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 7.84,
|
| 594 |
+
"learning_rate": 7.147766323024055e-05,
|
| 595 |
+
"loss": 0.0265,
|
| 596 |
+
"step": 980
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 7.92,
|
| 600 |
+
"learning_rate": 7.010309278350515e-05,
|
| 601 |
+
"loss": 0.0282,
|
| 602 |
+
"step": 990
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 8.0,
|
| 606 |
+
"learning_rate": 6.872852233676977e-05,
|
| 607 |
+
"loss": 0.028,
|
| 608 |
+
"step": 1000
|
| 609 |
+
}
|
| 610 |
+
],
|
| 611 |
+
"max_steps": 1500,
|
| 612 |
+
"num_train_epochs": 12,
|
| 613 |
+
"total_flos": 4.91514246463488e+17,
|
| 614 |
+
"trial_name": null,
|
| 615 |
+
"trial_params": null
|
| 616 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ad160e28912f51f22be68ed1e02d4f0e36de2516ceb1b5fcda3e552ec09de74
|
| 3 |
+
size 3963
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|