Commit
•
9a55e3f
1
Parent(s):
3a47222
Training in progress, step 18000
Browse files- adapter_config.json +5 -5
- adapter_model.bin +1 -1
- checkpoint-18000/README.md +20 -0
- checkpoint-18000/adapter_config.json +26 -0
- checkpoint-18000/adapter_model.bin +3 -0
- checkpoint-18000/optimizer.pt +3 -0
- checkpoint-18000/rng_state.pth +3 -0
- checkpoint-18000/scheduler.pt +3 -0
- checkpoint-18000/trainer_state.json +1240 -0
- checkpoint-18000/training_args.bin +3 -0
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -14,13 +14,13 @@
|
|
| 14 |
"r": 32,
|
| 15 |
"revision": null,
|
| 16 |
"target_modules": [
|
| 17 |
-
"v_proj",
|
| 18 |
-
"o_proj",
|
| 19 |
-
"gate_proj",
|
| 20 |
-
"k_proj",
|
| 21 |
"up_proj",
|
| 22 |
"down_proj",
|
| 23 |
-
"q_proj"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
],
|
| 25 |
"task_type": "CAUSAL_LM"
|
| 26 |
}
|
|
|
|
| 14 |
"r": 32,
|
| 15 |
"revision": null,
|
| 16 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"up_proj",
|
| 18 |
"down_proj",
|
| 19 |
+
"q_proj",
|
| 20 |
+
"v_proj",
|
| 21 |
+
"k_proj",
|
| 22 |
+
"gate_proj",
|
| 23 |
+
"o_proj"
|
| 24 |
],
|
| 25 |
"task_type": "CAUSAL_LM"
|
| 26 |
}
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 500897101
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71bf449473329db623c9e20b261816375a55b691f04f413c33c16578f715c541
|
| 3 |
size 500897101
|
checkpoint-18000/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 0.5.0.dev0
|
checkpoint-18000/adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "/workspace/webui/models/TheBloke_Llama-2-13B-fp16",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": null,
|
| 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": 32,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"up_proj",
|
| 18 |
+
"down_proj",
|
| 19 |
+
"q_proj",
|
| 20 |
+
"v_proj",
|
| 21 |
+
"k_proj",
|
| 22 |
+
"gate_proj",
|
| 23 |
+
"o_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
checkpoint-18000/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71bf449473329db623c9e20b261816375a55b691f04f413c33c16578f715c541
|
| 3 |
+
size 500897101
|
checkpoint-18000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26df0d8c29c8387b0078001ba77499ae2c7e3c93bf63ba77b6e9f6e5d426a377
|
| 3 |
+
size 1001723453
|
checkpoint-18000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d53dc571c7357590eb279d921d2c025244bb82d035e40e44f08a12815eec53c
|
| 3 |
+
size 14575
|
checkpoint-18000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b78dacfd488ca08dbc1fe1369dc6869b6315793fbe6735fa309357590127c966
|
| 3 |
+
size 627
|
checkpoint-18000/trainer_state.json
ADDED
|
@@ -0,0 +1,1240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6444052457809448,
|
| 3 |
+
"best_model_checkpoint": "./qlora-out/checkpoint-18000",
|
| 4 |
+
"epoch": 0.6711159166324895,
|
| 5 |
+
"global_step": 18000,
|
| 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": 0.00019999938245325715,
|
| 13 |
+
"loss": 0.9023,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.01,
|
| 18 |
+
"learning_rate": 0.00019999724773356797,
|
| 19 |
+
"loss": 0.8027,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.01,
|
| 24 |
+
"learning_rate": 0.0001999935882494411,
|
| 25 |
+
"loss": 0.8041,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.01,
|
| 30 |
+
"learning_rate": 0.00019998840405667672,
|
| 31 |
+
"loss": 0.7944,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.02,
|
| 36 |
+
"learning_rate": 0.00019998169523432365,
|
| 37 |
+
"loss": 0.81,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02,
|
| 42 |
+
"learning_rate": 0.0001999734618846785,
|
| 43 |
+
"loss": 0.7855,
|
| 44 |
+
"step": 600
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.03,
|
| 48 |
+
"learning_rate": 0.00019996370413328385,
|
| 49 |
+
"loss": 0.7849,
|
| 50 |
+
"step": 700
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.03,
|
| 54 |
+
"learning_rate": 0.00019995242212892653,
|
| 55 |
+
"loss": 0.7564,
|
| 56 |
+
"step": 800
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.03,
|
| 60 |
+
"learning_rate": 0.00019993961604363532,
|
| 61 |
+
"loss": 0.7724,
|
| 62 |
+
"step": 900
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.04,
|
| 66 |
+
"learning_rate": 0.00019992528607267815,
|
| 67 |
+
"loss": 0.7308,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.04,
|
| 72 |
+
"eval_loss": 0.7677998542785645,
|
| 73 |
+
"eval_runtime": 1774.3517,
|
| 74 |
+
"eval_samples_per_second": 0.305,
|
| 75 |
+
"eval_steps_per_second": 0.305,
|
| 76 |
+
"step": 1000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.04,
|
| 80 |
+
"learning_rate": 0.0001999094324345594,
|
| 81 |
+
"loss": 0.7844,
|
| 82 |
