Upload folder using huggingface_hub
Browse files- README.md +20 -0
- adapter_config.json +26 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1296 -0
- training_args.bin +3 -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 0.5.0.dev0
|
adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "openlm-research/open_llama_3b",
|
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": 32,
|
11 |
+
"lora_dropout": 0.05,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 8,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"up_proj",
|
18 |
+
"v_proj",
|
19 |
+
"gate_proj",
|
20 |
+
"o_proj",
|
21 |
+
"k_proj",
|
22 |
+
"down_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM"
|
26 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a11f8c6b674e9e913471abe1f1fb11fe4c76f5c0eb9fc7b955192957ba063b0
|
3 |
+
size 50899792
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:488d3c74c13d3f6a503f44d0a7a58c959f74669a68aefa1b90a8b17f8eee16aa
|
3 |
+
size 101918533
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b74995a6af923dc7f679d75189617e1a78bc68a7fa5f611b52499f95fdd38bed
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d24e6ccc821f2d700beba085903183c6e37db7bb536db52800811a5227d712ec
|
3 |
+
size 627
|
trainer_state.json
ADDED
@@ -0,0 +1,1296 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.14619883040935672,
|
5 |
+
"global_step": 200,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 2e-05,
|
13 |
+
"loss": 1.2695,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.0,
|
18 |
+
"learning_rate": 4e-05,
|
19 |
+
"loss": 1.4688,
|
20 |
+
"step": 2
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.0,
|
24 |
+
"learning_rate": 6e-05,
|
25 |
+
"loss": 1.2927,
|
26 |
+
"step": 3
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.0,
|
30 |
+
"learning_rate": 8e-05,
|
31 |
+
"loss": 1.2911,
|
32 |
+
"step": 4
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.0,
|
36 |
+
"learning_rate": 0.0001,
|
37 |
+
"loss": 1.1655,
|
38 |
+
"step": 5
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.0,
|
42 |
+
"learning_rate": 0.00012,
|
43 |
+
"loss": 1.3511,
|
44 |
+
"step": 6
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.01,
|
48 |
+
"learning_rate": 0.00014,
|
49 |
+
"loss": 1.2358,
|
50 |
+
"step": 7
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.01,
|
54 |
+
"learning_rate": 0.00016,
|
55 |
+
"loss": 1.287,
|
56 |
+
"step": 8
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.01,
|
60 |
+
"learning_rate": 0.00018,
|
61 |
+
"loss": 1.1919,
|
62 |
+
"step": 9
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.01,
|
66 |
+
"learning_rate": 0.0002,
|
67 |
+
"loss": 1.3329,
|
68 |
+
"step": 10
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.01,
|
72 |
+
"learning_rate": 0.00019999993359236733,
|
73 |
+
"loss": 1.0765,
|
74 |
+
"step": 11
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.01,
|
78 |
+
"learning_rate": 0.00019999973436955748,
|
79 |
+
"loss": 1.2112,
|
80 |
+
"step": 12
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.01,
|
84 |
+
"learning_rate": 0.00019999940233183508,
|
85 |
+
"loss": 1.2021,
|
86 |
+
"step": 13
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.01,
|
90 |
+
"learning_rate": 0.0001999989374796411,
|
91 |
+
"loss": 1.306,
|
92 |
+
"step": 14
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.01,
|
96 |
+
"learning_rate": 0.00019999833981359296,
|
97 |
+
"loss": 1.2094,
|
98 |
+
"step": 15
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.01,
|
102 |
+
"learning_rate": 0.00019999760933448442,
|
103 |
+
"loss": 1.3033,
|
104 |
+
"step": 16
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.01,
|
108 |
+
"learning_rate": 0.00019999674604328566,
|
109 |
+
"loss": 1.2345,
|
110 |
+
"step": 17
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.01,
|
114 |
+
"learning_rate": 0.00019999574994114335,
