Commit
•
001d3a6
1
Parent(s):
1e97834
add weights
Browse files- README.md +20 -0
- adapter_config.json +20 -0
- adapter_model.bin +3 -0
- all_results.json +7 -0
- checkpoint-1000/README.md +20 -0
- checkpoint-1000/adapter_config.json +20 -0
- checkpoint-1000/adapter_model.bin +3 -0
- checkpoint-1000/finetuning_args.json +15 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state_0.pth +3 -0
- checkpoint-1000/rng_state_1.pth +3 -0
- checkpoint-1000/rng_state_2.pth +3 -0
- checkpoint-1000/rng_state_3.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/trainer_state.json +616 -0
- checkpoint-1000/training_args.bin +3 -0
- finetuning_args.json +15 -0
- train_results.json +7 -0
- trainer_log.jsonl +108 -0
- trainer_state.json +667 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
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: float16
|
| 17 |
+
### Framework versions
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- PEFT 0.4.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "../Baichuan2-13B-Chat",
|
| 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": 32.0,
|
| 11 |
+
"lora_dropout": 0.1,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"W_pack"
|
| 18 |
+
],
|
| 19 |
+
"task_type": "CAUSAL_LM"
|
| 20 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b46972030be120067c5284f694a8112aa47548e6471cabe67d85099dbfd1e3a5
|
| 3 |
+
size 26241825
|
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 1.5770846359804964,
|
| 4 |
+
"train_runtime": 13419.9836,
|
| 5 |
+
"train_samples_per_second": 10.287,
|
| 6 |
+
"train_steps_per_second": 0.08
|
| 7 |
+
}
|
checkpoint-1000/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: float16
|
| 17 |
+
### Framework versions
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- PEFT 0.4.0
|
checkpoint-1000/adapter_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "../Baichuan2-13B-Chat",
|
| 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": 32.0,
|
| 11 |
+
"lora_dropout": 0.1,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"W_pack"
|
| 18 |
+
],
|
| 19 |
+
"task_type": "CAUSAL_LM"
|
| 20 |
+
}
|
checkpoint-1000/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0c6f9a3827c723b798e96a73880310fa0efb72e74a648097dd0013eb97c5810
|
| 3 |
+
size 26241825
|
checkpoint-1000/finetuning_args.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dpo_beta": 0.1,
|
| 3 |
+
"finetuning_type": "lora",
|
| 4 |
+
"lora_alpha": 32.0,
|
| 5 |
+
"lora_dropout": 0.1,
|
| 6 |
+
"lora_rank": 8,
|
| 7 |
+
"lora_target": [
|
| 8 |
+
"W_pack"
|
| 9 |
+
],
|
| 10 |
+
"name_module_trainable": "mlp",
|
| 11 |
+
"num_hidden_layers": 32,
|
| 12 |
+
"num_layer_trainable": 3,
|
| 13 |
+
"ppo_score_norm": false,
|
| 14 |
+
"resume_lora_training": true
|
| 15 |
+
}
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e621fce530ee2227ffe989ec8032812991cad2a5c4aecfeeb6a1502e7ea2681a
|
| 3 |
+
size 52476101
|
checkpoint-1000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfed83d02d0194b678b514212b6419c48ddecec362a6a746c0840ab1cc9e860f
|
| 3 |
+
size 18679
|
checkpoint-1000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91a0481f60411ef59e93bf24c9aa8fbd45d68712f754306cedf8bb1d2192b46f
|
| 3 |
+
size 18679
|
checkpoint-1000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b04c95737623c2406475eeee1502802220425d11d23dc2b0774ba988f0046cb3
|
| 3 |
+
size 18679
|
checkpoint-1000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d13689e3d2222e605b91993016c04d573d966012148b3341f4fb72a486be6118
|
| 3 |
+
size 18679
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e84f57a783241321dee02d8f3be0c1b87153d61108e1f3152d069e1c8ddc2b0
|
| 3 |
+
size 627
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,616 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.8544274455261938,
|
| 5 |
+
"global_step": 1000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 4.998938447446803e-05,
|
| 13 |
+
"loss": 2.0078,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"learning_rate": 4.9957546913022665e-05,
|
| 19 |
+
"loss": 1.8414,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.06,
|
| 24 |
+
"learning_rate": 4.9904514353459654e-05,
|
| 25 |
+
"loss": 1.7763,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.07,
|
| 30 |
+
"learning_rate": 4.983033183325818e-05,
|
| 31 |
+
"loss": 1.7278,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.09,
|
| 36 |
+
"learning_rate": 4.973506235133323e-05,
|
| 37 |
+
"loss": 1.7139,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.11,
|
| 42 |
+
"learning_rate": 4.96313569658781e-05,
|
| 43 |
+
"loss": 1.6947,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.13,
|
| 48 |
+
"learning_rate": 4.94962599008322e-05,
|
| 49 |
+
"loss": 1.6749,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.15,
|
| 54 |
+
"learning_rate": 4.9340359581993066e-05,
|
| 55 |
+
"loss": 1.6579,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.17,
|
| 60 |
+
"learning_rate": 4.916378840646592e-05,
|
| 61 |
+
"loss": 1.6499,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.19,
|
| 66 |
+
"learning_rate": 4.8966696325916515e-05,
|
| 67 |
+
"loss": 1.6507,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.2,
|
| 72 |
+
"learning_rate": 4.8749250719225915e-05,
|
| 73 |
+
"loss": 1.6426,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.22,
|
| 78 |
+
"learning_rate": 4.8511636250345294e-05,
|
| 79 |
+
"loss": 1.6288,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.24,
|
| 84 |
+
"learning_rate": 4.825405471147153e-05,
|
| 85 |
+
"loss": 1.6265,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.26,
|
| 90 |
+
"learning_rate": 4.797672485167683e-05,
|
| 91 |
+
"loss": 1.6252,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.28,
|
| 96 |
+
"learning_rate": 4.7679882191137804e-05,
|
| 97 |
+
"loss": 1.6218,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.3,
|
| 102 |
+
"learning_rate": 4.7363778821121784e-05,
|
| 103 |
+
"loss": 1.6146,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.32,
|
| 108 |
+
"learning_rate": 4.702868318990039e-05,
|
| 109 |
+
"loss": 1.604,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.33,
|
| 114 |
+
"learning_rate": 4.6674879874771926e-05,
|
| 115 |
+
"loss": 1.607,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.35,
|
| 120 |
+
"learning_rate": 4.630266934038642e-05,
|
| 121 |
+
"loss": 1.5972,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.37,
|
| 126 |
+
"learning_rate": 4.591236768357833e-05,
|
| 127 |
+
"loss": 1.5973,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.39,
|
| 132 |
+
"learning_rate": 4.55043063649239e-05,
|
| 133 |
+
"loss": 1.6043,
|
| 134 |
+
"step": 210
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.41,
|
| 138 |
+
"learning_rate": 4.507883192725089e-05,
|
| 139 |
+
"loss": 1.5839,
|
| 140 |
+
"step": 220
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.43,
|
| 144 |
+
"learning_rate": 4.463630570133978e-05,
|
| 145 |
+
"loss": 1.5923,
|
| 146 |
+
"step": 230
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.45,
|
| 150 |
+
"learning_rate": 4.417710349906658e-05,
|
| 151 |
+
"loss": 1.5841,
|
| 152 |
+
"step": 240
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.46,
|
| 156 |
+
"learning_rate": 4.3701615294247465e-05,
|
| 157 |
+
"loss": 1.5977,
|
| 158 |
+
"step": 250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.48,
|
| 162 |
+
"learning_rate": 4.321024489145673e-05,
|
| 163 |
+
"loss": 1.5954,
|
| 164 |
+
"step": 260
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.5,
|
| 168 |
+
"learning_rate": 4.270340958309888e-05,
|
| 169 |
+
"loss": 1.5914,
|
| 170 |
+
"step": 270
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.52,
|
| 174 |
+
"learning_rate": 4.2181539795026435e-05,
|
| 175 |
+
"loss": 1.577,
|
| 176 |
+
"step": 280
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.54,
|
| 180 |
+
"learning_rate": 4.1645078721004174e-05,
|
| 181 |
+
"loss": 1.576,
|
| 182 |
+
"step": 290