+
"step": 1100
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.04,
|
| 86 |
+
"learning_rate": 0.00019989205537101633,
|
| 87 |
+
"loss": 0.7668,
|
| 88 |
+
"step": 1200
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.05,
|
| 92 |
+
"learning_rate": 0.00019987315514701553,
|
| 93 |
+
"loss": 0.7727,
|
| 94 |
+
"step": 1300
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.05,
|
| 98 |
+
"learning_rate": 0.00019985273205074878,
|
| 99 |
+
"loss": 0.7467,
|
| 100 |
+
"step": 1400
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.06,
|
| 104 |
+
"learning_rate": 0.00019983078639362883,
|
| 105 |
+
"loss": 0.7516,
|
| 106 |
+
"step": 1500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.06,
|
| 110 |
+
"learning_rate": 0.00019980731851028445,
|
| 111 |
+
"loss": 0.7267,
|
| 112 |
+
"step": 1600
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.06,
|
| 116 |
+
"learning_rate": 0.0001997823287585554,
|
| 117 |
+
"loss": 0.7632,
|
| 118 |
+
"step": 1700
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.07,
|
| 122 |
+
"learning_rate": 0.000199755817519487,
|
| 123 |
+
"loss": 0.7392,
|
| 124 |
+
"step": 1800
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.07,
|
| 128 |
+
"learning_rate": 0.00019972778519732436,
|
| 129 |
+
"loss": 0.7528,
|
| 130 |
+
"step": 1900
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.07,
|
| 134 |
+
"learning_rate": 0.0001996982322195061,
|
| 135 |
+
"loss": 0.725,
|
| 136 |
+
"step": 2000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.07,
|
| 140 |
+
"eval_loss": 0.7452704310417175,
|
| 141 |
+
"eval_runtime": 1787.7554,
|
| 142 |
+
"eval_samples_per_second": 0.303,
|
| 143 |
+
"eval_steps_per_second": 0.303,
|
| 144 |
+
"step": 2000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.08,
|
| 148 |
+
"learning_rate": 0.00019966715903665795,
|
| 149 |
+
"loss": 0.7234,
|
| 150 |
+
"step": 2100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.08,
|
| 154 |
+
"learning_rate": 0.00019963456612258576,
|
| 155 |
+
"loss": 0.754,
|
| 156 |
+
"step": 2200
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.09,
|
| 160 |
+
"learning_rate": 0.00019960045397426841,
|
| 161 |
+
"loss": 0.7856,
|
| 162 |
+
"step": 2300
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.09,
|
| 166 |
+
"learning_rate": 0.00019956482311185006,
|
| 167 |
+
"loss": 0.7387,
|
| 168 |
+
"step": 2400
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.09,
|
| 172 |
+
"learning_rate": 0.00019952767407863245,
|
| 173 |
+
"loss": 0.7309,
|
| 174 |
+
"step": 2500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.1,
|
| 178 |
+
"learning_rate": 0.00019948900744106633,
|
| 179 |
+
"loss": 0.7232,
|
| 180 |
+
"step": 2600
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.1,
|
| 184 |
+
"learning_rate": 0.00019944882378874316,
|
| 185 |
+
"loss": 0.7406,
|
| 186 |
+
"step": 2700
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.1,
|
| 190 |
+
"learning_rate": 0.0001994071237343858,
|
| 191 |
+
"loss": 0.7166,
|
| 192 |
+
"step": 2800
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.11,
|
| 196 |
+
"learning_rate": 0.00019936390791383936,
|
| 197 |
+
"loss": 0.7308,
|
| 198 |
+
"step": 2900
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.11,
|
| 202 |
+
"learning_rate": 0.00019931917698606143,
|
| 203 |
+
"loss": 0.7288,
|
| 204 |
+
"step": 3000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.11,
|
| 208 |
+
"eval_loss": 0.7343490123748779,
|
| 209 |
+
"eval_runtime": 1770.9966,
|
| 210 |
+
"eval_samples_per_second": 0.306,
|
| 211 |
+
"eval_steps_per_second": 0.306,
|
| 212 |
+
"step": 3000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.12,
|
| 216 |
+
"learning_rate": 0.00019927293163311206,
|
| 217 |
+
"loss": 0.7236,
|
| 218 |
+
"step": 3100
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.12,
|
| 222 |
+
"learning_rate": 0.00019922517256014337,
|
| 223 |
+
"loss": 0.716,
|
| 224 |
+
"step": 3200
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.12,
|
| 228 |
+
"learning_rate": 0.00019917590049538874,
|
| 229 |
+
"loss": 0.7564,
|
| 230 |
+
"step": 3300
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.13,
|
| 234 |
+
"learning_rate": 0.00019912511619015177,
|
| 235 |
+
"loss": 0.7082,
|
| 236 |
+
"step": 3400
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.13,
|
| 240 |
+
"learning_rate": 0.00019907282041879484,
|
| 241 |
+
"loss": 0.7103,
|
| 242 |
+
"step": 3500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.13,
|
| 246 |
+
"learning_rate": 0.00019901901397872715,
|
| 247 |
+
"loss": 0.7457,
|
| 248 |
+
"step": 3600
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.14,
|
| 252 |
+