|
115 |
+
"loss": 1.1763,
|
116 |
+
"step": 18
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.01,
|
120 |
+
"learning_rate": 0.00019999462102938037,
|
121 |
+
"loss": 1.2333,
|
122 |
+
"step": 19
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.01,
|
126 |
+
"learning_rate": 0.00019999335930949612,
|
127 |
+
"loss": 1.213,
|
128 |
+
"step": 20
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.01,
|
132 |
+
"eval_loss": 1.181932806968689,
|
133 |
+
"eval_runtime": 76.4827,
|
134 |
+
"eval_samples_per_second": 0.732,
|
135 |
+
"eval_steps_per_second": 0.183,
|
136 |
+
"step": 20
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.02,
|
140 |
+
"learning_rate": 0.00019999196478316637,
|
141 |
+
"loss": 1.1985,
|
142 |
+
"step": 21
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.02,
|
146 |
+
"learning_rate": 0.00019999043745224323,
|
147 |
+
"loss": 1.2438,
|
148 |
+
"step": 22
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 0.02,
|
152 |
+
"learning_rate": 0.00019998877731875524,
|
153 |
+
"loss": 1.0714,
|
154 |
+
"step": 23
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 0.02,
|
158 |
+
"learning_rate": 0.00019998698438490736,
|
159 |
+
"loss": 1.2336,
|
160 |
+
"step": 24
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 0.02,
|
164 |
+
"learning_rate": 0.00019998505865308084,
|
165 |
+
"loss": 1.1357,
|
166 |
+
"step": 25
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 0.02,
|
170 |
+
"learning_rate": 0.00019998300012583333,
|
171 |
+
"loss": 1.1176,
|
172 |
+
"step": 26
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.02,
|
176 |
+
"learning_rate": 0.0001999808088058989,
|
177 |
+
"loss": 1.2537,
|
178 |
+
"step": 27
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.02,
|
182 |
+
"learning_rate": 0.0001999784846961879,
|
183 |
+
"loss": 1.2098,
|
184 |
+
"step": 28
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.02,
|
188 |
+
"learning_rate": 0.0001999760277997872,
|
189 |
+
"loss": 1.3226,
|
190 |
+
"step": 29
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 0.02,
|
194 |
+
"learning_rate": 0.00019997343811995984,
|
195 |
+
"loss": 1.271,
|
196 |
+
"step": 30
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 0.02,
|
200 |
+
"learning_rate": 0.00019997071566014535,
|
201 |
+
"loss": 1.1423,
|
202 |
+
"step": 31
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 0.02,
|
206 |
+
"learning_rate": 0.0001999678604239596,
|
207 |
+
"loss": 1.1422,
|
208 |
+
"step": 32
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 0.02,
|
212 |
+
"learning_rate": 0.00019996487241519473,
|
213 |
+
"loss": 1.2029,
|
214 |
+
"step": 33
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.02,
|
218 |
+
"learning_rate": 0.0001999617516378193,
|
219 |
+
"loss": 1.1305,
|
220 |
+
"step": 34
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.03,
|
224 |
+
"learning_rate": 0.00019995849809597814,
|
225 |
+
"loss": 1.3264,
|
226 |
+
"step": 35
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.03,
|
230 |
+
"learning_rate": 0.0001999551117939925,
|
231 |
+
"loss": 1.2266,
|
232 |
+
"step": 36
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 0.03,
|
236 |
+
"learning_rate": 0.0001999515927363599,
|
237 |
+
"loss": 1.1214,
|
238 |
+
"step": 37
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 0.03,
|
242 |
+
"learning_rate": 0.00019994794092775418,
|
243 |
+
"loss": 1.2081,
|
244 |
+
"step": 38
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 0.03,
|
248 |
+
"learning_rate": 0.00019994415637302547,
|
249 |
+
"loss": 1.2039,
|
250 |
+
"step": 39
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 0.03,
|
254 |
+
"learning_rate": 0.00019994023907720027,
|
255 |
+
"loss": 1.2026,
|
256 |
+
"step": 40
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.03,
|
260 |
+
"eval_loss": 1.152363896369934,
|
261 |
+