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.56,
|
| 186 |
+
"learning_rate": 4.109448194633033e-05,
|
| 187 |
+
"loss": 1.5771,
|
| 188 |
+
"step": 300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.57,
|
| 192 |
+
"learning_rate": 4.0530217060934466e-05,
|
| 193 |
+
"loss": 1.5825,
|
| 194 |
+
"step": 310
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.59,
|
| 198 |
+
"learning_rate": 3.9952763262280405e-05,
|
| 199 |
+
"loss": 1.581,
|
| 200 |
+
"step": 320
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.61,
|
| 204 |
+
"learning_rate": 3.9362610948411585e-05,
|
| 205 |
+
"loss": 1.5691,
|
| 206 |
+
"step": 330
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.63,
|
| 210 |
+
"learning_rate": 3.8760261301484466e-05,
|
| 211 |
+
"loss": 1.5795,
|
| 212 |
+
"step": 340
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.65,
|
| 216 |
+
"learning_rate": 3.8208140480771856e-05,
|
| 217 |
+
"loss": 1.5847,
|
| 218 |
+
"step": 350
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.67,
|
| 222 |
+
"learning_rate": 3.758403340686345e-05,
|
| 223 |
+
"loss": 1.5737,
|
| 224 |
+
"step": 360
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.69,
|
| 228 |
+
"learning_rate": 3.6949239442720976e-05,
|
| 229 |
+
"loss": 1.5645,
|
| 230 |
+
"step": 370
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.7,
|
| 234 |
+
"learning_rate": 3.6304297682067144e-05,
|
| 235 |
+
"loss": 1.5659,
|
| 236 |
+
"step": 380
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.72,
|
| 240 |
+
"learning_rate": 3.5649755836560106e-05,
|
| 241 |
+
"loss": 1.5613,
|
| 242 |
+
"step": 390
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.74,
|
| 246 |
+
"learning_rate": 3.4986169770653685e-05,
|
| 247 |
+
"loss": 1.5725,
|
| 248 |
+
"step": 400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.76,
|
| 252 |
+
"learning_rate": 3.431410302953389e-05,
|
| 253 |
+
"loss": 1.5619,
|
| 254 |
+
"step": 410
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.78,
|
| 258 |
+
"learning_rate": 3.363412636053269e-05,
|
| 259 |
+
"loss": 1.5615,
|
| 260 |
+
"step": 420
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.8,
|
| 264 |
+
"learning_rate": 3.294681722842537e-05,
|
| 265 |
+
"loss": 1.5623,
|
| 266 |
+
"step": 430
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.82,
|
| 270 |
+
"learning_rate": 3.225275932502315e-05,
|
| 271 |
+
"loss": 1.5685,
|
| 272 |
+
"step": 440
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.83,
|
| 276 |
+
"learning_rate": 3.1552542073477555e-05,
|
| 277 |
+
"loss": 1.566,
|
| 278 |
+
"step": 450
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.85,
|
| 282 |
+
"learning_rate": 3.084676012771753e-05,
|
| 283 |
+
"loss": 1.5643,
|
| 284 |
+
"step": 460
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.87,
|
| 288 |
+
"learning_rate": 3.0136012867444297e-05,
|
| 289 |
+
"loss": 1.5588,
|
| 290 |
+
"step": 470
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.89,
|
| 294 |
+
"learning_rate": 2.942090388911291e-05,
|
| 295 |
+
"loss": 1.5598,
|
| 296 |
+
"step": 480
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.91,
|
| 300 |
+
"learning_rate": 2.8702040493332778e-05,
|
| 301 |
+
"loss": 1.5618,
|
| 302 |
+
"step": 490
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.93,
|
| 306 |
+
"learning_rate": 2.7980033169122454e-05,
|
| 307 |
+
"loss": 1.5602,
|
| 308 |
+
"step": 500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.95,
|
| 312 |
+
"learning_rate": 2.7255495075456693e-05,
|
| 313 |
+
"loss": 1.5453,
|
| 314 |
+
"step": 510
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.96,
|
| 318 |
+
"learning_rate": 2.652904152054607e-05,
|
| 319 |
+
"loss": 1.5557,
|
| 320 |
+
"step": 520
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.98,
|
| 324 |
+
"learning_rate": 2.5801289439291388e-05,
|
| 325 |
+
"loss": 1.5493,
|
| 326 |
+
"step": 530
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.0,
|
| 330 |
+
"learning_rate": 2.5072856869356593e-05,
|
| 331 |
+
"loss": 1.5527,
|
| 332 |
+
"step": 540
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.02,
|
| 336 |
+
"learning_rate": 2.4344362426305255e-05,
|
| 337 |
+
"loss": 1.5564,
|
| 338 |
+
"step": 550
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.04,
|
| 342 |
+
"learning_rate": 2.3616424778246173e-05,
|
| 343 |
+
"loss": 1.5514,
|
| 344 |
+
"step": 560
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.06,
|
| 348 |
+
"learning_rate": 2.2889662120434453e-05,
|
| 349 |
+
"loss": 1.5427,
|
| 350 |
+
"step": 570
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.08,
|
| 354 |
+
"learning_rate": 2.216469165027406e-05,
|
| 355 |
+
"loss": 1.5428,
|
| 356 |
+
"step": 580
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.09,
|
| 360 |
+
"learning_rate": 2.1442129043167874e-05,
|
| 361 |
+
"loss": 1.5441,
|
| 362 |
+
"step": 590
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.11,
|
| 366 |
+
"learning_rate": 2.0722587929660227e-05,
|
| 367 |
+
"loss": 1.552,
|
| 368 |
+
"step": 600
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.13,
|
| 372 |
+
"learning_rate": 2.0006679374316062e-05,
|
| 373 |
+
"loss": 1.5555,
|
| 374 |
+
"step": 610
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.15,
|
| 378 |
+
"learning_rate": 1.9295011356779192e-05,
|
| 379 |
+
"loss": 1.5504,
|
| 380 |
+
"step": 620
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.17,
|
| 384 |
+
"learning_rate": 1.8588188255450466e-05,
|
| 385 |
+
"loss": 1.5452,
|
| 386 |
+
"step": 630
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.19,
|
| 390 |
+
"learning_rate": 1.7886810334224192e-05,
|
| 391 |
+
"loss": 1.5502,
|
| 392 |
+
"step": 640
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.21,
|
| 396 |
+
"learning_rate": 1.7191473232718774e-05,
|
| 397 |
+
"loss": 1.556,
|
| 398 |
+
"step": 650
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.22,
|
| 402 |
+
"learning_rate": 1.6502767460434588e-05,
|
| 403 |
+
"loss": 1.5419,
|
| 404 |
+
"step": 660
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.24,
|
| 408 |
+
"learning_rate": 1.582127789526838e-05,
|
| 409 |
+
"loss": 1.5528,
|
| 410 |
+
"step": 670
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.26,
|
| 414 |
+
"learning_rate": 1.5147583286810485e-05,
|
| 415 |
+
"loss": 1.545,
|
| 416 |
+
"step": 680
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.28,
|
| 420 |
+
"learning_rate": 1.4482255764846225e-05,
|
| 421 |
+
"loss": 1.5433,
|
| 422 |
+
"step": 690
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.3,
|
| 426 |
+
"learning_rate": 1.3825860353479336e-05,
|
| 427 |
+
"loss": 1.551,
|
| 428 |
+
"step": 700
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.32,
|
| 432 |
+
"learning_rate": 1.3178954491289692e-05,
|
| 433 |
+
"loss": 1.5424,
|
| 434 |
+
"step": 710
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.34,
|
| 438 |
+
"learning_rate": 1.2542087557933041e-05,
|
| 439 |
+
"loss": 1.5426,
|
| 440 |
+
"step": 720
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.35,
|
| 444 |
+
"learning_rate": 1.1915800407584704e-05,
|
| 445 |
+
"loss": 1.5555,
|
| 446 |
+
"step": 730
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.37,
|
| 450 |
+
"learning_rate": 1.1300624909623463e-05,
|
| 451 |
+
"loss": 1.5335,
|
| 452 |
+
"step": 740
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.39,
|
| 456 |
+
"learning_rate": 1.0697083496945765e-05,
|
| 457 |
+
"loss": 1.5446,
|
| 458 |
+
"step": 750
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.41,
|
| 462 |
+
"learning_rate": 1.0105688722293643e-05,
|
| 463 |
+
"loss": 1.5422,
|
| 464 |
+
"step": 760
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.43,
|
| 468 |
+
"learning_rate": 9.526942822973522e-06,
|
| 469 |
+
"loss": 1.548,
|
| 470 |
+
"step": 770
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.45,
|
| 474 |
+
"learning_rate": 8.961337294335021e-06,
|
| 475 |
+
"loss": 1.5436,
|
| 476 |
+
"step": 780