"learning_rate": 0.0001989636976903928,
|
| 253 |
+
"loss": 0.7076,
|
| 254 |
+
"step": 3700
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.14,
|
| 258 |
+
"learning_rate": 0.0001989068723972581,
|
| 259 |
+
"loss": 0.7217,
|
| 260 |
+
"step": 3800
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.15,
|
| 264 |
+
"learning_rate": 0.00019884853896579873,
|
| 265 |
+
"loss": 0.7175,
|
| 266 |
+
"step": 3900
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.15,
|
| 270 |
+
"learning_rate": 0.0001987886982854866,
|
| 271 |
+
"loss": 0.7083,
|
| 272 |
+
"step": 4000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.15,
|
| 276 |
+
"eval_loss": 0.726176917552948,
|
| 277 |
+
"eval_runtime": 1765.3933,
|
| 278 |
+
"eval_samples_per_second": 0.307,
|
| 279 |
+
"eval_steps_per_second": 0.307,
|
| 280 |
+
"step": 4000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.15,
|
| 284 |
+
"learning_rate": 0.00019872735126877622,
|
| 285 |
+
"loss": 0.7228,
|
| 286 |
+
"step": 4100
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.16,
|
| 290 |
+
"learning_rate": 0.0001986644988510909,
|
| 291 |
+
"loss": 0.7133,
|
| 292 |
+
"step": 4200
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.16,
|
| 296 |
+
"learning_rate": 0.00019860014199080822,
|
| 297 |
+
"loss": 0.7243,
|
| 298 |
+
"step": 4300
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.16,
|
| 302 |
+
"learning_rate": 0.00019853428166924576,
|
| 303 |
+
"loss": 0.6929,
|
| 304 |
+
"step": 4400
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.17,
|
| 308 |
+
"learning_rate": 0.00019846691889064593,
|
| 309 |
+
"loss": 0.7392,
|
| 310 |
+
"step": 4500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.17,
|
| 314 |
+
"learning_rate": 0.0001983980546821607,
|
| 315 |
+
"loss": 0.7247,
|
| 316 |
+
"step": 4600
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.18,
|
| 320 |
+
"learning_rate": 0.0001983276900938359,
|
| 321 |
+
"loss": 0.7258,
|
| 322 |
+
"step": 4700
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.18,
|
| 326 |
+
"learning_rate": 0.00019825582619859532,
|
| 327 |
+
"loss": 0.7197,
|
| 328 |
+
"step": 4800
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.18,
|
| 332 |
+
"learning_rate": 0.0001981824640922242,
|
| 333 |
+
"loss": 0.6906,
|
| 334 |
+
"step": 4900
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.19,
|
| 338 |
+
"learning_rate": 0.00019810760489335266,
|
| 339 |
+
"loss": 0.7274,
|
| 340 |
+
"step": 5000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.19,
|
| 344 |
+
"eval_loss": 0.7171670794487,
|
| 345 |
+
"eval_runtime": 1812.7597,
|
| 346 |
+
"eval_samples_per_second": 0.299,
|
| 347 |
+
"eval_steps_per_second": 0.299,
|
| 348 |
+
"step": 5000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.19,
|
| 352 |
+
"learning_rate": 0.0001980312497434385,
|
| 353 |
+
"loss": 0.7105,
|
| 354 |
+
"step": 5100
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.19,
|
| 358 |
+
"learning_rate": 0.00019795339980675002,
|
| 359 |
+
"loss": 0.7091,
|
| 360 |
+
"step": 5200
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.2,
|
| 364 |
+
"learning_rate": 0.00019787405627034804,
|
| 365 |
+
"loss": 0.7102,
|
| 366 |
+
"step": 5300
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.2,
|
| 370 |
+
"learning_rate": 0.0001977932203440678,
|
| 371 |
+
"loss": 0.7314,
|
| 372 |
+
"step": 5400
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.21,
|
| 376 |
+
"learning_rate": 0.00019771089326050075,
|
| 377 |
+
"loss": 0.6945,
|
| 378 |
+
"step": 5500
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.21,
|
| 382 |
+
"learning_rate": 0.0001976270762749755,
|
| 383 |
+
"loss": 0.7048,
|
| 384 |
+
"step": 5600
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.21,
|
| 388 |
+
"learning_rate": 0.00019754177066553882,
|
| 389 |
+
"loss": 0.6963,
|
| 390 |
+
"step": 5700
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.22,
|
| 394 |
+
"learning_rate": 0.00019745497773293613,
|
| 395 |
+
"loss": 0.711,
|
| 396 |
+
"step": 5800
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.22,
|
| 400 |
+
"learning_rate": 0.0001973666988005916,
|
| 401 |
+
"loss": 0.7017,
|
| 402 |
+
"step": 5900
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.22,
|
| 406 |
+
"learning_rate": 0.00019727693521458806,
|
| 407 |
+
"loss": 0.7287,
|
| 408 |
+
"step": 6000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.22,
|
| 412 |
+
"eval_loss": 0.710155725479126,
|
| 413 |
+
"eval_runtime": 1786.7467,
|
| 414 |
+
"eval_samples_per_second": 0.303,
|
| 415 |
+
"eval_steps_per_second": 0.303,
|
| 416 |
+
"step": 6000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.23,
|
| 420 |
+
