Farouk
commited on
Commit
·
d4d8edb
1
Parent(s):
7226ac6
Training in progress, step 200
Browse files- adapter_config.json +26 -0
- adapter_model.bin +3 -0
- added_tokens.json +3 -0
- checkpoint-200/README.md +20 -0
- checkpoint-200/adapter_config.json +26 -0
- checkpoint-200/adapter_model.bin +3 -0
- checkpoint-200/added_tokens.json +3 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/special_tokens_map.json +6 -0
- checkpoint-200/tokenizer.model +3 -0
- checkpoint-200/tokenizer_config.json +35 -0
- checkpoint-200/trainer_state.json +1400 -0
- checkpoint-200/training_args.bin +3 -0
- special_tokens_map.json +6 -0
- tokenizer.model +3 -0
- tokenizer_config.json +35 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "NousResearch/Nous-Hermes-llama-2-7b",
|
| 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": 16.0,
|
| 11 |
+
"lora_dropout": 0.4,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 64,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"o_proj",
|
| 18 |
+
"v_proj",
|
| 19 |
+
"k_proj",
|
| 20 |
+
"down_proj",
|
| 21 |
+
"q_proj",
|
| 22 |
+
"up_proj",
|
| 23 |
+
"gate_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8b032b3810215b9d28ca2afcd2782384c578549804194aa90506394ecf2ab91
|
| 3 |
+
size 319977229
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 32000
|
| 3 |
+
}
|
checkpoint-200/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: True
|
| 16 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 17 |
+
### Framework versions
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- PEFT 0.4.0
|
checkpoint-200/adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "NousResearch/Nous-Hermes-llama-2-7b",
|
| 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": 16.0,
|
| 11 |
+
"lora_dropout": 0.4,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 64,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"o_proj",
|
| 18 |
+
"v_proj",
|
| 19 |
+
"k_proj",
|
| 20 |
+
"down_proj",
|
| 21 |
+
"q_proj",
|
| 22 |
+
"up_proj",
|
| 23 |
+
"gate_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
checkpoint-200/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8b032b3810215b9d28ca2afcd2782384c578549804194aa90506394ecf2ab91
|
| 3 |
+
size 319977229
|
checkpoint-200/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 32000
|
| 3 |
+
}
|
checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfce01fde7672e3c085bb1b4adbfb52fe63a39f81037410fe771a9028175dce7
|
| 3 |
+
size 1279539525
|
checkpoint-200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d93c625376e5fc33031fb564b63ea6141dee48d9689edf2b6495666b1a3cefc
|
| 3 |
+
size 14511
|
checkpoint-200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96b7b9232fba96407a35a6869770cdac900992029aec47e58686fed283f85443
|
| 3 |
+
size 627
|
checkpoint-200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<unk>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
checkpoint-200/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<s>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"legacy": false,
|
| 22 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"padding_side": "right",
|
| 25 |
+
"sp_model_kwargs": {},
|
| 26 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 27 |
+
"unk_token": {
|
| 28 |
+
"__type": "AddedToken",
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
}
|
| 35 |
+
}
|
checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,1400 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5244021415710449,
|
| 3 |
+
"best_model_checkpoint": "./output_v2/7b_cluster00_Nous-Hermes-llama-2-7b_codellama_blob_1/checkpoint-200",
|
| 4 |
+
"epoch": 0.5614035087719298,
|
| 5 |
+
"global_step": 200,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 9.999999999999999e-06,
|
| 13 |
+
"loss": 0.7795,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.01,
|
| 18 |
+
"learning_rate": 1.9999999999999998e-05,
|
| 19 |
+
"loss": 0.6789,
|
| 20 |
+
"step": 2
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.01,
|
| 24 |
+
"learning_rate": 2.9999999999999997e-05,
|
| 25 |
+
"loss": 0.6846,
|
| 26 |
+
"step": 3
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.01,
|
| 30 |
+
"learning_rate": 3.9999999999999996e-05,
|
| 31 |
+
"loss": 0.6883,
|
| 32 |
+
"step": 4
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.01,
|
| 36 |
+
"learning_rate": 4.9999999999999996e-05,
|
| 37 |
+
"loss": 0.5963,
|
| 38 |
+
"step": 5
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02,
|
| 42 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 43 |
+
"loss": 0.6577,
|
| 44 |
+
"step": 6
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02,
|
| 48 |
+
"learning_rate": 7e-05,
|
| 49 |
+
"loss": 0.625,
|
| 50 |
+
"step": 7
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.02,
|
| 54 |
+
"learning_rate": 7.999999999999999e-05,
|
| 55 |
+
"loss": 0.6864,
|
| 56 |
+
"step": 8
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.03,
|
| 60 |
+
"learning_rate": 8.999999999999999e-05,
|
| 61 |
+
"loss": 0.5344,
|
| 62 |
+
"step": 9
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.03,
|
| 66 |
+
"learning_rate": 9.999999999999999e-05,
|
| 67 |
+
"loss": 0.5956,
|
| 68 |
+
"step": 10
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.03,
|
| 72 |
+
"learning_rate": 0.00010999999999999998,
|
| 73 |
+
"loss": 0.6993,
|
| 74 |
+
"step": 11
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.03,
|
| 78 |
+
"learning_rate": 0.00011999999999999999,
|
| 79 |
+
"loss": 0.623,
|
| 80 |
+
"step": 12
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.04,
|
| 84 |
+
"learning_rate": 0.00013,
|
| 85 |
+
"loss": 0.5547,
|
| 86 |
+
"step": 13
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.04,