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.46,
|
| 480 |
+
"learning_rate": 8.409352472372595e-06,
|
| 481 |
+
"loss": 1.5483,
|
| 482 |
+
"step": 790
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.48,
|
| 486 |
+
"learning_rate": 7.871457125803896e-06,
|
| 487 |
+
"loss": 1.5348,
|
| 488 |
+
"step": 800
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.5,
|
| 492 |
+
"learning_rate": 7.348108057971728e-06,
|
| 493 |
+
"loss": 1.5309,
|
| 494 |
+
"step": 810
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.52,
|
| 498 |
+
"learning_rate": 6.839749718907429e-06,
|
| 499 |
+
"loss": 1.5343,
|
| 500 |
+
"step": 820
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.54,
|
| 504 |
+
"learning_rate": 6.3468138278852174e-06,
|
| 505 |
+
"loss": 1.5446,
|
| 506 |
+
"step": 830
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.56,
|
| 510 |
+
"learning_rate": 5.8697190067880325e-06,
|
| 511 |
+
"loss": 1.5381,
|
| 512 |
+
"step": 840
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.58,
|
| 516 |
+
"learning_rate": 5.408870424596238e-06,
|
| 517 |
+
"loss": 1.5483,
|
| 518 |
+
"step": 850
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.59,
|
| 522 |
+
"learning_rate": 4.9646594533010875e-06,
|
| 523 |
+
"loss": 1.5466,
|
| 524 |
+
"step": 860
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.61,
|
| 528 |
+
"learning_rate": 4.537463335535161e-06,
|
| 529 |
+
"loss": 1.5397,
|
| 530 |
+
"step": 870
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.63,
|
| 534 |
+
"learning_rate": 4.127644864202104e-06,
|
| 535 |
+
"loss": 1.5355,
|
| 536 |
+
"step": 880
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.65,
|
| 540 |
+
"learning_rate": 3.735552074377563e-06,
|
| 541 |
+
"loss": 1.5409,
|
| 542 |
+
"step": 890
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.67,
|
| 546 |
+
"learning_rate": 3.3615179477432645e-06,
|
| 547 |
+
"loss": 1.5383,
|
| 548 |
+
"step": 900
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.69,
|
| 552 |
+
"learning_rate": 3.0058601298048774e-06,
|
| 553 |
+
"loss": 1.5338,
|
| 554 |
+
"step": 910
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.71,
|
| 558 |
+
"learning_rate": 2.6688806601341765e-06,
|
| 559 |
+
"loss": 1.5384,
|
| 560 |
+
"step": 920
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.72,
|
| 564 |
+
"learning_rate": 2.350865715864278e-06,
|
| 565 |
+
"loss": 1.5305,
|
| 566 |
+
"step": 930
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.74,
|
| 570 |
+
"learning_rate": 2.0520853686560178e-06,
|
| 571 |
+
"loss": 1.5344,
|
| 572 |
+
"step": 940
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 1.76,
|
| 576 |
+
"learning_rate": 1.772793355341734e-06,
|
| 577 |
+
"loss": 1.5363,
|
| 578 |
+
"step": 950
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.78,
|
| 582 |
+
"learning_rate": 1.513226862441286e-06,
|
| 583 |
+
"loss": 1.5468,
|
| 584 |
+
"step": 960
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.8,
|
| 588 |
+
"learning_rate": 1.273606324733284e-06,
|
| 589 |
+
"loss": 1.5369,
|
| 590 |
+
"step": 970
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.82,
|
| 594 |
+
"learning_rate": 1.0541352380526087e-06,
|
| 595 |
+
"loss": 1.5428,
|
| 596 |
+
"step": 980
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.84,
|
| 600 |
+
"learning_rate": 8.549999864732011e-07,
|
| 601 |
+
"loss": 1.5338,
|
| 602 |
+
"step": 990
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.85,
|
| 606 |
+
"learning_rate": 6.763696840228456e-07,
|
| 607 |
+
"loss": 1.5399,
|
| 608 |
+
"step": 1000
|
| 609 |
+
}
|
| 610 |
+
],
|
| 611 |
+
"max_steps": 1078,
|
| 612 |
+
"num_train_epochs": 2,
|
| 613 |
+
"total_flos": 2.489434826550018e+18,
|
| 614 |
+
"trial_name": null,
|
| 615 |
+
"trial_params": null
|
| 616 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b69ea6b9f79d50f0ca7b5a2476627c8e100b6bcda45f5e45dfaba3d805792111
|
| 3 |
+
size 3264
|
finetuning_args.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dpo_beta": 0.1,
|
| 3 |
+
"finetuning_type": "lora",
|
| 4 |
+
"lora_alpha": 32.0,
|
| 5 |
+
"lora_dropout": 0.1,
|
| 6 |
+
"lora_rank": 8,
|
| 7 |
+
"lora_target": [
|
| 8 |
+
"W_pack"
|
| 9 |
+
],
|
| 10 |
+
"name_module_trainable": "mlp",
|
| 11 |
+
"num_hidden_layers": 32,
|
| 12 |
+
"num_layer_trainable": 3,
|
| 13 |
+
"ppo_score_norm": false,
|
| 14 |
+
"resume_lora_training": true
|
| 15 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 1.5770846359804964,
|
| 4 |
+
"train_runtime": 13419.9836,
|
| 5 |
+
"train_samples_per_second": 10.287,
|
| 6 |
+
"train_steps_per_second": 0.08
|
| 7 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 1078, "loss": 2.0078, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.998938447446803e-05, "epoch": 0.02, "percentage": 0.93, "elapsed_time": "0:02:04", "remaining_time": "3:41:58"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 1078, "loss": 1.8414, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9957546913022665e-05, "epoch": 0.04, "percentage": 1.86, "elapsed_time": "0:04:05", "remaining_time": "3:36:37"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 1078, "loss": 1.7763, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9904514353459654e-05, "epoch": 0.06, "percentage": 2.78, "elapsed_time": "0:06:11", "remaining_time": "3:36:07"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 1078, "loss": 1.7278, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.983033183325818e-05, "epoch": 0.07, "percentage": 3.71, "elapsed_time": "0:08:13", "remaining_time": "3:33:24"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 1078, "loss": 1.7139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.973506235133323e-05, "epoch": 0.09, "percentage": 4.64, "elapsed_time": "0:10:18", "remaining_time": "3:32:00"}
|
| 6 |
+
{"current_steps": 60, "total_steps": 1078, "loss": 1.6947, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.96313569658781e-05, "epoch": 0.11, "percentage": 5.57, "elapsed_time": "0:12:23", "remaining_time": "3:30:12"}
|
| 7 |
+
{"current_steps": 70, "total_steps": 1078, "loss": 1.6749, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.94962599008322e-05, "epoch": 0.13, "percentage": 6.49, "elapsed_time": "0:14:25", "remaining_time": "3:27:46"}
|
| 8 |
+
{"current_steps": 80, "total_steps": 1078, "loss": 1.6579, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9340359581993066e-05, "epoch": 0.15, "percentage": 7.42, "elapsed_time": "0:16:31", "remaining_time": "3:26:09"}
|
| 9 |
+
{"current_steps": 90, "total_steps": 1078, "loss": 1.6499, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.916378840646592e-05, "epoch": 0.17, "percentage": 8.35, "elapsed_time": "0:18:34", "remaining_time": "3:23:59"}
|
| 10 |
+
{"current_steps": 100, "total_steps": 1078, "loss": 1.6507, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8966696325916515e-05, "epoch": 0.19, "percentage": 9.28, "elapsed_time": "0:20:40", "remaining_time": "3:22:09"}
|
| 11 |
+
{"current_steps": 110, "total_steps": 1078, "loss": 1.6426, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8749250719225915e-05, "epoch": 0.2, "percentage": 10.2, "elapsed_time": "0:22:45", "remaining_time": "3:20:14"}
|
| 12 |
+
{"current_steps": 120, "total_steps": 1078, "loss": 1.6288, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8511636250345294e-05, "epoch": 0.22, "percentage": 11.13, "elapsed_time": "0:24:47", "remaining_time": "3:17:51"}
|
| 13 |
+
{"current_steps": 130, "total_steps": 1078, "loss": 1.6265, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.825405471147153e-05, "epoch": 0.24, "percentage": 12.06, "elapsed_time": "0:26:53", "remaining_time": "3:16:06"}
|
| 14 |
+
{"current_steps": 140, "total_steps": 1078, "loss": 1.6252, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.797672485167683e-05, "epoch": 0.26, "percentage": 12.99, "elapsed_time": "0:29:02", "remaining_time": "3:14:34"}
|
| 15 |
+