"learning_rate": 0.00019718568834364638,
|
| 421 |
+
"loss": 0.6894,
|
| 422 |
+
"step": 6100
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.23,
|
| 426 |
+
"learning_rate": 0.00019709295957910476,
|
| 427 |
+
"loss": 0.7061,
|
| 428 |
+
"step": 6200
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.23,
|
| 432 |
+
"learning_rate": 0.00019699875033489728,
|
| 433 |
+
"loss": 0.7063,
|
| 434 |
+
"step": 6300
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.24,
|
| 438 |
+
"learning_rate": 0.00019690306204753254,
|
| 439 |
+
"loss": 0.6872,
|
| 440 |
+
"step": 6400
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.24,
|
| 444 |
+
"learning_rate": 0.0001968058961760717,
|
| 445 |
+
"loss": 0.7095,
|
| 446 |
+
"step": 6500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.25,
|
| 450 |
+
"learning_rate": 0.00019670725420210618,
|
| 451 |
+
"loss": 0.695,
|
| 452 |
+
"step": 6600
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.25,
|
| 456 |
+
"learning_rate": 0.0001966071376297351,
|
| 457 |
+
"loss": 0.674,
|
| 458 |
+
"step": 6700
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.25,
|
| 462 |
+
"learning_rate": 0.00019650554798554236,
|
| 463 |
+
"loss": 0.7225,
|
| 464 |
+
"step": 6800
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.26,
|
| 468 |
+
"learning_rate": 0.00019640248681857342,
|
| 469 |
+
"loss": 0.6845,
|
| 470 |
+
"step": 6900
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.26,
|
| 474 |
+
"learning_rate": 0.00019629795570031149,
|
| 475 |
+
"loss": 0.6891,
|
| 476 |
+
"step": 7000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.26,
|
| 480 |
+
"eval_loss": 0.703677773475647,
|
| 481 |
+
"eval_runtime": 1767.3593,
|
| 482 |
+
"eval_samples_per_second": 0.307,
|
| 483 |
+
"eval_steps_per_second": 0.307,
|
| 484 |
+
"step": 7000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.26,
|
| 488 |
+
"learning_rate": 0.00019619195622465379,
|
| 489 |
+
"loss": 0.6962,
|
| 490 |
+
"step": 7100
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.27,
|
| 494 |
+
"learning_rate": 0.0001960844900078871,
|
| 495 |
+
"loss": 0.6779,
|
| 496 |
+
"step": 7200
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.27,
|
| 500 |
+
"learning_rate": 0.00019597555868866318,
|
| 501 |
+
"loss": 0.7354,
|
| 502 |
+
"step": 7300
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.28,
|
| 506 |
+
"learning_rate": 0.00019586516392797374,
|
| 507 |
+
"loss": 0.7196,
|
| 508 |
+
"step": 7400
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.28,
|
| 512 |
+
"learning_rate": 0.0001957533074091252,
|
| 513 |
+
"loss": 0.682,
|
| 514 |
+
"step": 7500
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.28,
|
| 518 |
+
"learning_rate": 0.0001956399908377129,
|
| 519 |
+
"loss": 0.6938,
|
| 520 |
+
"step": 7600
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.29,
|
| 524 |
+
"learning_rate": 0.0001955252159415952,
|
| 525 |
+
"loss": 0.6912,
|
| 526 |
+
"step": 7700
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.29,
|
| 530 |
+
"learning_rate": 0.00019540898447086705,
|
| 531 |
+
"loss": 0.7048,
|
| 532 |
+
"step": 7800
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.29,
|
| 536 |
+
"learning_rate": 0.00019529129819783334,
|
| 537 |
+
"loss": 0.7007,
|
| 538 |
+
"step": 7900
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.3,
|
| 542 |
+
"learning_rate": 0.00019517215891698192,
|
| 543 |
+
"loss": 0.6969,
|
| 544 |
+
"step": 8000
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.3,
|
| 548 |
+
"eval_loss": 0.6973471641540527,
|
| 549 |
+
"eval_runtime": 1793.2355,
|
| 550 |
+
"eval_samples_per_second": 0.302,
|
| 551 |
+
"eval_steps_per_second": 0.302,
|
| 552 |
+
"step": 8000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.3,
|
| 556 |
+
"learning_rate": 0.00019505156844495619,
|
| 557 |
+
"loss": 0.6894,
|
| 558 |
+
"step": 8100
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.31,
|
| 562 |
+
"learning_rate": 0.00019492952862052733,
|
| 563 |
+
"loss": 0.6971,
|
| 564 |
+
"step": 8200
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.31,
|
| 568 |
+
"learning_rate": 0.0001948060413045665,
|
| 569 |
+
"loss": 0.7135,
|
| 570 |
+
"step": 8300
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.31,
|
| 574 |
+
"learning_rate": 0.0001946811083800161,
|
| 575 |
+
"loss": 0.6794,
|
| 576 |
+
"step": 8400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.32,
|
| 580 |
+
"learning_rate": 0.0001945547317518614,
|
| 581 |
+
"loss": 0.7086,
|
| 582 |
+
"step": 8500
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.32,
|
| 586 |
+
"learning_rate": 0.00019442691334710136,
|
| 587 |
+
"loss": 0.7042,
|
| 588 |
+
"step": 8600