"eval_runtime": 76.6763,
|
262 |
+
"eval_samples_per_second": 0.73,
|
263 |
+
"eval_steps_per_second": 0.183,
|
264 |
+
"step": 40
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.03,
|
268 |
+
"learning_rate": 0.00019993618904548131,
|
269 |
+
"loss": 1.2681,
|
270 |
+
"step": 41
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.03,
|
274 |
+
"learning_rate": 0.0001999320062832477,
|
275 |
+
"loss": 1.0463,
|
276 |
+
"step": 42
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.03,
|
280 |
+
"learning_rate": 0.00019992769079605477,
|
281 |
+
"loss": 1.2364,
|
282 |
+
"step": 43
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.03,
|
286 |
+
"learning_rate": 0.00019992324258963413,
|
287 |
+
"loss": 1.1188,
|
288 |
+
"step": 44
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 0.03,
|
292 |
+
"learning_rate": 0.00019991866166989367,
|
293 |
+
"loss": 1.2932,
|
294 |
+
"step": 45
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.03,
|
298 |
+
"learning_rate": 0.00019991394804291758,
|
299 |
+
"loss": 1.1784,
|
300 |
+
"step": 46
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 0.03,
|
304 |
+
"learning_rate": 0.00019990910171496627,
|
305 |
+
"loss": 1.2541,
|
306 |
+
"step": 47
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 0.04,
|
310 |
+
"learning_rate": 0.0001999041226924764,
|
311 |
+
"loss": 1.1132,
|
312 |
+
"step": 48
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.04,
|
316 |
+
"learning_rate": 0.00019989901098206082,
|
317 |
+
"loss": 1.1555,
|
318 |
+
"step": 49
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.04,
|
322 |
+
"learning_rate": 0.00019989376659050877,
|
323 |
+
"loss": 1.3394,
|
324 |
+
"step": 50
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.04,
|
328 |
+
"learning_rate": 0.0001998883895247855,
|
329 |
+
"loss": 1.2951,
|
330 |
+
"step": 51
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 0.04,
|
334 |
+
"learning_rate": 0.00019988287979203265,
|
335 |
+
"loss": 1.2399,
|
336 |
+
"step": 52
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 0.04,
|
340 |
+
"learning_rate": 0.0001998772373995679,
|
341 |
+
"loss": 1.1664,
|
342 |
+
"step": 53
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 0.04,
|
346 |
+
"learning_rate": 0.0001998714623548853,
|
347 |
+
"loss": 1.117,
|
348 |
+
"step": 54
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 0.04,
|
352 |
+
"learning_rate": 0.00019986555466565493,
|
353 |
+
"loss": 1.1931,
|
354 |
+
"step": 55
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.04,
|
358 |
+
"learning_rate": 0.00019985951433972314,
|
359 |
+
"loss": 1.2058,
|
360 |
+
"step": 56
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.04,
|
364 |
+
"learning_rate": 0.00019985334138511237,
|
365 |
+
"loss": 1.1864,
|
366 |
+
"step": 57
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.04,
|
370 |
+
"learning_rate": 0.0001998470358100213,
|
371 |
+
"loss": 1.2206,
|
372 |
+
"step": 58
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 0.04,
|
376 |
+
"learning_rate": 0.00019984059762282467,
|
377 |
+
"loss": 1.0549,
|
378 |
+
"step": 59
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 0.04,
|
382 |
+
"learning_rate": 0.00019983402683207332,
|
383 |
+
"loss": 1.0102,
|
384 |
+
"step": 60
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.04,
|
388 |
+
"eval_loss": 1.1410892009735107,
|
389 |
+
"eval_runtime": 76.6475,
|
390 |
+
"eval_samples_per_second": 0.731,
|
391 |
+
"eval_steps_per_second": 0.183,
|
392 |
+
"step": 60
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 0.04,
|
396 |
+
"learning_rate": 0.00019982732344649433,
|
397 |
+
"loss": 1.0848,
|
398 |
+
"step": 61
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.05,
|
402 |
+
"learning_rate": 0.00019982048747499081,
|
403 |
+
"loss": 1.3566,
|
404 |
+
"step": 62
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.05,