{"current_steps": 150, "total_steps": 1078, "loss": 1.6218, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7679882191137804e-05, "epoch": 0.28, "percentage": 13.91, "elapsed_time": "0:31:04", "remaining_time": "3:12:14"}
|
| 16 |
+
{"current_steps": 160, "total_steps": 1078, "loss": 1.6146, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7363778821121784e-05, "epoch": 0.3, "percentage": 14.84, "elapsed_time": "0:33:07", "remaining_time": "3:10:03"}
|
| 17 |
+
{"current_steps": 170, "total_steps": 1078, "loss": 1.604, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.702868318990039e-05, "epoch": 0.32, "percentage": 15.77, "elapsed_time": "0:35:18", "remaining_time": "3:08:34"}
|
| 18 |
+
{"current_steps": 180, "total_steps": 1078, "loss": 1.607, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6674879874771926e-05, "epoch": 0.33, "percentage": 16.7, "elapsed_time": "0:37:28", "remaining_time": "3:06:59"}
|
| 19 |
+
{"current_steps": 190, "total_steps": 1078, "loss": 1.5972, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.630266934038642e-05, "epoch": 0.35, "percentage": 17.63, "elapsed_time": "0:39:31", "remaining_time": "3:04:45"}
|
| 20 |
+
{"current_steps": 200, "total_steps": 1078, "loss": 1.5973, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.591236768357833e-05, "epoch": 0.37, "percentage": 18.55, "elapsed_time": "0:41:37", "remaining_time": "3:02:43"}
|
| 21 |
+
{"current_steps": 210, "total_steps": 1078, "loss": 1.6043, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.55043063649239e-05, "epoch": 0.39, "percentage": 19.48, "elapsed_time": "0:43:42", "remaining_time": "3:00:37"}
|
| 22 |
+
{"current_steps": 220, "total_steps": 1078, "loss": 1.5839, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.507883192725089e-05, "epoch": 0.41, "percentage": 20.41, "elapsed_time": "0:45:44", "remaining_time": "2:58:22"}
|
| 23 |
+
{"current_steps": 230, "total_steps": 1078, "loss": 1.5923, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.463630570133978e-05, "epoch": 0.43, "percentage": 21.34, "elapsed_time": "0:47:51", "remaining_time": "2:56:25"}
|
| 24 |
+
{"current_steps": 240, "total_steps": 1078, "loss": 1.5841, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.417710349906658e-05, "epoch": 0.45, "percentage": 22.26, "elapsed_time": "0:49:55", "remaining_time": "2:54:20"}
|
| 25 |
+
{"current_steps": 250, "total_steps": 1078, "loss": 1.5977, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3701615294247465e-05, "epoch": 0.46, "percentage": 23.19, "elapsed_time": "0:51:59", "remaining_time": "2:52:12"}
|
| 26 |
+
{"current_steps": 260, "total_steps": 1078, "loss": 1.5954, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.321024489145673e-05, "epoch": 0.48, "percentage": 24.12, "elapsed_time": "0:54:00", "remaining_time": "2:49:55"}
|
| 27 |
+
{"current_steps": 270, "total_steps": 1078, "loss": 1.5914, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.270340958309888e-05, "epoch": 0.5, "percentage": 25.05, "elapsed_time": "0:56:06", "remaining_time": "2:47:55"}
|
| 28 |
+
{"current_steps": 280, "total_steps": 1078, "loss": 1.577, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.2181539795026435e-05, "epoch": 0.52, "percentage": 25.97, "elapsed_time": "0:58:07", "remaining_time": "2:45:38"}
|
| 29 |
+
{"current_steps": 290, "total_steps": 1078, "loss": 1.576, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1645078721004174e-05, "epoch": 0.54, "percentage": 26.9, "elapsed_time": "1:00:09", "remaining_time": "2:43:28"}
|
| 30 |
+
{"current_steps": 300, "total_steps": 1078, "loss": 1.5771, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.109448194633033e-05, "epoch": 0.56, "percentage": 27.83, "elapsed_time": "1:02:11", "remaining_time": "2:41:17"}
|
| 31 |
+
{"current_steps": 310, "total_steps": 1078, "loss": 1.5825, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.0530217060934466e-05, "epoch": 0.57, "percentage": 28.76, "elapsed_time": "1:04:20", "remaining_time": "2:39:24"}
|
| 32 |
+
{"current_steps": 320, "total_steps": 1078, "loss": 1.581, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9952763262280405e-05, "epoch": 0.59, "percentage": 29.68, "elapsed_time": "1:06:22", "remaining_time": "2:37:13"}
|
| 33 |
+
{"current_steps": 330, "total_steps": 1078, "loss": 1.5691, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9362610948411585e-05, "epoch": 0.61, "percentage": 30.61, "elapsed_time": "1:08:29", "remaining_time": "2:35:13"}
|
| 34 |
+
{"current_steps": 340, "total_steps": 1078, "loss": 1.5795, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8760261301484466e-05, "epoch": 0.63, "percentage": 31.54, "elapsed_time": "1:10:31", "remaining_time": "2:33:04"}
|
| 35 |
+
{"current_steps": 350, "total_steps": 1078, "loss": 1.5847, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8208140480771856e-05, "epoch": 0.65, "percentage": 32.47, "elapsed_time": "1:12:35", "remaining_time": "2:30:58"}
|
| 36 |
+
{"current_steps": 360, "total_steps": 1078, "loss": 1.5737, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.758403340686345e-05, "epoch": 0.67, "percentage": 33.4, "elapsed_time": "1:14:37", "remaining_time": "2:28:51"}
|
| 37 |
+
{"current_steps": 370, "total_steps": 1078, "loss": 1.5645, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6949239442720976e-05, "epoch": 0.69, "percentage": 34.32, "elapsed_time": "1:16:46", "remaining_time": "2:26:54"}
|
| 38 |
+
{"current_steps": 380, "total_steps": 1078, "loss": 1.5659, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6304297682067144e-05, "epoch": 0.7, "percentage": 35.25, "elapsed_time": "1:18:55", "remaining_time": "2:24:58"}
|
| 39 |
+
{"current_steps": 390, "total_steps": 1078, "loss": 1.5613, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5649755836560106e-05, "epoch": 0.72, "percentage": 36.18, "elapsed_time": "1:21:02", "remaining_time": "2:22:57"}
|
| 40 |
+
{"current_steps": 400, "total_steps": 1078, "loss": 1.5725, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.4986169770653685e-05, "epoch": 0.74, "percentage": 37.11, "elapsed_time": "1:23:05", "remaining_time": "2:20:50"}
|
| 41 |
+
{"current_steps": 410, "total_steps": 1078, "loss": 1.5619, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.431410302953389e-05, "epoch": 0.76, "percentage": 38.03, "elapsed_time": "1:25:17", "remaining_time": "2:18:57"}
|
| 42 |
+
{"current_steps": 420, "total_steps": 1078, "loss": 1.5615, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.363412636053269e-05, "epoch": 0.78, "percentage": 38.96, "elapsed_time": "1:27:19", "remaining_time": "2:16:48"}
|
| 43 |
+
{"current_steps": 430, "total_steps": 1078, "loss": 1.5623, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.294681722842537e-05, "epoch": 0.8, "percentage": 39.89, "elapsed_time": "1:29:22", "remaining_time": "2:14:40"}
|
| 44 |
+
{"current_steps": 440, "total_steps": 1078, "loss": 1.5685, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.225275932502315e-05, "epoch": 0.82, "percentage": 40.82, "elapsed_time": "1:31:28", "remaining_time": "2:12:38"}
|
| 45 |
+
{"current_steps": 450, "total_steps": 1078, "loss": 1.566, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.1552542073477555e-05, "epoch": 0.83, "percentage": 41.74, "elapsed_time": "1:33:32", "remaining_time": "2:10:31"}
|
| 46 |
+
{"current_steps": 460, "total_steps": 1078, "loss": 1.5643, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.084676012771753e-05, "epoch": 0.85, "percentage": 42.67, "elapsed_time": "1:35:32", "remaining_time": "2:08:21"}
|
| 47 |
+
{"current_steps": 470, "total_steps": 1078, "loss": 1.5588, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0136012867444297e-05, "epoch": 0.87, "percentage": 43.6, "elapsed_time": "1:37:35", "remaining_time": "2:06:15"}
|
| 48 |
+
{"current_steps": 480, "total_steps": 1078, "loss": 1.5598, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.942090388911291e-05, "epoch": 0.89, "percentage": 44.53, "elapsed_time": "1:39:45", "remaining_time": "2:04:16"}