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.32,
|
| 592 |
+
"learning_rate": 0.00019429765511471916,
|
| 593 |
+
"loss": 0.6822,
|
| 594 |
+
"step": 8700
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.33,
|
| 598 |
+
"learning_rate": 0.0001941669590256526,
|
| 599 |
+
"loss": 0.7016,
|
| 600 |
+
"step": 8800
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.33,
|
| 604 |
+
"learning_rate": 0.00019403482707276406,
|
| 605 |
+
"loss": 0.705,
|
| 606 |
+
"step": 8900
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.34,
|
| 610 |
+
"learning_rate": 0.00019390126127080999,
|
| 611 |
+
"loss": 0.698,
|
| 612 |
+
"step": 9000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.34,
|
| 616 |
+
"eval_loss": 0.6910382509231567,
|
| 617 |
+
"eval_runtime": 1782.1661,
|
| 618 |
+
"eval_samples_per_second": 0.304,
|
| 619 |
+
"eval_steps_per_second": 0.304,
|
| 620 |
+
"step": 9000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.34,
|
| 624 |
+
"learning_rate": 0.00019376626365641026,
|
| 625 |
+
"loss": 0.6926,
|
| 626 |
+
"step": 9100
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.34,
|
| 630 |
+
"learning_rate": 0.0001936298362880172,
|
| 631 |
+
"loss": 0.6871,
|
| 632 |
+
"step": 9200
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.35,
|
| 636 |
+
"learning_rate": 0.00019349198124588403,
|
| 637 |
+
"loss": 0.6894,
|
| 638 |
+
"step": 9300
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.35,
|
| 642 |
+
"learning_rate": 0.00019335270063203325,
|
| 643 |
+
"loss": 0.6894,
|
| 644 |
+
"step": 9400
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.35,
|
| 648 |
+
"learning_rate": 0.00019321199657022464,
|
| 649 |
+
"loss": 0.7057,
|
| 650 |
+
"step": 9500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.36,
|
| 654 |
+
"learning_rate": 0.00019306987120592265,
|
| 655 |
+
"loss": 0.6682,
|
| 656 |
+
"step": 9600
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.36,
|
| 660 |
+
"learning_rate": 0.00019292632670626401,
|
| 661 |
+
"loss": 0.6931,
|
| 662 |
+
"step": 9700
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.37,
|
| 666 |
+
"learning_rate": 0.00019278136526002443,
|
| 667 |
+
"loss": 0.7244,
|
| 668 |
+
"step": 9800
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.37,
|
| 672 |
+
"learning_rate": 0.0001926349890775853,
|
| 673 |
+
"loss": 0.6881,
|
| 674 |
+
"step": 9900
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.37,
|
| 678 |
+
"learning_rate": 0.00019248720039090006,
|
| 679 |
+
"loss": 0.6839,
|
| 680 |
+
"step": 10000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.37,
|
| 684 |
+
"eval_loss": 0.6857322454452515,
|
| 685 |
+
"eval_runtime": 1760.8664,
|
| 686 |
+
"eval_samples_per_second": 0.308,
|
| 687 |
+
"eval_steps_per_second": 0.308,
|
| 688 |
+
"step": 10000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.38,
|
| 692 |
+
"learning_rate": 0.00019233800145346006,
|
| 693 |
+
"loss": 0.6917,
|
| 694 |
+
"step": 10100
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 0.38,
|
| 698 |
+
"learning_rate": 0.0001921873945402602,
|
| 699 |
+
"loss": 0.6672,
|
| 700 |
+
"step": 10200
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 0.38,
|
| 704 |
+
"learning_rate": 0.00019203538194776442,
|
| 705 |
+
"loss": 0.6873,
|
| 706 |
+
"step": 10300
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.39,
|
| 710 |
+
"learning_rate": 0.00019188196599387043,
|
| 711 |
+
"loss": 0.6733,
|
| 712 |
+
"step": 10400
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.39,
|
| 716 |
+
"learning_rate": 0.00019172714901787453,
|
| 717 |
+
"loss": 0.706,
|
| 718 |
+
"step": 10500
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.4,
|
| 722 |
+
"learning_rate": 0.00019157093338043583,
|
| 723 |
+
"loss": 0.6848,
|
| 724 |
+
"step": 10600
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.4,
|
| 728 |
+
"learning_rate": 0.00019141332146354042,
|
| 729 |
+
"loss": 0.6728,
|
| 730 |
+
"step": 10700
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.4,
|
| 734 |
+
"learning_rate": 0.00019125431567046494,
|
| 735 |
+
"loss": 0.686,
|
| 736 |
+
"step": 10800
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.41,
|
| 740 |
+
"learning_rate": 0.00019109391842573987,
|
| 741 |
+
"loss": 0.6992,
|
| 742 |
+
"step": 10900
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 0.41,
|
| 746 |
+
"learning_rate": 0.00019093213217511265,
|
| 747 |
+
"loss": 0.6675,
|
| 748 |
+
"step": 11000
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.41,
|
| 752 |
+
"eval_loss": 0.6794907450675964,
|
| 753 |
+
"eval_runtime": 1782.5413,
|
| 754 |
+
"eval_samples_per_second": 0.304,
|
| 755 |
+
"eval_steps_per_second": 0.304,