|
408 |
+
"learning_rate": 0.00019981351892664194,
|
409 |
+
"loss": 1.2252,
|
410 |
+
"step": 63
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.05,
|
414 |
+
"learning_rate": 0.00019980641781070307,
|
415 |
+
"loss": 1.2283,
|
416 |
+
"step": 64
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.05,
|
420 |
+
"learning_rate": 0.00019979918413660553,
|
421 |
+
"loss": 1.1728,
|
422 |
+
"step": 65
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.05,
|
426 |
+
"learning_rate": 0.00019979181791395672,
|
427 |
+
"loss": 1.0926,
|
428 |
+
"step": 66
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.05,
|
432 |
+
"learning_rate": 0.00019978431915254017,
|
433 |
+
"loss": 1.1868,
|
434 |
+
"step": 67
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.05,
|
438 |
+
"learning_rate": 0.00019977668786231534,
|
439 |
+
"loss": 1.0868,
|
440 |
+
"step": 68
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.05,
|
444 |
+
"learning_rate": 0.00019976892405341773,
|
445 |
+
"loss": 1.1116,
|
446 |
+
"step": 69
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.05,
|
450 |
+
"learning_rate": 0.00019976102773615892,
|
451 |
+
"loss": 1.1881,
|
452 |
+
"step": 70
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.05,
|
456 |
+
"learning_rate": 0.00019975299892102636,
|
457 |
+
"loss": 1.1795,
|
458 |
+
"step": 71
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.05,
|
462 |
+
"learning_rate": 0.00019974483761868358,
|
463 |
+
"loss": 1.1028,
|
464 |
+
"step": 72
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.05,
|
468 |
+
"learning_rate": 0.00019973654383997007,
|
469 |
+
"loss": 0.9675,
|
470 |
+
"step": 73
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.05,
|
474 |
+
"learning_rate": 0.00019972811759590118,
|
475 |
+
"loss": 1.2491,
|
476 |
+
"step": 74
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.05,
|
480 |
+
"learning_rate": 0.00019971955889766825,
|
481 |
+
"loss": 1.1393,
|
482 |
+
"step": 75
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.06,
|
486 |
+
"learning_rate": 0.00019971086775663857,
|
487 |
+
"loss": 1.1288,
|
488 |
+
"step": 76
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.06,
|
492 |
+
"learning_rate": 0.00019970204418435526,
|
493 |
+
"loss": 1.1794,
|
494 |
+
"step": 77
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.06,
|
498 |
+
"learning_rate": 0.0001996930881925374,
|
499 |
+
"loss": 0.9819,
|
500 |
+
"step": 78
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.06,
|
504 |
+
"learning_rate": 0.0001996839997930799,
|
505 |
+
"loss": 1.1291,
|
506 |
+
"step": 79
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.06,
|
510 |
+
"learning_rate": 0.0001996747789980536,
|
511 |
+
"loss": 1.2502,
|
512 |
+
"step": 80
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.06,
|
516 |
+
"eval_loss": 1.1336756944656372,
|
517 |
+
"eval_runtime": 76.5931,
|
518 |
+
"eval_samples_per_second": 0.731,
|
519 |
+
"eval_steps_per_second": 0.183,
|
520 |
+
"step": 80
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.06,
|
524 |
+
"learning_rate": 0.000199665425819705,
|
525 |
+
"loss": 1.0629,
|
526 |
+
"step": 81
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 0.06,
|
530 |
+
"learning_rate": 0.00019965594027045665,
|
531 |
+
"loss": 1.0234,
|
532 |
+
"step": 82
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 0.06,
|
536 |
+
"learning_rate": 0.00019964632236290681,
|
537 |
+
"loss": 1.1065,
|
538 |
+
"step": 83
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 0.06,
|
542 |
+
"learning_rate": 0.00019963657210982948,
|
543 |
+
"loss": 1.1702,
|
544 |
+
"step": 84
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 0.06,
|
548 |
+
"learning_rate": 0.0001996266895241745,
|
549 |
+
"loss": 1.2096,
|
550 |
+
"step": 85
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.06,
|
554 |