|
| 90 |
+
"learning_rate": 0.00014,
|
| 91 |
+
"loss": 0.5404,
|
| 92 |
+
"step": 14
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.04,
|
| 96 |
+
"learning_rate": 0.00015,
|
| 97 |
+
"loss": 0.5536,
|
| 98 |
+
"step": 15
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.04,
|
| 102 |
+
"learning_rate": 0.00015999999999999999,
|
| 103 |
+
"loss": 0.6886,
|
| 104 |
+
"step": 16
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.05,
|
| 108 |
+
"learning_rate": 0.00016999999999999999,
|
| 109 |
+
"loss": 0.8917,
|
| 110 |
+
"step": 17
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.05,
|
| 114 |
+
"learning_rate": 0.00017999999999999998,
|
| 115 |
+
"loss": 0.6834,
|
| 116 |
+
"step": 18
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.05,
|
| 120 |
+
"learning_rate": 0.00018999999999999998,
|
| 121 |
+
"loss": 0.4784,
|
| 122 |
+
"step": 19
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.06,
|
| 126 |
+
"learning_rate": 0.00019999999999999998,
|
| 127 |
+
"loss": 0.5869,
|
| 128 |
+
"step": 20
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.06,
|
| 132 |
+
"learning_rate": 0.00020999999999999998,
|
| 133 |
+
"loss": 0.9495,
|
| 134 |
+
"step": 21
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.06,
|
| 138 |
+
"learning_rate": 0.00021999999999999995,
|
| 139 |
+
"loss": 0.8727,
|
| 140 |
+
"step": 22
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.06,
|
| 144 |
+
"learning_rate": 0.00023,
|
| 145 |
+
"loss": 0.671,
|
| 146 |
+
"step": 23
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.07,
|
| 150 |
+
"learning_rate": 0.00023999999999999998,
|
| 151 |
+
"loss": 0.6582,
|
| 152 |
+
"step": 24
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.07,
|
| 156 |
+
"learning_rate": 0.00025,
|
| 157 |
+
"loss": 0.6599,
|
| 158 |
+
"step": 25
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.07,
|
| 162 |
+
"eval_loss": 0.6080610752105713,
|
| 163 |
+
"eval_runtime": 26.3081,
|
| 164 |
+
"eval_samples_per_second": 7.602,
|
| 165 |
+
"eval_steps_per_second": 1.901,
|
| 166 |
+
"step": 25
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"dharma_eval_accuracy": 0.45126789906203946,
|
| 170 |
+
"dharma_eval_accuracy_ARC-Challenge": 0.5555555555555556,
|
| 171 |
+
"dharma_eval_accuracy_ARC-Easy": 0.5555555555555556,
|
| 172 |
+
"dharma_eval_accuracy_BoolQ": 0.7037037037037037,
|
| 173 |
+
"dharma_eval_accuracy_MMLU": 0.3888888888888889,
|
| 174 |
+
"dharma_eval_accuracy_agieval": 0.2711864406779661,
|
| 175 |
+
"dharma_eval_accuracy_bigbench": 0.47540983606557374,
|
| 176 |
+
"dharma_eval_accuracy_openbookqa": 0.35185185185185186,
|
| 177 |
+
"dharma_eval_accuracy_truthful_qa": 0.42592592592592593,
|
| 178 |
+
"dharma_eval_accuracy_winogrande": 0.3333333333333333,
|
| 179 |
+
"dharma_loss": 2.3038411536216734,
|
| 180 |
+
"epoch": 0.07,
|
| 181 |
+
"step": 25
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.07,
|
| 185 |
+
"learning_rate": 0.00026,
|
| 186 |
+
"loss": 0.568,
|
| 187 |
+
"step": 26
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.08,
|
| 191 |
+
"learning_rate": 0.00027,
|
| 192 |
+
"loss": 0.569,
|
| 193 |
+
"step": 27
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.08,
|
| 197 |
+
"learning_rate": 0.00028,
|
| 198 |
+
"loss": 0.4481,
|
| 199 |
+
"step": 28
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.08,
|
| 203 |
+
"learning_rate": 0.00029,
|
| 204 |
+
"loss": 0.5482,
|
| 205 |
+
"step": 29
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.08,
|
| 209 |
+
"learning_rate": 0.0003,
|
| 210 |
+
"loss": 0.8189,
|
| 211 |
+
"step": 30
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.09,
|
| 215 |
+
"learning_rate": 0.0002999992132854894,
|
| 216 |
+
"loss": 0.928,
|
| 217 |
+
"step": 31
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.09,
|
| 221 |
+
"learning_rate": 0.0002999968531502098,
|
| 222 |
+
"loss": 0.6567,
|
| 223 |
+
"step": 32
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.09,
|
| 227 |
+
"learning_rate": 0.0002999929196189179,
|
| 228 |
+
"loss": 0.469,
|
| 229 |
+
"step": 33
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.1,
|
| 233 |
+
"learning_rate": 0.00029998741273287477,
|
| 234 |
+
"loss": 0.6043,
|
| 235 |
+
"step": 34
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.1,
|
| 239 |
+
"learning_rate": 0.0002999803325498448,
|
| 240 |
+
"loss": 0.6288,
|
| 241 |
+
"step": 35
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.1,
|
| 245 |
+
"learning_rate": 0.0002999716791440959,
|
| 246 |
+
"loss": 0.6692,
|
| 247 |
+
"step": 36
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.1,
|
| 251 |
+
"learning_rate": 0.00029996145260639806,
|
| 252 |
+
"loss": 0.7591,
|
| 253 |
+
"step": 37
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.11,
|
| 257 |
+
"learning_rate": 0.000299949653044023,
|
| 258 |
+
"loss": 0.5729,
|
| 259 |
+
"step": 38
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.11,
|
| 263 |
+
"learning_rate": 0.00029993628058074245,
|
| 264 |
+
"loss": 0.4347,
|
| 265 |
+
"step": 39
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.11,
|
| 269 |
+
"learning_rate": 0.00029992133535682725,
|
| 270 |
+
"loss": 0.7718,
|
| 271 |
+
"step": 40
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.12,
|
| 275 |
+
"learning_rate": 0.00029990481752904563,
|
| 276 |
+
"loss": 0.7768,
|
| 277 |
+
"step": 41
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.12,
|
| 281 |
+
"learning_rate": 0.0002998867272706619,
|
| 282 |
+
"loss": 0.7359,
|
| 283 |
+
"step": 42
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.12,
|
| 287 |
+
"learning_rate": 0.0002998670647714343,
|