|
| 756 |
+
"step": 11000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.41,
|
| 760 |
+
"learning_rate": 0.0001907689593855104,
|
| 761 |
+
"loss": 0.6721,
|
| 762 |
+
"step": 11100
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.42,
|
| 766 |
+
"learning_rate": 0.00019060440254500228,
|
| 767 |
+
"loss": 0.6353,
|
| 768 |
+
"step": 11200
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.42,
|
| 772 |
+
"learning_rate": 0.00019043846416276155,
|
| 773 |
+
"loss": 0.6449,
|
| 774 |
+
"step": 11300
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.43,
|
| 778 |
+
"learning_rate": 0.0001902711467690272,
|
| 779 |
+
"loss": 0.6451,
|
| 780 |
+
"step": 11400
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.43,
|
| 784 |
+
"learning_rate": 0.00019010245291506569,
|
| 785 |
+
"loss": 0.6421,
|
| 786 |
+
"step": 11500
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.43,
|
| 790 |
+
"learning_rate": 0.00018993238517313167,
|
| 791 |
+
"loss": 0.6352,
|
| 792 |
+
"step": 11600
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 0.44,
|
| 796 |
+
"learning_rate": 0.0001897609461364289,
|
| 797 |
+
"loss": 0.6371,
|
| 798 |
+
"step": 11700
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.44,
|
| 802 |
+
"learning_rate": 0.00018958813841907083,
|
| 803 |
+
"loss": 0.623,
|
| 804 |
+
"step": 11800
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.44,
|
| 808 |
+
"learning_rate": 0.00018941396465604063,
|
| 809 |
+
"loss": 0.6533,
|
| 810 |
+
"step": 11900
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.45,
|
| 814 |
+
"learning_rate": 0.00018923842750315095,
|
| 815 |
+
"loss": 0.6371,
|
| 816 |
+
"step": 12000
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.45,
|
| 820 |
+
"eval_loss": 0.6759930849075317,
|
| 821 |
+
"eval_runtime": 1304.1351,
|
| 822 |
+
"eval_samples_per_second": 0.416,
|
| 823 |
+
"eval_steps_per_second": 0.416,
|
| 824 |
+
"step": 12000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.45,
|
| 828 |
+
"learning_rate": 0.00018906152963700358,
|
| 829 |
+
"loss": 0.6664,
|
| 830 |
+
"step": 12100
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.45,
|
| 834 |
+
"learning_rate": 0.00018888327375494847,
|
| 835 |
+
"loss": 0.6644,
|
| 836 |
+
"step": 12200
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.46,
|
| 840 |
+
"learning_rate": 0.00018870366257504274,
|
| 841 |
+
"loss": 0.623,
|
| 842 |
+
"step": 12300
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.46,
|
| 846 |
+
"learning_rate": 0.00018852269883600918,
|
| 847 |
+
"loss": 0.6242,
|
| 848 |
+
"step": 12400
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.47,
|
| 852 |
+
"learning_rate": 0.00018834038529719446,
|
| 853 |
+
"loss": 0.6318,
|
| 854 |
+
"step": 12500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.47,
|
| 858 |
+
"learning_rate": 0.0001881567247385271,
|
| 859 |
+
"loss": 0.6359,
|
| 860 |
+
"step": 12600
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.47,
|
| 864 |
+
"learning_rate": 0.00018797171996047505,
|
| 865 |
+
"loss": 0.6449,
|
| 866 |
+
"step": 12700
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.48,
|
| 870 |
+
"learning_rate": 0.00018778537378400304,
|
| 871 |
+
"loss": 0.6434,
|
| 872 |
+
"step": 12800
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.48,
|
| 876 |
+
"learning_rate": 0.00018759768905052946,
|
| 877 |
+
"loss": 0.6323,
|
| 878 |
+
"step": 12900
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.48,
|
| 882 |
+
"learning_rate": 0.00018740866862188317,
|
| 883 |
+
"loss": 0.6377,
|
| 884 |
+
"step": 13000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.48,
|
| 888 |
+
"eval_loss": 0.6696639060974121,
|
| 889 |
+
"eval_runtime": 1238.6847,
|
| 890 |
+
"eval_samples_per_second": 0.438,
|
| 891 |
+
"eval_steps_per_second": 0.438,
|
| 892 |
+
"step": 13000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.49,
|
| 896 |
+
"learning_rate": 0.0001872183153802598,
|
| 897 |
+
"loss": 0.6232,
|
| 898 |
+
"step": 13100
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.49,
|
| 902 |
+
"learning_rate": 0.00018702663222817774,
|
| 903 |
+
"loss": 0.6236,
|
| 904 |
+
"step": 13200
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 0.5,
|
| 908 |
+
"learning_rate": 0.00018683362208843395,
|
| 909 |
+
"loss": 0.6331,
|
| 910 |
+
"step": 13300
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.5,
|
| 914 |
+
"learning_rate": 0.00018663928790405945,
|
| 915 |
+
"loss": 0.6528,
|
| 916 |
+
"step": 13400
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 0.5,
|
| 920 |
+
"learning_rate": 0.00018644363263827426,
|
| 921 |
+
"loss": 0.6362,
|
| 922 |
+
"step": 13500