+
"learning_rate": 0.00019961667461906743,
|
555 |
+
"loss": 1.232,
|
556 |
+
"step": 86
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.06,
|
560 |
+
"learning_rate": 0.00019960652740780966,
|
561 |
+
"loss": 1.0296,
|
562 |
+
"step": 87
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.06,
|
566 |
+
"learning_rate": 0.0001995962479038782,
|
567 |
+
"loss": 1.1686,
|
568 |
+
"step": 88
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 0.07,
|
572 |
+
"learning_rate": 0.00019958583612092576,
|
573 |
+
"loss": 1.1196,
|
574 |
+
"step": 89
|
575 |
+
},
|
576 |
+
{
|
577 |
+
"epoch": 0.07,
|
578 |
+
"learning_rate": 0.00019957529207278082,
|
579 |
+
"loss": 1.3479,
|
580 |
+
"step": 90
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 0.07,
|
584 |
+
"learning_rate": 0.0001995646157734475,
|
585 |
+
"loss": 1.1783,
|
586 |
+
"step": 91
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 0.07,
|
590 |
+
"learning_rate": 0.0001995538072371055,
|
591 |
+
"loss": 1.2225,
|
592 |
+
"step": 92
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.07,
|
596 |
+
"learning_rate": 0.00019954286647811027,
|
597 |
+
"loss": 1.0859,
|
598 |
+
"step": 93
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 0.07,
|
602 |
+
"learning_rate": 0.00019953179351099275,
|
603 |
+
"loss": 1.0763,
|
604 |
+
"step": 94
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.07,
|
608 |
+
"learning_rate": 0.00019952058835045957,
|
609 |
+
"loss": 1.2688,
|
610 |
+
"step": 95
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 0.07,
|
614 |
+
"learning_rate": 0.0001995092510113929,
|
615 |
+
"loss": 1.1738,
|
616 |
+
"step": 96
|
617 |
+
},
|
618 |
+
{
|
619 |
+
"epoch": 0.07,
|
620 |
+
"learning_rate": 0.00019949778150885042,
|
621 |
+
"loss": 1.1326,
|
622 |
+
"step": 97
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 0.07,
|
626 |
+
"learning_rate": 0.0001994861798580654,
|
627 |
+
"loss": 1.1722,
|
628 |
+
"step": 98
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 0.07,
|
632 |
+
"learning_rate": 0.0001994744460744466,
|
633 |
+
"loss": 1.2148,
|
634 |
+
"step": 99
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.07,
|
638 |
+
"learning_rate": 0.00019946258017357828,
|
639 |
+
"loss": 1.2499,
|
640 |
+
"step": 100
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.07,
|
644 |
+
"eval_loss": 1.1291786432266235,
|
645 |
+
"eval_runtime": 76.5934,
|
646 |
+
"eval_samples_per_second": 0.731,
|
647 |
+
"eval_steps_per_second": 0.183,
|
648 |
+
"step": 100
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.07,
|
652 |
+
"learning_rate": 0.00019945058217122016,
|
653 |
+
"loss": 1.1765,
|
654 |
+
"step": 101
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.07,
|
658 |
+
"learning_rate": 0.00019943845208330742,
|
659 |
+
"loss": 1.2101,
|
660 |
+
"step": 102
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.08,
|
664 |
+
"learning_rate": 0.0001994261899259507,
|
665 |
+
"loss": 1.1028,
|
666 |
+
"step": 103
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 0.08,
|
670 |
+
"learning_rate": 0.00019941379571543596,
|
671 |
+
"loss": 1.2198,
|
672 |
+
"step": 104
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 0.08,
|
676 |
+
"learning_rate": 0.00019940126946822465,
|
677 |
+
"loss": 1.2474,
|
678 |
+
"step": 105
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 0.08,
|
682 |
+
"learning_rate": 0.00019938861120095353,
|
683 |
+
"loss": 1.1917,
|
684 |
+
"step": 106
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.08,
|
688 |
+
"learning_rate": 0.0001993758209304347,
|
689 |
+
"loss": 1.2239,
|
690 |
+
"step": 107
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.08,
|
694 |
+
"learning_rate": 0.00019936289867365556,
|
695 |
+
"loss": 1.2406,
|
696 |
+
"step": 108
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.08,
|
700 |
+