| 288 |
+
"loss": 0.5626,
|
| 289 |
+
"step": 43
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.12,
|
| 293 |
+
"learning_rate": 0.00029984583023761317,
|
| 294 |
+
"loss": 0.5444,
|
| 295 |
+
"step": 44
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.13,
|
| 299 |
+
"learning_rate": 0.00029982302389193856,
|
| 300 |
+
"loss": 0.5487,
|
| 301 |
+
"step": 45
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.13,
|
| 305 |
+
"learning_rate": 0.00029979864597363845,
|
| 306 |
+
"loss": 0.4916,
|
| 307 |
+
"step": 46
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.13,
|
| 311 |
+
"learning_rate": 0.0002997726967384255,
|
| 312 |
+
"loss": 0.4817,
|
| 313 |
+
"step": 47
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.13,
|
| 317 |
+
"learning_rate": 0.00029974517645849503,
|
| 318 |
+
"loss": 0.6375,
|
| 319 |
+
"step": 48
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.14,
|
| 323 |
+
"learning_rate": 0.0002997160854225217,
|
| 324 |
+
"loss": 0.5938,
|
| 325 |
+
"step": 49
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.14,
|
| 329 |
+
"learning_rate": 0.0002996854239356567,
|
| 330 |
+
"loss": 0.5868,
|
| 331 |
+
"step": 50
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.14,
|
| 335 |
+
"eval_loss": 0.5586252212524414,
|
| 336 |
+
"eval_runtime": 26.2488,
|
| 337 |
+
"eval_samples_per_second": 7.619,
|
| 338 |
+
"eval_steps_per_second": 1.905,
|
| 339 |
+
"step": 50
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"dharma_eval_accuracy": 0.4279315127544574,
|
| 343 |
+
"dharma_eval_accuracy_ARC-Challenge": 0.5925925925925926,
|
| 344 |
+
"dharma_eval_accuracy_ARC-Easy": 0.6481481481481481,
|
| 345 |
+
"dharma_eval_accuracy_BoolQ": 0.7037037037037037,
|
| 346 |
+
"dharma_eval_accuracy_MMLU": 0.4074074074074074,
|
| 347 |
+
"dharma_eval_accuracy_agieval": 0.2542372881355932,
|
| 348 |
+
"dharma_eval_accuracy_bigbench": 0.39344262295081966,
|
| 349 |
+
"dharma_eval_accuracy_openbookqa": 0.3148148148148148,
|
| 350 |
+
"dharma_eval_accuracy_truthful_qa": 0.4444444444444444,
|
| 351 |
+
"dharma_eval_accuracy_winogrande": 0.09259259259259259,
|
| 352 |
+
"dharma_loss": 2.1031297972202303,
|
| 353 |
+
"epoch": 0.14,
|
| 354 |
+
"step": 50
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.14,
|
| 358 |
+
"learning_rate": 0.00029965319231952455,
|
| 359 |
+
"loss": 0.612,
|
| 360 |
+
"step": 51
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.15,
|
| 364 |
+
"learning_rate": 0.0002996193909122197,
|
| 365 |
+
"loss": 0.8942,
|
| 366 |
+
"step": 52
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.15,
|
| 370 |
+
"learning_rate": 0.00029958402006830274,
|
| 371 |
+
"loss": 0.5766,
|
| 372 |
+
"step": 53
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.15,
|
| 376 |
+
"learning_rate": 0.0002995470801587973,
|
| 377 |
+
"loss": 0.6238,
|
| 378 |
+
"step": 54
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.15,
|
| 382 |
+
"learning_rate": 0.0002995085715711854,
|
| 383 |
+
"loss": 0.5561,
|
| 384 |
+
"step": 55
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.16,
|
| 388 |
+
"learning_rate": 0.0002994684947094039,
|
| 389 |
+
"loss": 0.6203,
|
| 390 |
+
"step": 56
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.16,
|
| 394 |
+
"learning_rate": 0.0002994268499938403,
|
| 395 |
+
"loss": 0.6534,
|
| 396 |
+
"step": 57
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.16,
|
| 400 |
+
"learning_rate": 0.00029938363786132774,
|
| 401 |
+
"loss": 0.594,
|
| 402 |
+
"step": 58
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.17,
|
| 406 |
+
"learning_rate": 0.00029933885876514115,
|
| 407 |
+
"loss": 0.5608,
|
| 408 |
+
"step": 59
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.17,
|
| 412 |
+
"learning_rate": 0.0002992925131749921,
|
| 413 |
+
"loss": 0.6622,
|
| 414 |
+
"step": 60
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.17,
|
| 418 |
+
"learning_rate": 0.00029924460157702376,
|
| 419 |
+
"loss": 0.5207,
|
| 420 |
+
"step": 61
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.17,
|
| 424 |
+
"learning_rate": 0.00029919512447380625,
|
| 425 |
+
"loss": 0.5308,
|
| 426 |
+
"step": 62
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.18,
|
| 430 |
+
"learning_rate": 0.0002991440823843309,
|
| 431 |
+
"loss": 0.6217,
|
| 432 |
+
"step": 63
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.18,
|
| 436 |
+
"learning_rate": 0.0002990914758440051,
|
| 437 |
+
"loss": 0.6541,
|
| 438 |
+
"step": 64
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.18,
|
| 442 |
+
"learning_rate": 0.00029903730540464666,
|
| 443 |
+
"loss": 0.514,
|
| 444 |
+
"step": 65
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.19,
|
| 448 |
+
"learning_rate": 0.00029898157163447763,
|
| 449 |
+
"loss": 0.5923,
|
| 450 |
+
"step": 66
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.19,
|
| 454 |
+
"learning_rate": 0.0002989242751181191,
|
| 455 |
+
"loss": 0.6156,
|
| 456 |
+
"step": 67
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.19,
|
| 460 |
+
"learning_rate": 0.0002988654164565843,
|
| 461 |
+
"loss": 0.5406,
|
| 462 |
+
"step": 68
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.19,
|
| 466 |
+
"learning_rate": 0.0002988049962672728,
|
| 467 |
+
"loss": 0.4563,
|
| 468 |
+
"step": 69
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 0.2,
|
| 472 |
+
"learning_rate": 0.00029874301518396376,
|
| 473 |
+
"loss": 0.5448,
|
| 474 |
+
"step": 70
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.2,
|
| 478 |
+
"learning_rate": 0.00029867947385680936,
|
| 479 |
+
"loss": 0.6164,
|
| 480 |
+
"step": 71
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.2,
|
| 484 |