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.51,
|
| 926 |
+
"learning_rate": 0.00018624665927444248,
|
| 927 |
+
"loss": 0.6308,
|
| 928 |
+
"step": 13600
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.51,
|
| 932 |
+
"learning_rate": 0.00018604837081602656,
|
| 933 |
+
"loss": 0.6107,
|
| 934 |
+
"step": 13700
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.51,
|
| 938 |
+
"learning_rate": 0.00018584877028654154,
|
| 939 |
+
"loss": 0.6418,
|
| 940 |
+
"step": 13800
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.52,
|
| 944 |
+
"learning_rate": 0.00018564786072950917,
|
| 945 |
+
"loss": 0.6276,
|
| 946 |
+
"step": 13900
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.52,
|
| 950 |
+
"learning_rate": 0.00018544564520841118,
|
| 951 |
+
"loss": 0.6296,
|
| 952 |
+
"step": 14000
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 0.52,
|
| 956 |
+
"eval_loss": 0.6651941537857056,
|
| 957 |
+
"eval_runtime": 1277.2835,
|
| 958 |
+
"eval_samples_per_second": 0.424,
|
| 959 |
+
"eval_steps_per_second": 0.424,
|
| 960 |
+
"step": 14000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.53,
|
| 964 |
+
"learning_rate": 0.00018524212680664286,
|
| 965 |
+
"loss": 0.636,
|
| 966 |
+
"step": 14100
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 0.53,
|
| 970 |
+
"learning_rate": 0.00018503730862746574,
|
| 971 |
+
"loss": 0.6643,
|
| 972 |
+
"step": 14200
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 0.53,
|
| 976 |
+
"learning_rate": 0.00018483119379396058,
|
| 977 |
+
"loss": 0.6282,
|
| 978 |
+
"step": 14300
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.54,
|
| 982 |
+
"learning_rate": 0.0001846237854489796,
|
| 983 |
+
"loss": 0.6381,
|
| 984 |
+
"step": 14400
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.54,
|
| 988 |
+
"learning_rate": 0.00018441508675509844,
|
| 989 |
+
"loss": 0.6692,
|
| 990 |
+
"step": 14500
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.54,
|
| 994 |
+
"learning_rate": 0.00018420510089456823,
|
| 995 |
+
"loss": 0.6478,
|
| 996 |
+
"step": 14600
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.55,
|
| 1000 |
+
"learning_rate": 0.00018399383106926676,
|
| 1001 |
+
"loss": 0.6293,
|
| 1002 |
+
"step": 14700
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.55,
|
| 1006 |
+
"learning_rate": 0.00018378128050064988,
|
| 1007 |
+
"loss": 0.6406,
|
| 1008 |
+
"step": 14800
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 0.56,
|
| 1012 |
+
"learning_rate": 0.0001835674524297023,
|
| 1013 |
+
"loss": 0.6407,
|
| 1014 |
+
"step": 14900
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 0.56,
|
| 1018 |
+
"learning_rate": 0.0001833523501168881,
|
| 1019 |
+
"loss": 0.633,
|
| 1020 |
+
"step": 15000
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.56,
|
| 1024 |
+
"eval_loss": 0.6601429581642151,
|
| 1025 |
+
"eval_runtime": 1275.6071,
|
| 1026 |
+
"eval_samples_per_second": 0.425,
|
| 1027 |
+
"eval_steps_per_second": 0.425,
|
| 1028 |
+
"step": 15000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.56,
|
| 1032 |
+
"learning_rate": 0.00018313597684210115,
|
| 1033 |
+
"loss": 0.6198,
|
| 1034 |
+
"step": 15100
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.57,
|
| 1038 |
+
"learning_rate": 0.00018291833590461498,
|
| 1039 |
+
"loss": 0.6345,
|
| 1040 |
+
"step": 15200
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.57,
|
| 1044 |
+
"learning_rate": 0.00018269943062303257,
|
| 1045 |
+
"loss": 0.6554,
|
| 1046 |
+
"step": 15300
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.57,
|
| 1050 |
+
"learning_rate": 0.00018247926433523562,
|
| 1051 |
+
"loss": 0.6151,
|
| 1052 |
+
"step": 15400
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.58,
|
| 1056 |
+
"learning_rate": 0.00018225784039833386,
|
| 1057 |
+
"loss": 0.6331,
|
| 1058 |
+
"step": 15500
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.58,
|
| 1062 |
+
"learning_rate": 0.0001820351621886136,
|
| 1063 |
+
"loss": 0.6256,
|
| 1064 |
+
"step": 15600
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.59,
|
| 1068 |
+
"learning_rate": 0.0001818112331014865,
|
| 1069 |
+
"loss": 0.6263,
|
| 1070 |
+
"step": 15700
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 0.59,
|
| 1074 |
+
"learning_rate": 0.00018158605655143757,
|
| 1075 |
+
"loss": 0.6015,
|
| 1076 |
+
"step": 15800
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.59,
|
| 1080 |
+
"learning_rate": 0.00018135963597197327,
|
| 1081 |
+
"loss": 0.6144,
|
| 1082 |
+
"step": 15900
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.6,
|
| 1086 |
+
"learning_rate": 0.00018113197481556912,
|
| 1087 |
+
"loss": 0.613,
|
| 1088 |
+