|
| 49 |
+
{"current_steps": 490, "total_steps": 1078, "loss": 1.5618, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8702040493332778e-05, "epoch": 0.91, "percentage": 45.45, "elapsed_time": "1:41:52", "remaining_time": "2:02:15"}
|
| 50 |
+
{"current_steps": 500, "total_steps": 1078, "loss": 1.5602, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7980033169122454e-05, "epoch": 0.93, "percentage": 46.38, "elapsed_time": "1:43:57", "remaining_time": "2:00:10"}
|
| 51 |
+
{"current_steps": 510, "total_steps": 1078, "loss": 1.5453, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7255495075456693e-05, "epoch": 0.95, "percentage": 47.31, "elapsed_time": "1:46:04", "remaining_time": "1:58:08"}
|
| 52 |
+
{"current_steps": 520, "total_steps": 1078, "loss": 1.5557, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.652904152054607e-05, "epoch": 0.96, "percentage": 48.24, "elapsed_time": "1:48:04", "remaining_time": "1:55:58"}
|
| 53 |
+
{"current_steps": 530, "total_steps": 1078, "loss": 1.5493, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5801289439291388e-05, "epoch": 0.98, "percentage": 49.17, "elapsed_time": "1:50:10", "remaining_time": "1:53:55"}
|
| 54 |
+
{"current_steps": 540, "total_steps": 1078, "loss": 1.5527, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5072856869356593e-05, "epoch": 1.0, "percentage": 50.09, "elapsed_time": "1:52:15", "remaining_time": "1:51:50"}
|
| 55 |
+
{"current_steps": 550, "total_steps": 1078, "loss": 1.5564, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4344362426305255e-05, "epoch": 1.02, "percentage": 51.02, "elapsed_time": "1:54:18", "remaining_time": "1:49:44"}
|
| 56 |
+
{"current_steps": 560, "total_steps": 1078, "loss": 1.5514, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3616424778246173e-05, "epoch": 1.04, "percentage": 51.95, "elapsed_time": "1:56:22", "remaining_time": "1:47:38"}
|
| 57 |
+
{"current_steps": 570, "total_steps": 1078, "loss": 1.5427, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2889662120434453e-05, "epoch": 1.06, "percentage": 52.88, "elapsed_time": "1:58:25", "remaining_time": "1:45:32"}
|
| 58 |
+
{"current_steps": 580, "total_steps": 1078, "loss": 1.5428, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.216469165027406e-05, "epoch": 1.08, "percentage": 53.8, "elapsed_time": "2:00:33", "remaining_time": "1:43:30"}
|
| 59 |
+
{"current_steps": 590, "total_steps": 1078, "loss": 1.5441, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1442129043167874e-05, "epoch": 1.09, "percentage": 54.73, "elapsed_time": "2:02:36", "remaining_time": "1:41:24"}
|
| 60 |
+
{"current_steps": 600, "total_steps": 1078, "loss": 1.552, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0722587929660227e-05, "epoch": 1.11, "percentage": 55.66, "elapsed_time": "2:04:41", "remaining_time": "1:39:20"}
|
| 61 |
+
{"current_steps": 610, "total_steps": 1078, "loss": 1.5555, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0006679374316062e-05, "epoch": 1.13, "percentage": 56.59, "elapsed_time": "2:06:44", "remaining_time": "1:37:14"}
|
| 62 |
+
{"current_steps": 620, "total_steps": 1078, "loss": 1.5504, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9295011356779192e-05, "epoch": 1.15, "percentage": 57.51, "elapsed_time": "2:08:51", "remaining_time": "1:35:11"}
|
| 63 |
+
{"current_steps": 630, "total_steps": 1078, "loss": 1.5452, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8588188255450466e-05, "epoch": 1.17, "percentage": 58.44, "elapsed_time": "2:10:52", "remaining_time": "1:33:03"}
|
| 64 |
+
{"current_steps": 640, "total_steps": 1078, "loss": 1.5502, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7886810334224192e-05, "epoch": 1.19, "percentage": 59.37, "elapsed_time": "2:12:57", "remaining_time": "1:30:59"}
|
| 65 |
+
{"current_steps": 650, "total_steps": 1078, "loss": 1.556, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7191473232718774e-05, "epoch": 1.21, "percentage": 60.3, "elapsed_time": "2:14:58", "remaining_time": "1:28:52"}
|
| 66 |
+
{"current_steps": 660, "total_steps": 1078, "loss": 1.5419, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6502767460434588e-05, "epoch": 1.22, "percentage": 61.22, "elapsed_time": "2:17:04", "remaining_time": "1:26:48"}
|
| 67 |
+
{"current_steps": 670, "total_steps": 1078, "loss": 1.5528, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.582127789526838e-05, "epoch": 1.24, "percentage": 62.15, "elapsed_time": "2:19:05", "remaining_time": "1:24:42"}
|
| 68 |
+
{"current_steps": 680, "total_steps": 1078, "loss": 1.545, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5147583286810485e-05, "epoch": 1.26, "percentage": 63.08, "elapsed_time": "2:21:05", "remaining_time": "1:22:34"}
|
| 69 |
+
{"current_steps": 690, "total_steps": 1078, "loss": 1.5433, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4482255764846225e-05, "epoch": 1.28, "percentage": 64.01, "elapsed_time": "2:23:07", "remaining_time": "1:20:29"}
|
| 70 |
+
{"current_steps": 700, "total_steps": 1078, "loss": 1.551, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3825860353479336e-05, "epoch": 1.3, "percentage": 64.94, "elapsed_time": "2:25:10", "remaining_time": "1:18:23"}
|
| 71 |
+
{"current_steps": 710, "total_steps": 1078, "loss": 1.5424, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3178954491289692e-05, "epoch": 1.32, "percentage": 65.86, "elapsed_time": "2:27:17", "remaining_time": "1:16:20"}
|
| 72 |
+
{"current_steps": 720, "total_steps": 1078, "loss": 1.5426, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2542087557933041e-05, "epoch": 1.34, "percentage": 66.79, "elapsed_time": "2:29:26", "remaining_time": "1:14:18"}
|
| 73 |
+
{"current_steps": 730, "total_steps": 1078, "loss": 1.5555, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1915800407584704e-05, "epoch": 1.35, "percentage": 67.72, "elapsed_time": "2:31:27", "remaining_time": "1:12:12"}
|
| 74 |
+
{"current_steps": 740, "total_steps": 1078, "loss": 1.5335, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1300624909623463e-05, "epoch": 1.37, "percentage": 68.65, "elapsed_time": "2:33:33", "remaining_time": "1:10:08"}
|
| 75 |
+
{"current_steps": 750, "total_steps": 1078, "loss": 1.5446, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0697083496945765e-05, "epoch": 1.39, "percentage": 69.57, "elapsed_time": "2:35:37", "remaining_time": "1:08:03"}
|
| 76 |
+
{"current_steps": 760, "total_steps": 1078, "loss": 1.5422, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0105688722293643e-05, "epoch": 1.41, "percentage": 70.5, "elapsed_time": "2:37:41", "remaining_time": "1:05:59"}
|
| 77 |
+
{"current_steps": 770, "total_steps": 1078, "loss": 1.548, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.526942822973522e-06, "epoch": 1.43, "percentage": 71.43, "elapsed_time": "2:39:41", "remaining_time": "1:03:52"}
|
| 78 |
+
{"current_steps": 780, "total_steps": 1078, "loss": 1.5436, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.961337294335021e-06, "epoch": 1.45, "percentage": 72.36, "elapsed_time": "2:41:41", "remaining_time": "1:01:46"}
|
| 79 |
+
{"current_steps": 790, "total_steps": 1078, "loss": 1.5483, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.409352472372595e-06, "epoch": 1.46, "percentage": 73.28, "elapsed_time": "2:43:50", "remaining_time": "0:59:43"}
|
| 80 |
+
{"current_steps": 800, "total_steps": 1078, "loss": 1.5348, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.871457125803896e-06, "epoch": 1.48, "percentage": 74.21, "elapsed_time": "2:45:53", "remaining_time": "0:57:38"}
|
| 81 |
+
{"current_steps": 810, "total_steps": 1078, "loss": 1.5309, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.348108057971728e-06, "epoch": 1.5, "percentage": 75.14, "elapsed_time": "2:47:54", "remaining_time": "0:55:33"}
|
| 82 |
+