"learning_rate": 0.0001993498444477789,
|
701 |
+
"loss": 1.2051,
|
702 |
+
"step": 109
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.08,
|
706 |
+
"learning_rate": 0.00019933665827014273,
|
707 |
+
"loss": 1.146,
|
708 |
+
"step": 110
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 0.08,
|
712 |
+
"learning_rate": 0.00019932334015826023,
|
713 |
+
"loss": 1.0871,
|
714 |
+
"step": 111
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.08,
|
718 |
+
"learning_rate": 0.00019930989012981992,
|
719 |
+
"loss": 1.1184,
|
720 |
+
"step": 112
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 0.08,
|
724 |
+
"learning_rate": 0.00019929630820268552,
|
725 |
+
"loss": 1.0224,
|
726 |
+
"step": 113
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 0.08,
|
730 |
+
"learning_rate": 0.00019928259439489589,
|
731 |
+
"loss": 1.0958,
|
732 |
+
"step": 114
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.08,
|
736 |
+
"learning_rate": 0.0001992687487246651,
|
737 |
+
"loss": 1.1811,
|
738 |
+
"step": 115
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.08,
|
742 |
+
"learning_rate": 0.00019925477121038218,
|
743 |
+
"loss": 1.3126,
|
744 |
+
"step": 116
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.09,
|
748 |
+
"learning_rate": 0.00019924066187061156,
|
749 |
+
"loss": 1.0572,
|
750 |
+
"step": 117
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 0.09,
|
754 |
+
"learning_rate": 0.0001992264207240925,
|
755 |
+
"loss": 1.0597,
|
756 |
+
"step": 118
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 0.09,
|
760 |
+
"learning_rate": 0.00019921204778973944,
|
761 |
+
"loss": 1.1559,
|
762 |
+
"step": 119
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 0.09,
|
766 |
+
"learning_rate": 0.00019919754308664187,
|
767 |
+
"loss": 1.2146,
|
768 |
+
"step": 120
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.09,
|
772 |
+
"eval_loss": 1.1247767210006714,
|
773 |
+
"eval_runtime": 80.1123,
|
774 |
+
"eval_samples_per_second": 0.699,
|
775 |
+
"eval_steps_per_second": 0.175,
|
776 |
+
"step": 120
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 0.09,
|
780 |
+
"learning_rate": 0.0001991829066340642,
|
781 |
+
"loss": 1.2127,
|
782 |
+
"step": 121
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 0.09,
|
786 |
+
"learning_rate": 0.00019916813845144587,
|
787 |
+
"loss": 1.1637,
|
788 |
+
"step": 122
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.09,
|
792 |
+
"learning_rate": 0.00019915323855840131,
|
793 |
+
"loss": 1.2383,
|
794 |
+
"step": 123
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.09,
|
798 |
+
"learning_rate": 0.00019913820697471985,
|
799 |
+
"loss": 1.0641,
|
800 |
+
"step": 124
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.09,
|
804 |
+
"learning_rate": 0.00019912304372036573,
|
805 |
+
"loss": 1.115,
|
806 |
+
"step": 125
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 0.09,
|
810 |
+
"learning_rate": 0.000199107748815478,
|
811 |
+
"loss": 1.0733,
|
812 |
+
"step": 126
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 0.09,
|
816 |
+
"learning_rate": 0.00019909232228037076,
|
817 |
+
"loss": 1.2392,
|
818 |
+
"step": 127
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 0.09,
|
822 |
+
"learning_rate": 0.00019907676413553267,
|
823 |
+
"loss": 1.3308,
|
824 |
+
"step": 128
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.09,
|
828 |
+
"learning_rate": 0.00019906107440162743,
|
829 |
+
"loss": 1.1723,
|
830 |
+
"step": 129
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.1,
|
834 |
+
"learning_rate": 0.00019904525309949334,
|
835 |
+
"loss": 1.1327,
|
836 |
+
"step": 130
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.1,
|
840 |
+
"learning_rate": 0.00019902930025014347,
|
841 |
+
"loss": 1.1309,
|
842 |
+
"step": 131
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.1,
|
846 |
+