"step": 16000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.6,
|
| 1092 |
+
"eval_loss": 0.6547831892967224,
|
| 1093 |
+
"eval_runtime": 1305.9645,
|
| 1094 |
+
"eval_samples_per_second": 0.415,
|
| 1095 |
+
"eval_steps_per_second": 0.415,
|
| 1096 |
+
"step": 16000
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 0.6,
|
| 1100 |
+
"learning_rate": 0.00018090307655361701,
|
| 1101 |
+
"loss": 0.6354,
|
| 1102 |
+
"step": 16100
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.6,
|
| 1106 |
+
"learning_rate": 0.00018067294467637228,
|
| 1107 |
+
"loss": 0.6349,
|
| 1108 |
+
"step": 16200
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.61,
|
| 1112 |
+
"learning_rate": 0.00018044158269290054,
|
| 1113 |
+
"loss": 0.6127,
|
| 1114 |
+
"step": 16300
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 0.61,
|
| 1118 |
+
"learning_rate": 0.00018020899413102412,
|
| 1119 |
+
"loss": 0.5977,
|
| 1120 |
+
"step": 16400
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 0.62,
|
| 1124 |
+
"learning_rate": 0.00017997518253726834,
|
| 1125 |
+
"loss": 0.6213,
|
| 1126 |
+
"step": 16500
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.62,
|
| 1130 |
+
"learning_rate": 0.00017974015147680734,
|
| 1131 |
+
"loss": 0.6168,
|
| 1132 |
+
"step": 16600
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.62,
|
| 1136 |
+
"learning_rate": 0.00017950390453340978,
|
| 1137 |
+
"loss": 0.5978,
|
| 1138 |
+
"step": 16700
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 0.63,
|
| 1142 |
+
"learning_rate": 0.0001792664453093842,
|
| 1143 |
+
"loss": 0.6201,
|
| 1144 |
+
"step": 16800
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.63,
|
| 1148 |
+
"learning_rate": 0.000179027777425524,
|
| 1149 |
+
"loss": 0.6141,
|
| 1150 |
+
"step": 16900
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.63,
|
| 1154 |
+
"learning_rate": 0.00017878790452105245,
|
| 1155 |
+
"loss": 0.6135,
|
| 1156 |
+
"step": 17000
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 0.63,
|
| 1160 |
+
"eval_loss": 0.6480616927146912,
|
| 1161 |
+
"eval_runtime": 1347.9883,
|
| 1162 |
+
"eval_samples_per_second": 0.402,
|
| 1163 |
+
"eval_steps_per_second": 0.402,
|
| 1164 |
+
"step": 17000
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.64,
|
| 1168 |
+
"learning_rate": 0.0001785468302535669,
|
| 1169 |
+
"loss": 0.6363,
|
| 1170 |
+
"step": 17100
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 0.64,
|
| 1174 |
+
"learning_rate": 0.00017830455829898317,
|
| 1175 |
+
"loss": 0.6076,
|
| 1176 |
+
"step": 17200
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 0.65,
|
| 1180 |
+
"learning_rate": 0.00017806109235147963,
|
| 1181 |
+
"loss": 0.609,
|
| 1182 |
+
"step": 17300
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.65,
|
| 1186 |
+
"learning_rate": 0.00017781643612344058,
|
| 1187 |
+
"loss": 0.6044,
|
| 1188 |
+
"step": 17400
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 0.65,
|
| 1192 |
+
"learning_rate": 0.00017757059334539994,
|
| 1193 |
+
"loss": 0.6262,
|
| 1194 |
+
"step": 17500
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.66,
|
| 1198 |
+
"learning_rate": 0.00017732356776598403,
|
| 1199 |
+
"loss": 0.6195,
|
| 1200 |
+
"step": 17600
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.66,
|
| 1204 |
+
"learning_rate": 0.0001770753631518548,
|
| 1205 |
+
"loss": 0.6328,
|
| 1206 |
+
"step": 17700
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.66,
|
| 1210 |
+
"learning_rate": 0.000176825983287652,
|
| 1211 |
+
"loss": 0.6028,
|
| 1212 |
+
"step": 17800
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 0.67,
|
| 1216 |
+
"learning_rate": 0.0001765754319759358,
|
| 1217 |
+
"loss": 0.6159,
|
| 1218 |
+
"step": 17900
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 0.67,
|
| 1222 |
+
"learning_rate": 0.0001763237130371287,
|
| 1223 |
+
"loss": 0.6169,
|
| 1224 |
+
"step": 18000
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.67,
|
| 1228 |
+
"eval_loss": 0.6444052457809448,
|
| 1229 |
+
"eval_runtime": 1304.3701,
|
| 1230 |
+
"eval_samples_per_second": 0.416,
|
| 1231 |
+
"eval_steps_per_second": 0.416,
|
| 1232 |
+
"step": 18000
|
| 1233 |
+
}
|
| 1234 |
+
],
|
| 1235 |
+
"max_steps": 80463,
|
| 1236 |
+
"num_train_epochs": 3,
|
| 1237 |
+
"total_flos": 5.045441572600873e+18,
|
| 1238 |
+
"trial_name": null,
|
| 1239 |
+
"trial_params": null
|
| 1240 |
+
}
|
checkpoint-18000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8ca8c55b410908f1a6fb4d78d55fe6aad82bbca76ec8021e18981496f18fa70
|
| 3 |
+
size 4027
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8ca8c55b410908f1a6fb4d78d55fe6aad82bbca76ec8021e18981496f18fa70
|
| 3 |
size 4027
|