+
"learning_rate": 0.0002986143729523282,
|
| 485 |
+
"loss": 0.5636,
|
| 486 |
+
"step": 72
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.2,
|
| 490 |
+
"learning_rate": 0.00029854771315339785,
|
| 491 |
+
"loss": 0.5301,
|
| 492 |
+
"step": 73
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.21,
|
| 496 |
+
"learning_rate": 0.00029847949515924806,
|
| 497 |
+
"loss": 0.6074,
|
| 498 |
+
"step": 74
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.21,
|
| 502 |
+
"learning_rate": 0.0002984097196854534,
|
| 503 |
+
"loss": 0.5123,
|
| 504 |
+
"step": 75
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.21,
|
| 508 |
+
"eval_loss": 0.541282057762146,
|
| 509 |
+
"eval_runtime": 26.1496,
|
| 510 |
+
"eval_samples_per_second": 7.648,
|
| 511 |
+
"eval_steps_per_second": 1.912,
|
| 512 |
+
"step": 75
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"dharma_eval_accuracy": 0.4466804336366869,
|
| 516 |
+
"dharma_eval_accuracy_ARC-Challenge": 0.6296296296296297,
|
| 517 |
+
"dharma_eval_accuracy_ARC-Easy": 0.5740740740740741,
|
| 518 |
+
"dharma_eval_accuracy_BoolQ": 0.7037037037037037,
|
| 519 |
+
"dharma_eval_accuracy_MMLU": 0.4074074074074074,
|
| 520 |
+
"dharma_eval_accuracy_agieval": 0.2711864406779661,
|
| 521 |
+
"dharma_eval_accuracy_bigbench": 0.5081967213114754,
|
| 522 |
+
"dharma_eval_accuracy_openbookqa": 0.12962962962962962,
|
| 523 |
+
"dharma_eval_accuracy_truthful_qa": 0.4074074074074074,
|
| 524 |
+
"dharma_eval_accuracy_winogrande": 0.3888888888888889,
|
| 525 |
+
"dharma_loss": 2.2732545466423035,
|
| 526 |
+
"epoch": 0.21,
|
| 527 |
+
"step": 75
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.21,
|
| 531 |
+
"learning_rate": 0.0002983383874639254,
|
| 532 |
+
"loss": 0.5206,
|
| 533 |
+
"step": 76
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.22,
|
| 537 |
+
"learning_rate": 0.00029826549924290557,
|
| 538 |
+
"loss": 0.6452,
|
| 539 |
+
"step": 77
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.22,
|
| 543 |
+
"learning_rate": 0.00029819105578695655,
|
| 544 |
+
"loss": 0.6085,
|
| 545 |
+
"step": 78
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.22,
|
| 549 |
+
"learning_rate": 0.00029811505787695524,
|
| 550 |
+
"loss": 0.5163,
|
| 551 |
+
"step": 79
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.22,
|
| 555 |
+
"learning_rate": 0.00029803750631008356,
|
| 556 |
+
"loss": 0.5511,
|
| 557 |
+
"step": 80
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.23,
|
| 561 |
+
"learning_rate": 0.0002979584018998209,
|
| 562 |
+
"loss": 0.6395,
|
| 563 |
+
"step": 81
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.23,
|
| 567 |
+
"learning_rate": 0.000297877745475935,
|
| 568 |
+
"loss": 0.6281,
|
| 569 |
+
"step": 82
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.23,
|
| 573 |
+
"learning_rate": 0.00029779553788447357,
|
| 574 |
+
"loss": 0.4932,
|
| 575 |
+
"step": 83
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.24,
|
| 579 |
+
"learning_rate": 0.00029771177998775536,
|
| 580 |
+
"loss": 0.5497,
|
| 581 |
+
"step": 84
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.24,
|
| 585 |
+
"learning_rate": 0.0002976264726643611,
|
| 586 |
+
"loss": 0.5496,
|
| 587 |
+
"step": 85
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.24,
|
| 591 |
+
"learning_rate": 0.00029753961680912427,
|
| 592 |
+
"loss": 0.4569,
|
| 593 |
+
"step": 86
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.24,
|
| 597 |
+
"learning_rate": 0.00029745121333312163,
|
| 598 |
+
"loss": 0.5152,
|
| 599 |
+
"step": 87
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.25,
|
| 603 |
+
"learning_rate": 0.0002973612631636638,
|
| 604 |
+
"loss": 0.6928,
|
| 605 |
+
"step": 88
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.25,
|
| 609 |
+
"learning_rate": 0.0002972697672442856,
|
| 610 |
+
"loss": 0.5503,
|
| 611 |
+
"step": 89
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.25,
|
| 615 |
+
"learning_rate": 0.0002971767265347358,
|
| 616 |
+
"loss": 0.7074,
|
| 617 |
+
"step": 90
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.26,
|
| 621 |
+
"learning_rate": 0.00029708214201096755,
|
| 622 |
+
"loss": 0.6397,
|
| 623 |
+
"step": 91
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.26,
|
| 627 |
+
"learning_rate": 0.0002969860146651276,
|
| 628 |
+
"loss": 0.7815,
|
| 629 |
+
"step": 92
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.26,
|
| 633 |
+
"learning_rate": 0.00029688834550554646,
|
| 634 |
+
"loss": 0.6274,
|
| 635 |
+
"step": 93
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.26,
|
| 639 |
+
"learning_rate": 0.0002967891355567273,
|
| 640 |
+
"loss": 0.6196,
|
| 641 |
+
"step": 94
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.27,
|
| 645 |
+
"learning_rate": 0.00029668838585933556,
|
| 646 |
+
"loss": 0.5845,
|
| 647 |
+
"step": 95
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.27,
|
| 651 |
+
"learning_rate": 0.0002965860974701879,
|
| 652 |
+
"loss": 0.5934,
|
| 653 |
+
"step": 96
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.27,
|
| 657 |
+
"learning_rate": 0.0002964822714622412,
|
| 658 |
+
"loss": 0.6277,
|
| 659 |
+
"step": 97
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.28,
|
| 663 |
+
"learning_rate": 0.000296376908924581,
|
| 664 |
+
"loss": 0.555,
|
| 665 |
+
"step": 98
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.28,
|
| 669 |
+
"learning_rate": 0.00029627001096241057,
|
| 670 |
+
"loss": 0.5478,
|
| 671 |
+
"step": 99
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.28,
|
| 675 |
+
"learning_rate": 0.0002961615786970389,
|
| 676 |
+
"loss": 0.6851,
|
| 677 |
+
"step": 100