"learning_rate": 0.00019901321587476574,
|
847 |
+
"loss": 1.1563,
|
848 |
+
"step": 132
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 0.1,
|
852 |
+
"learning_rate": 0.00019899699999472258,
|
853 |
+
"loss": 1.1824,
|
854 |
+
"step": 133
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 0.1,
|
858 |
+
"learning_rate": 0.0001989806526315512,
|
859 |
+
"loss": 1.2014,
|
860 |
+
"step": 134
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.1,
|
864 |
+
"learning_rate": 0.00019896417380696333,
|
865 |
+
"loss": 1.182,
|
866 |
+
"step": 135
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 0.1,
|
870 |
+
"learning_rate": 0.0001989475635428454,
|
871 |
+
"loss": 1.1519,
|
872 |
+
"step": 136
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.1,
|
876 |
+
"learning_rate": 0.0001989308218612584,
|
877 |
+
"loss": 1.2197,
|
878 |
+
"step": 137
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.1,
|
882 |
+
"learning_rate": 0.00019891394878443784,
|
883 |
+
"loss": 1.01,
|
884 |
+
"step": 138
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.1,
|
888 |
+
"learning_rate": 0.0001988969443347937,
|
889 |
+
"loss": 1.2011,
|
890 |
+
"step": 139
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 0.1,
|
894 |
+
"learning_rate": 0.0001988798085349105,
|
895 |
+
"loss": 1.1338,
|
896 |
+
"step": 140
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 0.1,
|
900 |
+
"eval_loss": 1.120542287826538,
|
901 |
+
"eval_runtime": 79.9836,
|
902 |
+
"eval_samples_per_second": 0.7,
|
903 |
+
"eval_steps_per_second": 0.175,
|
904 |
+
"step": 140
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 0.1,
|
908 |
+
"learning_rate": 0.00019886254140754722,
|
909 |
+
"loss": 1.0325,
|
910 |
+
"step": 141
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"epoch": 0.1,
|
914 |
+
"learning_rate": 0.0001988451429756372,
|
915 |
+
"loss": 1.2331,
|
916 |
+
"step": 142
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 0.1,
|
920 |
+
"learning_rate": 0.00019882761326228825,
|
921 |
+
"loss": 1.1751,
|
922 |
+
"step": 143
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 0.11,
|
926 |
+
"learning_rate": 0.0001988099522907825,
|
927 |
+
"loss": 1.2066,
|
928 |
+
"step": 144
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 0.11,
|
932 |
+
"learning_rate": 0.00019879216008457642,
|
933 |
+
"loss": 1.1406,
|
934 |
+
"step": 145
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.11,
|
938 |
+
"learning_rate": 0.00019877423666730075,
|
939 |
+
"loss": 1.2226,
|
940 |
+
"step": 146
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.11,
|
944 |
+
"learning_rate": 0.00019875618206276053,
|
945 |
+
"loss": 1.1612,
|
946 |
+
"step": 147
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 0.11,
|
950 |
+
"learning_rate": 0.00019873799629493508,
|
951 |
+
"loss": 1.203,
|
952 |
+
"step": 148
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 0.11,
|
956 |
+
"learning_rate": 0.0001987196793879778,
|
957 |
+
"loss": 1.1134,
|
958 |
+
"step": 149
|
959 |
+
},
|
960 |
+
{
|
961 |
+
"epoch": 0.11,
|
962 |
+
"learning_rate": 0.00019870123136621638,
|
963 |
+
"loss": 1.164,
|
964 |
+
"step": 150
|
965 |
+
},
|
966 |
+
{
|
967 |
+
"epoch": 0.11,
|
968 |
+
"learning_rate": 0.00019868265225415265,
|
969 |
+
"loss": 0.9973,
|
970 |
+
"step": 151
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 0.11,
|
974 |
+
"learning_rate": 0.0001986639420764624,
|
975 |
+
"loss": 1.0642,
|
976 |
+
"step": 152
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 0.11,
|
980 |
+
"learning_rate": 0.00019864510085799568,
|
981 |
+
"loss": 1.1626,
|
982 |
+
"step": 153
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.11,
|
986 |
+
"learning_rate": 0.00019862612862377648,
|
987 |
+
"loss": 1.1529,
|
988 |
+
"step": 154
|
989 |
+
},
|
990 |
+
{
|
991 |
+
"epoch": 0.11,
|
992 |
+
"learning_rate": 0.00019860702539900287,