{"current_steps": 820, "total_steps": 1078, "loss": 1.5343, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.839749718907429e-06, "epoch": 1.52, "percentage": 76.07, "elapsed_time": "2:49:54", "remaining_time": "0:53:27"}
|
| 83 |
+
{"current_steps": 830, "total_steps": 1078, "loss": 1.5446, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.3468138278852174e-06, "epoch": 1.54, "percentage": 76.99, "elapsed_time": "2:51:58", "remaining_time": "0:51:23"}
|
| 84 |
+
{"current_steps": 840, "total_steps": 1078, "loss": 1.5381, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.8697190067880325e-06, "epoch": 1.56, "percentage": 77.92, "elapsed_time": "2:54:02", "remaining_time": "0:49:18"}
|
| 85 |
+
{"current_steps": 850, "total_steps": 1078, "loss": 1.5483, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.408870424596238e-06, "epoch": 1.58, "percentage": 78.85, "elapsed_time": "2:56:07", "remaining_time": "0:47:14"}
|
| 86 |
+
{"current_steps": 860, "total_steps": 1078, "loss": 1.5466, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9646594533010875e-06, "epoch": 1.59, "percentage": 79.78, "elapsed_time": "2:58:08", "remaining_time": "0:45:09"}
|
| 87 |
+
{"current_steps": 870, "total_steps": 1078, "loss": 1.5397, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.537463335535161e-06, "epoch": 1.61, "percentage": 80.71, "elapsed_time": "3:00:12", "remaining_time": "0:43:05"}
|
| 88 |
+
{"current_steps": 880, "total_steps": 1078, "loss": 1.5355, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.127644864202104e-06, "epoch": 1.63, "percentage": 81.63, "elapsed_time": "3:02:16", "remaining_time": "0:41:00"}
|
| 89 |
+
{"current_steps": 890, "total_steps": 1078, "loss": 1.5409, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.735552074377563e-06, "epoch": 1.65, "percentage": 82.56, "elapsed_time": "3:04:21", "remaining_time": "0:38:56"}
|
| 90 |
+
{"current_steps": 900, "total_steps": 1078, "loss": 1.5383, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3615179477432645e-06, "epoch": 1.67, "percentage": 83.49, "elapsed_time": "3:06:27", "remaining_time": "0:36:52"}
|
| 91 |
+
{"current_steps": 910, "total_steps": 1078, "loss": 1.5338, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0058601298048774e-06, "epoch": 1.69, "percentage": 84.42, "elapsed_time": "3:08:29", "remaining_time": "0:34:47"}
|
| 92 |
+
{"current_steps": 920, "total_steps": 1078, "loss": 1.5384, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6688806601341765e-06, "epoch": 1.71, "percentage": 85.34, "elapsed_time": "3:10:36", "remaining_time": "0:32:44"}
|
| 93 |
+
{"current_steps": 930, "total_steps": 1078, "loss": 1.5305, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.350865715864278e-06, "epoch": 1.72, "percentage": 86.27, "elapsed_time": "3:12:40", "remaining_time": "0:30:39"}
|
| 94 |
+
{"current_steps": 940, "total_steps": 1078, "loss": 1.5344, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0520853686560178e-06, "epoch": 1.74, "percentage": 87.2, "elapsed_time": "3:14:43", "remaining_time": "0:28:35"}
|
| 95 |
+
{"current_steps": 950, "total_steps": 1078, "loss": 1.5363, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.772793355341734e-06, "epoch": 1.76, "percentage": 88.13, "elapsed_time": "3:16:48", "remaining_time": "0:26:30"}
|
| 96 |
+
{"current_steps": 960, "total_steps": 1078, "loss": 1.5468, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.513226862441286e-06, "epoch": 1.78, "percentage": 89.05, "elapsed_time": "3:18:51", "remaining_time": "0:24:26"}
|
| 97 |
+
{"current_steps": 970, "total_steps": 1078, "loss": 1.5369, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.273606324733284e-06, "epoch": 1.8, "percentage": 89.98, "elapsed_time": "3:20:55", "remaining_time": "0:22:22"}
|
| 98 |
+
{"current_steps": 980, "total_steps": 1078, "loss": 1.5428, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0541352380526087e-06, "epoch": 1.82, "percentage": 90.91, "elapsed_time": "3:23:03", "remaining_time": "0:20:18"}
|
| 99 |
+
{"current_steps": 990, "total_steps": 1078, "loss": 1.5338, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.549999864732011e-07, "epoch": 1.84, "percentage": 91.84, "elapsed_time": "3:25:14", "remaining_time": "0:18:14"}
|
| 100 |
+
{"current_steps": 1000, "total_steps": 1078, "loss": 1.5399, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.763696840228456e-07, "epoch": 1.85, "percentage": 92.76, "elapsed_time": "3:27:17", "remaining_time": "0:16:10"}
|
| 101 |
+
{"current_steps": 1010, "total_steps": 1078, "loss": 1.5406, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.183960310644748e-07, "epoch": 1.87, "percentage": 93.69, "elapsed_time": "3:29:21", "remaining_time": "0:14:05"}
|
| 102 |
+
{"current_steps": 1020, "total_steps": 1078, "loss": 1.5381, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.812131854657813e-07, "epoch": 1.89, "percentage": 94.62, "elapsed_time": "3:31:29", "remaining_time": "0:12:01"}
|
| 103 |
+
{"current_steps": 1030, "total_steps": 1078, "loss": 1.5354, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.649376486667743e-07, "epoch": 1.91, "percentage": 95.55, "elapsed_time": "3:33:35", "remaining_time": "0:09:57"}
|
| 104 |
+
{"current_steps": 1040, "total_steps": 1078, "loss": 1.5358, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6966816674182373e-07, "epoch": 1.93, "percentage": 96.47, "elapsed_time": "3:35:41", "remaining_time": "0:07:52"}
|
| 105 |
+
{"current_steps": 1050, "total_steps": 1078, "loss": 1.5481, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.019530491929821e-07, "epoch": 1.95, "percentage": 97.4, "elapsed_time": "3:37:50", "remaining_time": "0:05:48"}
|
| 106 |
+
{"current_steps": 1060, "total_steps": 1078, "loss": 1.5504, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.680317016582669e-08, "epoch": 1.97, "percentage": 98.33, "elapsed_time": "3:39:54", "remaining_time": "0:03:44"}
|
| 107 |
+
{"current_steps": 1070, "total_steps": 1078, "loss": 1.5429, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.284459498280266e-08, "epoch": 1.98, "percentage": 99.26, "elapsed_time": "3:41:57", "remaining_time": "0:01:39"}
|
| 108 |
+
{"current_steps": 1078, "total_steps": 1078, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "3:43:39", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,667 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.999072786277237,
|
| 5 |
+
"global_step": 1078,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 4.998938447446803e-05,
|
| 13 |
+
"loss": 2.0078,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"learning_rate": 4.9957546913022665e-05,
|
| 19 |
+
"loss": 1.8414,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.06,
|
| 24 |
+
"learning_rate": 4.9904514353459654e-05,
|
| 25 |
+
"loss": 1.7763,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.07,
|
| 30 |
+
"learning_rate": 4.983033183325818e-05,
|
| 31 |
+
"loss": 1.7278,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.09,
|
| 36 |
+
"learning_rate": 4.973506235133323e-05,
|
| 37 |
+
"loss": 1.7139,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.11,
|
| 42 |
+
"learning_rate": 4.96313569658781e-05,
|
| 43 |
+
"loss": 1.6947,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.13,
|
| 48 |
+
"learning_rate": 4.94962599008322e-05,
|
| 49 |
+
"loss": 1.6749,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.15,
|
| 54 |
+
"learning_rate": 4.9340359581993066e-05,
|
| 55 |
+
"loss": 1.6579,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.17,
|
| 60 |
+
"learning_rate": 4.916378840646592e-05,
|
| 61 |
+
"loss": 1.6499,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.19,
|
| 66 |
+
"learning_rate": 4.8966696325916515e-05,
|
| 67 |
+
"loss": 1.6507,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.2,
|
| 72 |
+
"learning_rate": 4.8749250719225915e-05,
|
| 73 |
+
"loss": 1.6426,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.22,
|
| 78 |
+
"learning_rate": 4.8511636250345294e-05,
|
| 79 |
+