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.28,
|
| 681 |
+
"eval_loss": 0.5322936177253723,
|
| 682 |
+
"eval_runtime": 26.2408,
|
| 683 |
+
"eval_samples_per_second": 7.622,
|
| 684 |
+
"eval_steps_per_second": 1.905,
|
| 685 |
+
"step": 100
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"dharma_eval_accuracy": 0.3837211296690781,
|
| 689 |
+
"dharma_eval_accuracy_ARC-Challenge": 0.6296296296296297,
|
| 690 |
+
"dharma_eval_accuracy_ARC-Easy": 0.5925925925925926,
|
| 691 |
+
"dharma_eval_accuracy_BoolQ": 0.7037037037037037,
|
| 692 |
+
"dharma_eval_accuracy_MMLU": 0.4444444444444444,
|
| 693 |
+
"dharma_eval_accuracy_agieval": 0.22033898305084745,
|
| 694 |
+
"dharma_eval_accuracy_bigbench": 0.3442622950819672,
|
| 695 |
+
"dharma_eval_accuracy_openbookqa": 0.09259259259259259,
|
| 696 |
+
"dharma_eval_accuracy_truthful_qa": 0.2777777777777778,
|
| 697 |
+
"dharma_eval_accuracy_winogrande": 0.14814814814814814,
|
| 698 |
+
"dharma_loss": 2.1400452837944033,
|
| 699 |
+
"epoch": 0.28,
|
| 700 |
+
"step": 100
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 0.28,
|
| 704 |
+
"learning_rate": 0.00029605161326586916,
|
| 705 |
+
"loss": 0.5637,
|
| 706 |
+
"step": 101
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.29,
|
| 710 |
+
"learning_rate": 0.0002959401158223867,
|
| 711 |
+
"loss": 0.5563,
|
| 712 |
+
"step": 102
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.29,
|
| 716 |
+
"learning_rate": 0.0002958270875361469,
|
| 717 |
+
"loss": 0.7583,
|
| 718 |
+
"step": 103
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.29,
|
| 722 |
+
"learning_rate": 0.0002957125295927631,
|
| 723 |
+
"loss": 0.4775,
|
| 724 |
+
"step": 104
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.29,
|
| 728 |
+
"learning_rate": 0.0002955964431938939,
|
| 729 |
+
"loss": 0.6912,
|
| 730 |
+
"step": 105
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.3,
|
| 734 |
+
"learning_rate": 0.0002954788295572305,
|
| 735 |
+
"loss": 0.7142,
|
| 736 |
+
"step": 106
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.3,
|
| 740 |
+
"learning_rate": 0.00029535968991648454,
|
| 741 |
+
"loss": 0.5264,
|
| 742 |
+
"step": 107
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 0.3,
|
| 746 |
+
"learning_rate": 0.00029523902552137433,
|
| 747 |
+
"loss": 0.509,
|
| 748 |
+
"step": 108
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.31,
|
| 752 |
+
"learning_rate": 0.0002951168376376124,
|
| 753 |
+
"loss": 0.7375,
|
| 754 |
+
"step": 109
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.31,
|
| 758 |
+
"learning_rate": 0.0002949931275468917,
|
| 759 |
+
"loss": 0.4407,
|
| 760 |
+
"step": 110
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.31,
|
| 764 |
+
"learning_rate": 0.00029486789654687253,
|
| 765 |
+
"loss": 0.5361,
|
| 766 |
+
"step": 111
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.31,
|
| 770 |
+
"learning_rate": 0.00029474114595116896,
|
| 771 |
+
"loss": 0.6161,
|
| 772 |
+
"step": 112
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.32,
|
| 776 |
+
"learning_rate": 0.00029461287708933473,
|
| 777 |
+
"loss": 0.589,
|
| 778 |
+
"step": 113
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.32,
|
| 782 |
+
"learning_rate": 0.0002944830913068494,
|
| 783 |
+
"loss": 0.5677,
|
| 784 |
+
"step": 114
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.32,
|
| 788 |
+
"learning_rate": 0.00029435178996510455,
|
| 789 |
+
"loss": 0.5946,
|
| 790 |
+
"step": 115
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.33,
|
| 794 |
+
"learning_rate": 0.00029421897444138897,
|
| 795 |
+
"loss": 0.526,
|
| 796 |
+
"step": 116
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.33,
|
| 800 |
+
"learning_rate": 0.0002940846461288748,
|
| 801 |
+
"loss": 0.8164,
|
| 802 |
+
"step": 117
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.33,
|
| 806 |
+
"learning_rate": 0.0002939488064366024,
|
| 807 |
+
"loss": 0.6519,
|
| 808 |
+
"step": 118
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.33,
|
| 812 |
+
"learning_rate": 0.00029381145678946584,
|
| 813 |
+
"loss": 0.6519,
|
| 814 |
+
"step": 119
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.34,
|
| 818 |
+
"learning_rate": 0.00029367259862819804,
|
| 819 |
+
"loss": 0.7479,
|
| 820 |
+
"step": 120
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 0.34,
|
| 824 |
+
"learning_rate": 0.0002935322334093553,
|
| 825 |
+
"loss": 0.5756,
|
| 826 |
+
"step": 121
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.34,
|
| 830 |
+
"learning_rate": 0.0002933903626053024,
|
| 831 |
+
"loss": 0.3582,
|
| 832 |
+
"step": 122
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.35,
|
| 836 |
+
"learning_rate": 0.00029324698770419685,
|
| 837 |
+
"loss": 0.5282,
|
| 838 |
+
"step": 123
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.35,
|
| 842 |
+
"learning_rate": 0.0002931021102099737,
|
| 843 |
+
"loss": 0.5435,
|
| 844 |
+
"step": 124
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.35,
|
| 848 |
+
"learning_rate": 0.0002929557316423291,
|
| 849 |
+
"loss": 0.7049,
|
| 850 |
+
"step": 125
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.35,
|
| 854 |
+
"eval_loss": 0.539155125617981,
|
| 855 |
+
"eval_runtime": 26.1963,
|
| 856 |
+
"eval_samples_per_second": 7.635,
|
| 857 |
+
"eval_steps_per_second": 1.909,
|
| 858 |
+
"step": 125
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"dharma_eval_accuracy": 0.25951081518986185,
|
| 862 |
+
"dharma_eval_accuracy_ARC-Challenge": 0.42592592592592593,
|
| 863 |
+
"dharma_eval_accuracy_ARC-Easy": 0.46296296296296297,
|
| 864 |
+
"dharma_eval_accuracy_BoolQ": 0.1111111111111111,
|
| 865 |
+
"dharma_eval_accuracy_MMLU": 0.4074074074074074,
|
| 866 |
+
"dharma_eval_accuracy_agieval": 0.2542372881355932,
|
| 867 |
+
"dharma_eval_accuracy_bigbench": 0.22950819672131148,
|
| 868 |
+
"dharma_eval_accuracy_openbookqa": 0.14814814814814814,
|
| 869 |
+
"dharma_eval_accuracy_truthful_qa": 0.2962962962962963,
|
| 870 |
+
"dharma_eval_accuracy_winogrande": 0.0,
|
| 871 |
+
"dharma_loss": 2.083115490436554,
|
| 872 |
+
"epoch": 0.35,
|
| 873 |
+
"step": 125
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.35,
|
| 877 |
+
"learning_rate": 0.00029280785353670514,
|
| 878 |
+
"loss": 0.5792,
|
| 879 |
+
"step": 126
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.36,
|
| 883 |
+
"learning_rate": 0.00029265847744427303,
|
| 884 |
+
"loss": 0.8134,
|
| 885 |
+
"step": 127
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.36,
|
| 889 |
+
"learning_rate": 0.00029250760493191734,
|
| 890 |
+
"loss": 0.6023,
|
| 891 |
+
"step": 128
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.36,
|
| 895 |
+
"learning_rate": 0.0002923552375822194,
|
| 896 |
+
"loss": 0.6515,
|
| 897 |
+
"step": 129
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.36,
|
| 901 |
+
"learning_rate": 0.00029220137699344055,
|
| 902 |
+
"loss": 0.7513,
|
| 903 |
+
"step": 130
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.37,
|
| 907 |
+
"learning_rate": 0.00029204602477950556,
|
| 908 |
+
"loss": 0.6878,
|
| 909 |
+
"step": 131
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.37,
|
| 913 |
+
"learning_rate": 0.00029188918256998564,
|
| 914 |
+
"loss": 0.4415,
|
| 915 |
+
"step": 132
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.37,
|
| 919 |
+
"learning_rate": 0.0002917308520100814,
|
| 920 |
+
"loss": 0.5476,
|
| 921 |
+
"step": 133
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.38,
|
| 925 |
+
"learning_rate": 0.00029157103476060544,
|
| 926 |
+
"loss": 0.5394,
|
| 927 |
+
"step": 134
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.38,
|
| 931 |
+
"learning_rate": 0.0002914097324979651,
|
| 932 |
+
"loss": 0.4909,
|
| 933 |
+
"step": 135
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.38,
|
| 937 |
+
"learning_rate": 0.0002912469469141448,
|
| 938 |
+
"loss": 0.4633,
|
| 939 |
+
"step": 136
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.38,
|
| 943 |
+
"learning_rate": 0.0002910826797166882,
|
| 944 |
+
"loss": 0.6073,
|
| 945 |
+
"step": 137
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.39,
|
| 949 |
+
"learning_rate": 0.00029091693262868067,
|
| 950 |
+
"loss": 0.7209,
|
| 951 |
+
"step": 138
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.39,
|
| 955 |
+
"learning_rate": 0.0002907497073887305,
|
| 956 |
+
"loss": 0.6085,
|
| 957 |
+
"step": 139
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.39,
|
| 961 |
+
"learning_rate": 0.0002905810057509515,
|
| 962 |
+
"loss": 0.7864,
|
| 963 |
+
"step": 140
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.4,
|
| 967 |
+
"learning_rate": 0.00029041082948494395,
|
| 968 |
+
"loss": 0.5827,
|
| 969 |
+
"step": 141
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.4,
|
| 973 |
+
"learning_rate": 0.00029023918037577635,
|
| 974 |
+
"loss": 0.5981,
|
| 975 |
+
"step": 142
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.4,
|
| 979 |
+
"learning_rate": 0.00029006606022396667,
|
| 980 |
+
"loss": 0.5293,
|
| 981 |
+
"step": 143
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.4,
|
| 985 |
+
"learning_rate": 0.00028989147084546333,
|
| 986 |
+
"loss": 0.7339,
|
| 987 |
+
"step": 144
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.41,
|
| 991 |
+
"learning_rate": 0.00028971541407162634,
|
| 992 |
+
"loss": 0.6057,
|
| 993 |
+
"step": 145
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.41,
|
| 997 |
+
"learning_rate": 0.0002895378917492079,
|
| 998 |
+
"loss": 0.5364,
|
| 999 |
+
"step": 146
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.41,
|
| 1003 |
+
"learning_rate": 0.0002893589057403332,
|
| 1004 |
+
"loss": 0.5716,
|
| 1005 |
+
"step": 147
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.42,
|
| 1009 |
+
"learning_rate": 0.0002891784579224808,
|
| 1010 |
+
"loss": 1.1362,
|
| 1011 |
+
"step": 148
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.42,
|
| 1015 |
+
"learning_rate": 0.00028899655018846295,
|
| 1016 |
+
"loss": 0.5743,
|
| 1017 |
+
"step": 149
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.42,
|
| 1021 |
+
"learning_rate": 0.0002888131844464056,
|
| 1022 |
+
"loss": 0.5567,
|
| 1023 |
+
"step": 150
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.42,
|
| 1027 |
+
"eval_loss": 0.5322738885879517,
|
| 1028 |
+
"eval_runtime": 26.2089,
|
| 1029 |
+
"eval_samples_per_second": 7.631,
|
| 1030 |
+
"eval_steps_per_second": 1.908,
|
| 1031 |
+
"step": 150
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"dharma_eval_accuracy": 0.38818510400122574,
|
| 1035 |
+
"dharma_eval_accuracy_ARC-Challenge": 0.4074074074074074,
|
| 1036 |
+
"dharma_eval_accuracy_ARC-Easy": 0.46296296296296297,
|
| 1037 |
+
"dharma_eval_accuracy_BoolQ": 0.7037037037037037,
|
| 1038 |
+
"dharma_eval_accuracy_MMLU": 0.37037037037037035,
|
| 1039 |
+
"dharma_eval_accuracy_agieval": 0.1864406779661017,
|
| 1040 |
+
"dharma_eval_accuracy_bigbench": 0.3442622950819672,
|
| 1041 |
+
"dharma_eval_accuracy_openbookqa": 0.2037037037037037,
|
| 1042 |
+
"dharma_eval_accuracy_truthful_qa": 0.4074074074074074,
|
| 1043 |
+
"dharma_eval_accuracy_winogrande": 0.4074074074074074,
|
| 1044 |
+
"dharma_loss": 2.3776819763183594,
|
| 1045 |
+
"epoch": 0.42,
|
| 1046 |
+
"step": 150
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.42,
|
| 1050 |
+