"loss": 1.6288,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.24,
|
| 84 |
+
"learning_rate": 4.825405471147153e-05,
|
| 85 |
+
"loss": 1.6265,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.26,
|
| 90 |
+
"learning_rate": 4.797672485167683e-05,
|
| 91 |
+
"loss": 1.6252,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.28,
|
| 96 |
+
"learning_rate": 4.7679882191137804e-05,
|
| 97 |
+
"loss": 1.6218,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.3,
|
| 102 |
+
"learning_rate": 4.7363778821121784e-05,
|
| 103 |
+
"loss": 1.6146,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.32,
|
| 108 |
+
"learning_rate": 4.702868318990039e-05,
|
| 109 |
+
"loss": 1.604,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.33,
|
| 114 |
+
"learning_rate": 4.6674879874771926e-05,
|
| 115 |
+
"loss": 1.607,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.35,
|
| 120 |
+
"learning_rate": 4.630266934038642e-05,
|
| 121 |
+
"loss": 1.5972,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.37,
|
| 126 |
+
"learning_rate": 4.591236768357833e-05,
|
| 127 |
+
"loss": 1.5973,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.39,
|
| 132 |
+
"learning_rate": 4.55043063649239e-05,
|
| 133 |
+
"loss": 1.6043,
|
| 134 |
+
"step": 210
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.41,
|
| 138 |
+
"learning_rate": 4.507883192725089e-05,
|
| 139 |
+
"loss": 1.5839,
|
| 140 |
+
"step": 220
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.43,
|
| 144 |
+
"learning_rate": 4.463630570133978e-05,
|
| 145 |
+
"loss": 1.5923,
|
| 146 |
+
"step": 230
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.45,
|
| 150 |
+
"learning_rate": 4.417710349906658e-05,
|
| 151 |
+
"loss": 1.5841,
|
| 152 |
+
"step": 240
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.46,
|
| 156 |
+
"learning_rate": 4.3701615294247465e-05,
|
| 157 |
+
"loss": 1.5977,
|
| 158 |
+
"step": 250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.48,
|
| 162 |
+
"learning_rate": 4.321024489145673e-05,
|
| 163 |
+
"loss": 1.5954,
|
| 164 |
+
"step": 260
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.5,
|
| 168 |
+
"learning_rate": 4.270340958309888e-05,
|
| 169 |
+
"loss": 1.5914,
|
| 170 |
+
"step": 270
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.52,
|
| 174 |
+
"learning_rate": 4.2181539795026435e-05,
|
| 175 |
+
"loss": 1.577,
|
| 176 |
+
"step": 280
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.54,
|
| 180 |
+
"learning_rate": 4.1645078721004174e-05,
|
| 181 |
+
"loss": 1.576,
|
| 182 |
+
"step": 290
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.56,
|
| 186 |
+
"learning_rate": 4.109448194633033e-05,
|
| 187 |
+
"loss": 1.5771,
|
| 188 |
+
"step": 300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.57,
|
| 192 |
+
"learning_rate": 4.0530217060934466e-05,
|
| 193 |
+
"loss": 1.5825,
|
| 194 |
+
"step": 310
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.59,
|
| 198 |
+
"learning_rate": 3.9952763262280405e-05,
|
| 199 |
+
"loss": 1.581,
|
| 200 |
+
"step": 320
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.61,
|
| 204 |
+
"learning_rate": 3.9362610948411585e-05,
|
| 205 |
+
"loss": 1.5691,
|
| 206 |
+
"step": 330
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.63,
|
| 210 |
+
"learning_rate": 3.8760261301484466e-05,
|
| 211 |
+
"loss": 1.5795,
|
| 212 |
+
"step": 340
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.65,
|
| 216 |
+
"learning_rate": 3.8208140480771856e-05,
|
| 217 |
+
"loss": 1.5847,
|
| 218 |
+
"step": 350
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.67,
|
| 222 |
+
"learning_rate": 3.758403340686345e-05,
|
| 223 |
+
"loss": 1.5737,
|
| 224 |
+
"step": 360
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.69,
|
| 228 |
+
"learning_rate": 3.6949239442720976e-05,
|
| 229 |
+
"loss": 1.5645,
|
| 230 |
+
"step": 370
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.7,
|
| 234 |
+
"learning_rate": 3.6304297682067144e-05,
|
| 235 |
+
"loss": 1.5659,
|
| 236 |
+
"step": 380
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.72,
|
| 240 |
+
"learning_rate": 3.5649755836560106e-05,
|
| 241 |
+
"loss": 1.5613,
|
| 242 |
+
"step": 390
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.74,
|
| 246 |
+
"learning_rate": 3.4986169770653685e-05,
|
| 247 |
+
"loss": 1.5725,
|
| 248 |
+
"step": 400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.76,
|
| 252 |
+
"learning_rate": 3.431410302953389e-05,
|
| 253 |
+
"loss": 1.5619,
|
| 254 |
+
"step": 410
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.78,
|
| 258 |
+
"learning_rate": 3.363412636053269e-05,
|
| 259 |
+
"loss": 1.5615,
|
| 260 |
+
"step": 420
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.8,
|
| 264 |
+
"learning_rate": 3.294681722842537e-05,
|
| 265 |
+
"loss": 1.5623,
|
| 266 |
+
"step": 430
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.82,
|
| 270 |
+
"learning_rate": 3.225275932502315e-05,
|
| 271 |
+
"loss": 1.5685,
|
| 272 |
+
"step": 440
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.83,
|
| 276 |
+
"learning_rate": 3.1552542073477555e-05,
|
| 277 |
+
"loss": 1.566,
|
| 278 |
+
"step": 450
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.85,
|
| 282 |
+
"learning_rate": 3.084676012771753e-05,
|
| 283 |
+
"loss": 1.5643,
|
| 284 |
+
"step": 460
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.87,
|
| 288 |
+
"learning_rate": 3.0136012867444297e-05,
|
| 289 |
+
"loss": 1.5588,
|
| 290 |
+
"step": 470
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.89,
|
| 294 |
+
"learning_rate": 2.942090388911291e-05,
|
| 295 |
+
"loss": 1.5598,
|
| 296 |
+
"step": 480
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.91,
|
| 300 |
+
"learning_rate": 2.8702040493332778e-05,
|
| 301 |
+
"loss": 1.5618,
|
| 302 |
+
"step": 490
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.93,
|
| 306 |
+
"learning_rate": 2.7980033169122454e-05,
|
| 307 |
+
"loss": 1.5602,
|
| 308 |
+
"step": 500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.95,
|
| 312 |
+
"learning_rate": 2.7255495075456693e-05,
|
| 313 |
+
"loss": 1.5453,
|
| 314 |
+
"step": 510
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.96,
|
| 318 |
+
"learning_rate": 2.652904152054607e-05,
|
| 319 |
+
"loss": 1.5557,
|
| 320 |
+
"step": 520
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.98,
|
| 324 |
+
"learning_rate": 2.5801289439291388e-05,
|
| 325 |
+
"loss": 1.5493,
|
| 326 |
+
"step": 530
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.0,
|
| 330 |
+
"learning_rate": 2.5072856869356593e-05,
|
| 331 |
+
"loss": 1.5527,
|
| 332 |
+
"step": 540
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.02,
|
| 336 |
+
"learning_rate": 2.4344362426305255e-05,
|
| 337 |
+
"loss": 1.5564,
|
| 338 |
+
"step": 550
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.04,
|
| 342 |
+
"learning_rate": 2.3616424778246173e-05,
|
| 343 |
+
"loss": 1.5514,
|
| 344 |
+
"step": 560
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.06,
|
| 348 |
+
"learning_rate": 2.2889662120434453e-05,
|
| 349 |
+
"loss": 1.5427,
|
| 350 |
+
"step": 570
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.08,
|
| 354 |
+
"learning_rate": 2.216469165027406e-05,
|
| 355 |
+
"loss": 1.5428,
|
| 356 |
+
"step": 580
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.09,
|
| 360 |
+
"learning_rate": 2.1442129043167874e-05,
|
| 361 |
+
"loss": 1.5441,
|
| 362 |
+
"step": 590
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.11,
|
| 366 |
+
"learning_rate": 2.0722587929660227e-05,
|
| 367 |
+
"loss": 1.552,
|
| 368 |
+
"step": 600
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.13,
|
| 372 |
+
"learning_rate": 2.0006679374316062e-05,
|
| 373 |
+
"loss": 1.5555,
|
| 374 |
+
"step": 610
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.15,
|
| 378 |
+
"learning_rate": 1.9295011356779192e-05,
|
| 379 |
+
"loss": 1.5504,
|
| 380 |
+
"step": 620
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.17,
|