"learning_rate": 0.0002886283626197287,
|
| 1051 |
+
"loss": 0.6541,
|
| 1052 |
+
"step": 151
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.43,
|
| 1056 |
+
"learning_rate": 0.00028844208664712575,
|
| 1057 |
+
"loss": 0.4995,
|
| 1058 |
+
"step": 152
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.43,
|
| 1062 |
+
"learning_rate": 0.0002882543584825435,
|
| 1063 |
+
"loss": 0.4582,
|
| 1064 |
+
"step": 153
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.43,
|
| 1068 |
+
"learning_rate": 0.00028806518009516155,
|
| 1069 |
+
"loss": 0.7142,
|
| 1070 |
+
"step": 154
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 0.44,
|
| 1074 |
+
"learning_rate": 0.0002878745534693718,
|
| 1075 |
+
"loss": 0.5899,
|
| 1076 |
+
"step": 155
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.44,
|
| 1080 |
+
"learning_rate": 0.00028768248060475726,
|
| 1081 |
+
"loss": 0.4097,
|
| 1082 |
+
"step": 156
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.44,
|
| 1086 |
+
"learning_rate": 0.0002874889635160714,
|
| 1087 |
+
"loss": 0.5437,
|
| 1088 |
+
"step": 157
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.44,
|
| 1092 |
+
"learning_rate": 0.0002872940042332169,
|
| 1093 |
+
"loss": 0.5694,
|
| 1094 |
+
"step": 158
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.45,
|
| 1098 |
+
"learning_rate": 0.0002870976048012244,
|
| 1099 |
+
"loss": 0.5558,
|
| 1100 |
+
"step": 159
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 0.45,
|
| 1104 |
+
"learning_rate": 0.000286899767280231,
|
| 1105 |
+
"loss": 0.6174,
|
| 1106 |
+
"step": 160
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.45,
|
| 1110 |
+
"learning_rate": 0.0002867004937454587,
|
| 1111 |
+
"loss": 0.4809,
|
| 1112 |
+
"step": 161
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.45,
|
| 1116 |
+
"learning_rate": 0.00028649978628719254,
|
| 1117 |
+
"loss": 0.7249,
|
| 1118 |
+
"step": 162
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.46,
|
| 1122 |
+
"learning_rate": 0.00028629764701075885,
|
| 1123 |
+
"loss": 0.5729,
|
| 1124 |
+
"step": 163
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 0.46,
|
| 1128 |
+
"learning_rate": 0.0002860940780365029,
|
| 1129 |
+
"loss": 0.3942,
|
| 1130 |
+
"step": 164
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.46,
|
| 1134 |
+
"learning_rate": 0.000285889081499767,
|
| 1135 |
+
"loss": 0.62,
|
| 1136 |
+
"step": 165
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.47,
|
| 1140 |
+
"learning_rate": 0.00028568265955086774,
|
| 1141 |
+
"loss": 0.6196,
|
| 1142 |
+
"step": 166
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 0.47,
|
| 1146 |
+
"learning_rate": 0.0002854748143550738,
|
| 1147 |
+
"loss": 0.4698,
|
| 1148 |
+
"step": 167
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 0.47,
|
| 1152 |
+
"learning_rate": 0.00028526554809258275,
|
| 1153 |
+
"loss": 0.53,
|
| 1154 |
+
"step": 168
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.47,
|
| 1158 |
+
"learning_rate": 0.0002850548629584988,
|
| 1159 |
+
"loss": 0.6017,
|
| 1160 |
+
"step": 169
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.48,
|
| 1164 |
+
"learning_rate": 0.00028484276116280926,
|
| 1165 |
+
"loss": 0.5452,
|
| 1166 |
+
"step": 170
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 0.48,
|
| 1170 |
+
"learning_rate": 0.00028462924493036164,
|
| 1171 |
+
"loss": 0.5359,
|
| 1172 |
+
"step": 171
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.48,
|
| 1176 |
+
"learning_rate": 0.00028441431650084016,
|
| 1177 |
+
"loss": 0.4914,
|
| 1178 |
+
"step": 172
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.49,
|
| 1182 |
+
"learning_rate": 0.00028419797812874237,
|
| 1183 |
+
"loss": 0.44,
|
| 1184 |
+
"step": 173
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 0.49,
|
| 1188 |
+
"learning_rate": 0.00028398023208335533,
|
| 1189 |
+
"loss": 0.4378,
|
| 1190 |
+
"step": 174
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 0.49,
|
| 1194 |
+
"learning_rate": 0.00028376108064873215,
|
| 1195 |
+
"loss": 0.5328,
|
| 1196 |
+
"step": 175
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.49,
|
| 1200 |
+
"eval_loss": 0.5265315771102905,
|
| 1201 |
+
"eval_runtime": 26.1903,
|
| 1202 |
+
"eval_samples_per_second": 7.636,
|
| 1203 |
+
"eval_steps_per_second": 1.909,
|
| 1204 |
+
"step": 175
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"dharma_eval_accuracy": 0.35997424982019466,
|
| 1208 |
+
"dharma_eval_accuracy_ARC-Challenge": 0.4444444444444444,
|
| 1209 |
+
"dharma_eval_accuracy_ARC-Easy": 0.5185185185185185,
|
| 1210 |
+
"dharma_eval_accuracy_BoolQ": 0.5925925925925926,
|
| 1211 |
+
"dharma_eval_accuracy_MMLU": 0.3888888888888889,
|
| 1212 |
+
"dharma_eval_accuracy_agieval": 0.22033898305084745,
|
| 1213 |
+
"dharma_eval_accuracy_bigbench": 0.2786885245901639,
|
| 1214 |
+
"dharma_eval_accuracy_openbookqa": 0.1111111111111111,
|
| 1215 |
+
"dharma_eval_accuracy_truthful_qa": 0.3333333333333333,
|
| 1216 |
+
"dharma_eval_accuracy_winogrande": 0.35185185185185186,
|
| 1217 |
+
"dharma_loss": 2.2151358013153075,
|
| 1218 |
+
"epoch": 0.49,
|
| 1219 |
+
"step": 175
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 0.49,
|
| 1223 |
+
"learning_rate": 0.00028354052612366757,
|
| 1224 |
+
"loss": 0.7281,
|
| 1225 |
+
"step": 176
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 0.5,
|
| 1229 |
+
"learning_rate": 0.0002833185708216743,
|
| 1230 |
+
"loss": 0.6805,
|
| 1231 |
+
"step": 177
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.5,
|
| 1235 |
+
"learning_rate": 0.0002830952170709583,
|
| 1236 |
+
"loss": 0.5105,
|
| 1237 |
+
"step": 178
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 0.5,