| 384 |
+
"learning_rate": 1.8588188255450466e-05,
|
| 385 |
+
"loss": 1.5452,
|
| 386 |
+
"step": 630
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.19,
|
| 390 |
+
"learning_rate": 1.7886810334224192e-05,
|
| 391 |
+
"loss": 1.5502,
|
| 392 |
+
"step": 640
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.21,
|
| 396 |
+
"learning_rate": 1.7191473232718774e-05,
|
| 397 |
+
"loss": 1.556,
|
| 398 |
+
"step": 650
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.22,
|
| 402 |
+
"learning_rate": 1.6502767460434588e-05,
|
| 403 |
+
"loss": 1.5419,
|
| 404 |
+
"step": 660
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.24,
|
| 408 |
+
"learning_rate": 1.582127789526838e-05,
|
| 409 |
+
"loss": 1.5528,
|
| 410 |
+
"step": 670
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.26,
|
| 414 |
+
"learning_rate": 1.5147583286810485e-05,
|
| 415 |
+
"loss": 1.545,
|
| 416 |
+
"step": 680
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.28,
|
| 420 |
+
"learning_rate": 1.4482255764846225e-05,
|
| 421 |
+
"loss": 1.5433,
|
| 422 |
+
"step": 690
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.3,
|
| 426 |
+
"learning_rate": 1.3825860353479336e-05,
|
| 427 |
+
"loss": 1.551,
|
| 428 |
+
"step": 700
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.32,
|
| 432 |
+
"learning_rate": 1.3178954491289692e-05,
|
| 433 |
+
"loss": 1.5424,
|
| 434 |
+
"step": 710
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.34,
|
| 438 |
+
"learning_rate": 1.2542087557933041e-05,
|
| 439 |
+
"loss": 1.5426,
|
| 440 |
+
"step": 720
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.35,
|
| 444 |
+
"learning_rate": 1.1915800407584704e-05,
|
| 445 |
+
"loss": 1.5555,
|
| 446 |
+
"step": 730
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.37,
|
| 450 |
+
"learning_rate": 1.1300624909623463e-05,
|
| 451 |
+
"loss": 1.5335,
|
| 452 |
+
"step": 740
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.39,
|
| 456 |
+
"learning_rate": 1.0697083496945765e-05,
|
| 457 |
+
"loss": 1.5446,
|
| 458 |
+
"step": 750
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.41,
|
| 462 |
+
"learning_rate": 1.0105688722293643e-05,
|
| 463 |
+
"loss": 1.5422,
|
| 464 |
+
"step": 760
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.43,
|
| 468 |
+
"learning_rate": 9.526942822973522e-06,
|
| 469 |
+
"loss": 1.548,
|
| 470 |
+
"step": 770
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.45,
|
| 474 |
+
"learning_rate": 8.961337294335021e-06,
|
| 475 |
+
"loss": 1.5436,
|
| 476 |
+
"step": 780
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.46,
|
| 480 |
+
"learning_rate": 8.409352472372595e-06,
|
| 481 |
+
"loss": 1.5483,
|
| 482 |
+
"step": 790
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.48,
|
| 486 |
+
"learning_rate": 7.871457125803896e-06,
|
| 487 |
+
"loss": 1.5348,
|
| 488 |
+
"step": 800
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.5,
|
| 492 |
+
"learning_rate": 7.348108057971728e-06,
|
| 493 |
+
"loss": 1.5309,
|
| 494 |
+
"step": 810
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.52,
|
| 498 |
+
"learning_rate": 6.839749718907429e-06,
|
| 499 |
+
"loss": 1.5343,
|
| 500 |
+
"step": 820
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.54,
|
| 504 |
+
"learning_rate": 6.3468138278852174e-06,
|
| 505 |
+
"loss": 1.5446,
|
| 506 |
+
"step": 830
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.56,
|
| 510 |
+
"learning_rate": 5.8697190067880325e-06,
|
| 511 |
+
"loss": 1.5381,
|
| 512 |
+
"step": 840
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.58,
|
| 516 |
+
"learning_rate": 5.408870424596238e-06,
|
| 517 |
+
"loss": 1.5483,
|
| 518 |
+
"step": 850
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.59,
|
| 522 |
+
"learning_rate": 4.9646594533010875e-06,
|
| 523 |
+
"loss": 1.5466,
|
| 524 |
+
"step": 860
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.61,
|
| 528 |
+
"learning_rate": 4.537463335535161e-06,
|
| 529 |
+
"loss": 1.5397,
|
| 530 |
+
"step": 870
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.63,
|
| 534 |
+
"learning_rate": 4.127644864202104e-06,
|
| 535 |
+
"loss": 1.5355,
|
| 536 |
+
"step": 880
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.65,
|
| 540 |
+
"learning_rate": 3.735552074377563e-06,
|
| 541 |
+
"loss": 1.5409,
|
| 542 |
+
"step": 890
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.67,
|
| 546 |
+
"learning_rate": 3.3615179477432645e-06,
|
| 547 |
+
"loss": 1.5383,
|
| 548 |
+
"step": 900
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.69,
|
| 552 |
+
"learning_rate": 3.0058601298048774e-06,
|
| 553 |
+
"loss": 1.5338,
|
| 554 |
+
"step": 910
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.71,
|
| 558 |
+
"learning_rate": 2.6688806601341765e-06,
|
| 559 |
+
"loss": 1.5384,
|
| 560 |
+
"step": 920
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.72,
|
| 564 |
+
"learning_rate": 2.350865715864278e-06,
|
| 565 |
+
"loss": 1.5305,
|
| 566 |
+
"step": 930
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.74,
|
| 570 |
+
"learning_rate": 2.0520853686560178e-06,
|
| 571 |
+
"loss": 1.5344,
|
| 572 |
+
"step": 940
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 1.76,
|
| 576 |
+
"learning_rate": 1.772793355341734e-06,
|
| 577 |
+
"loss": 1.5363,
|
| 578 |
+
"step": 950
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.78,
|
| 582 |
+
"learning_rate": 1.513226862441286e-06,
|
| 583 |
+
"loss": 1.5468,
|
| 584 |
+
"step": 960
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.8,
|
| 588 |
+
"learning_rate": 1.273606324733284e-06,
|
| 589 |
+
"loss": 1.5369,
|
| 590 |
+
"step": 970
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.82,
|
| 594 |
+
"learning_rate": 1.0541352380526087e-06,
|
| 595 |
+
"loss": 1.5428,
|
| 596 |
+
"step": 980
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.84,
|
| 600 |
+
"learning_rate": 8.549999864732011e-07,
|
| 601 |
+
"loss": 1.5338,
|
| 602 |
+
"step": 990
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.85,
|
| 606 |
+
"learning_rate": 6.763696840228456e-07,
|
| 607 |
+
"loss": 1.5399,
|
| 608 |
+
"step": 1000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.87,
|
| 612 |
+
"learning_rate": 5.183960310644748e-07,
|
| 613 |
+
"loss": 1.5406,
|
| 614 |
+
"step": 1010
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.89,
|
| 618 |
+
"learning_rate": 3.812131854657813e-07,
|
| 619 |
+
"loss": 1.5381,
|
| 620 |
+
"step": 1020
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 1.91,
|
| 624 |
+
"learning_rate": 2.649376486667743e-07,
|
| 625 |
+
"loss": 1.5354,
|
| 626 |
+
"step": 1030
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.93,
|
| 630 |
+
"learning_rate": 1.6966816674182373e-07,
|
| 631 |
+
"loss": 1.5358,
|
| 632 |
+
"step": 1040
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.95,
|
| 636 |
+
"learning_rate": 1.019530491929821e-07,
|
| 637 |
+
"loss": 1.5481,
|
| 638 |
+
"step": 1050
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 1.97,
|
| 642 |
+
"learning_rate": 4.680317016582669e-08,
|
| 643 |
+
"loss": 1.5504,
|
| 644 |
+
"step": 1060
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 1.98,
|
| 648 |
+
"learning_rate": 1.284459498280266e-08,
|
| 649 |
+
"loss": 1.5429,
|
| 650 |
+
"step": 1070
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 2.0,
|
| 654 |
+
"step": 1078,
|
| 655 |
+
"total_flos": 2.684311584557236e+18,
|
| 656 |
+
"train_loss": 1.5770846359804964,
|
| 657 |
+
"train_runtime": 13419.9836,
|
| 658 |
+
"train_samples_per_second": 10.287,
|
| 659 |
+
"train_steps_per_second": 0.08
|
| 660 |
+
}
|
| 661 |
+
],
|
| 662 |
+
"max_steps": 1078,
|
| 663 |
+
"num_train_epochs": 2,
|
| 664 |
+
"total_flos": 2.684311584557236e+18,
|
| 665 |
+
"trial_name": null,
|
| 666 |
+
"trial_params": null
|
| 667 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b69ea6b9f79d50f0ca7b5a2476627c8e100b6bcda45f5e45dfaba3d805792111
|
| 3 |
+
size 3264
|
training_loss.png
ADDED
|