|
| 1241 |
+
"learning_rate": 0.00028287046721439484,
|
| 1242 |
+
"loss": 0.565,
|
| 1243 |
+
"step": 179
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.51,
|
| 1247 |
+
"learning_rate": 0.00028264432360950353,
|
| 1248 |
+
"loss": 0.6562,
|
| 1249 |
+
"step": 180
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.51,
|
| 1253 |
+
"learning_rate": 0.0002824167886284237,
|
| 1254 |
+
"loss": 0.4868,
|
| 1255 |
+
"step": 181
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.51,
|
| 1259 |
+
"learning_rate": 0.0002821878646578898,
|
| 1260 |
+
"loss": 0.722,
|
| 1261 |
+
"step": 182
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 0.51,
|
| 1265 |
+
"learning_rate": 0.0002819575540992058,
|
| 1266 |
+
"loss": 0.6236,
|
| 1267 |
+
"step": 183
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 0.52,
|
| 1271 |
+
"learning_rate": 0.00028172585936822055,
|
| 1272 |
+
"loss": 0.6328,
|
| 1273 |
+
"step": 184
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.52,
|
| 1277 |
+
"learning_rate": 0.00028149278289530213,
|
| 1278 |
+
"loss": 0.5526,
|
| 1279 |
+
"step": 185
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.52,
|
| 1283 |
+
"learning_rate": 0.00028125832712531246,
|
| 1284 |
+
"loss": 0.6678,
|
| 1285 |
+
"step": 186
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 0.52,
|
| 1289 |
+
"learning_rate": 0.0002810224945175816,
|
| 1290 |
+
"loss": 0.6193,
|
| 1291 |
+
"step": 187
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.53,
|
| 1295 |
+
"learning_rate": 0.00028078528754588205,
|
| 1296 |
+
"loss": 0.5589,
|
| 1297 |
+
"step": 188
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.53,
|
| 1301 |
+
"learning_rate": 0.00028054670869840265,
|
| 1302 |
+
"loss": 0.5679,
|
| 1303 |
+
"step": 189
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 0.53,
|
| 1307 |
+
"learning_rate": 0.00028030676047772265,
|
| 1308 |
+
"loss": 0.4394,
|
| 1309 |
+
"step": 190
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 0.54,
|
| 1313 |
+
"learning_rate": 0.00028006544540078534,
|
| 1314 |
+
"loss": 0.7148,
|
| 1315 |
+
"step": 191
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.54,
|
| 1319 |
+
"learning_rate": 0.0002798227659988717,
|
| 1320 |
+
"loss": 0.7248,
|
| 1321 |
+
"step": 192
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.54,
|
| 1325 |
+
"learning_rate": 0.00027957872481757374,
|
| 1326 |
+
"loss": 0.6304,
|
| 1327 |
+
"step": 193
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 0.54,
|
| 1331 |
+
"learning_rate": 0.00027933332441676807,
|
| 1332 |
+
"loss": 0.5778,
|
| 1333 |
+
"step": 194
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.55,
|
| 1337 |
+
"learning_rate": 0.0002790865673705888,
|
| 1338 |
+
"loss": 0.4473,
|
| 1339 |
+
"step": 195
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.55,
|
| 1343 |
+
"learning_rate": 0.00027883845626740044,
|
| 1344 |
+
"loss": 0.5202,
|
| 1345 |
+
"step": 196
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 0.55,
|
| 1349 |
+
"learning_rate": 0.0002785889937097712,
|
| 1350 |
+
"loss": 0.4966,
|
| 1351 |
+
"step": 197
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 0.56,
|
| 1355 |
+
"learning_rate": 0.00027833818231444516,
|
| 1356 |
+
"loss": 0.6239,
|
| 1357 |
+
"step": 198
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.56,
|
| 1361 |
+
"learning_rate": 0.00027808602471231524,
|
| 1362 |
+
"loss": 0.5887,
|
| 1363 |
+
"step": 199
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 0.56,
|
| 1367 |
+
"learning_rate": 0.0002778325235483954,
|
| 1368 |
+
"loss": 0.5363,
|
| 1369 |
+
"step": 200
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 0.56,
|
| 1373 |
+
"eval_loss": 0.5244021415710449,
|
| 1374 |
+
"eval_runtime": 26.2022,
|
| 1375 |
+
"eval_samples_per_second": 7.633,
|
| 1376 |
+
"eval_steps_per_second": 1.908,
|
| 1377 |
+
"step": 200
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"dharma_eval_accuracy": 0.4286398713863134,
|
| 1381 |
+
"dharma_eval_accuracy_ARC-Challenge": 0.5185185185185185,
|
| 1382 |
+
"dharma_eval_accuracy_ARC-Easy": 0.5370370370370371,
|
| 1383 |
+
"dharma_eval_accuracy_BoolQ": 0.7777777777777778,
|
| 1384 |
+
"dharma_eval_accuracy_MMLU": 0.3888888888888889,
|
| 1385 |
+
"dharma_eval_accuracy_agieval": 0.2542372881355932,
|
| 1386 |
+
"dharma_eval_accuracy_bigbench": 0.3442622950819672,
|
| 1387 |
+
"dharma_eval_accuracy_openbookqa": 0.1111111111111111,
|
| 1388 |
+
"dharma_eval_accuracy_truthful_qa": 0.4444444444444444,
|
| 1389 |
+
"dharma_eval_accuracy_winogrande": 0.48148148148148145,
|
| 1390 |
+
"dharma_loss": 2.3920813593864443,
|
| 1391 |
+
"epoch": 0.56,
|
| 1392 |
+
"step": 200
|
| 1393 |
+
}
|
| 1394 |
+
],
|
| 1395 |
+
"max_steps": 1000,
|
| 1396 |
+
"num_train_epochs": 3,
|
| 1397 |
+
"total_flos": 6.277915233887846e+16,
|
| 1398 |
+
"trial_name": null,
|
| 1399 |
+
"trial_params": null
|
| 1400 |
+
}
|
checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d82b859a9cd8d6d889fcf83059a0117f69472b64660a7ed0075051324482a44
|
| 3 |
+
size 5947
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<unk>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<s>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"legacy": false,
|
| 22 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"padding_side": "right",
|
| 25 |
+
"sp_model_kwargs": {},
|
| 26 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 27 |
+
"unk_token": {
|
| 28 |
+
"__type": "AddedToken",
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
}
|
| 35 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d82b859a9cd8d6d889fcf83059a0117f69472b64660a7ed0075051324482a44
|
| 3 |
+
size 5947
|