|
993 |
+
"loss": 1.2552,
|
994 |
+
"step": 155
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 0.11,
|
998 |
+
"learning_rate": 0.00019858779120904678,
|
999 |
+
"loss": 1.1867,
|
1000 |
+
"step": 156
|
1001 |
+
},
|
1002 |
+
{
|
1003 |
+
"epoch": 0.11,
|
1004 |
+
"learning_rate": 0.00019856842607945418,
|
1005 |
+
"loss": 1.2168,
|
1006 |
+
"step": 157
|
1007 |
+
},
|
1008 |
+
{
|
1009 |
+
"epoch": 0.12,
|
1010 |
+
"learning_rate": 0.00019854893003594493,
|
1011 |
+
"loss": 1.1797,
|
1012 |
+
"step": 158
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"epoch": 0.12,
|
1016 |
+
"learning_rate": 0.00019852930310441274,
|
1017 |
+
"loss": 1.2606,
|
1018 |
+
"step": 159
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 0.12,
|
1022 |
+
"learning_rate": 0.00019850954531092517,
|
1023 |
+
"loss": 1.2599,
|
1024 |
+
"step": 160
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.12,
|
1028 |
+
"eval_loss": 1.1176784038543701,
|
1029 |
+
"eval_runtime": 79.9641,
|
1030 |
+
"eval_samples_per_second": 0.7,
|
1031 |
+
"eval_steps_per_second": 0.175,
|
1032 |
+
"step": 160
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 0.12,
|
1036 |
+
"learning_rate": 0.00019848965668172356,
|
1037 |
+
"loss": 0.9995,
|
1038 |
+
"step": 161
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.12,
|
1042 |
+
"learning_rate": 0.0001984696372432231,
|
1043 |
+
"loss": 1.2258,
|
1044 |
+
"step": 162
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 0.12,
|
1048 |
+
"learning_rate": 0.00019844948702201265,
|
1049 |
+
"loss": 1.085,
|
1050 |
+
"step": 163
|
1051 |
+
},
|
1052 |
+
{
|
1053 |
+
"epoch": 0.12,
|
1054 |
+
"learning_rate": 0.00019842920604485473,
|
1055 |
+
"loss": 1.125,
|
1056 |
+
"step": 164
|
1057 |
+
},
|
1058 |
+
{
|
1059 |
+
"epoch": 0.12,
|
1060 |
+
"learning_rate": 0.0001984087943386856,
|
1061 |
+
"loss": 1.1549,
|
1062 |
+
"step": 165
|
1063 |
+
},
|
1064 |
+
{
|
1065 |
+
"epoch": 0.12,
|
1066 |
+
"learning_rate": 0.00019838825193061518,
|
1067 |
+
"loss": 1.1749,
|
1068 |
+
"step": 166
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 0.12,
|
1072 |
+
"learning_rate": 0.00019836757884792683,
|
1073 |
+
"loss": 1.1702,
|
1074 |
+
"step": 167
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.12,
|
1078 |
+
"learning_rate": 0.0001983467751180776,
|
1079 |
+
"loss": 1.2037,
|
1080 |
+
"step": 168
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.12,
|
1084 |
+
"learning_rate": 0.00019832584076869805,
|
1085 |
+
"loss": 1.0019,
|
1086 |
+
"step": 169
|
1087 |
+
},
|
1088 |
+
{
|
1089 |
+
"epoch": 0.12,
|
1090 |
+
"learning_rate": 0.00019830477582759212,
|
1091 |
+
"loss": 1.1183,
|
1092 |
+
"step": 170
|
1093 |
+
},
|
1094 |
+
{
|
1095 |
+
"epoch": 0.12,
|
1096 |
+
"learning_rate": 0.00019828358032273735,
|
1097 |
+
"loss": 1.0197,
|
1098 |
+
"step": 171
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 0.13,
|
1102 |
+
"learning_rate": 0.00019826225428228457,
|
1103 |
+
"loss": 1.107,
|
1104 |
+
"step": 172
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 0.13,
|
1108 |
+
"learning_rate": 0.000198240797734558,
|
1109 |
+
"loss": 1.1855,
|
1110 |
+
"step": 173
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 0.13,
|
1114 |
+
"learning_rate": 0.0001982192107080552,
|
1115 |
+
"loss": 1.2044,
|
1116 |
+
"step": 174
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 0.13,
|
1120 |
+
"learning_rate": 0.00019819749323144709,
|
1121 |
+
"loss": 1.1586,
|
1122 |
+
"step": 175
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.13,
|
1126 |
+
"learning_rate": 0.00019817564533357773,
|
1127 |
+
"loss": 1.1092,
|
1128 |
+
"step": 176
|
1129 |
+
},
|
1130 |
+
{
|
1131 |
+
"epoch": 0.13,
|
1132 |
+
"learning_rate": 0.00019815366704346453,
|
1133 |
+
"loss": 1.2592,
|
1134 |
+
"step": 177
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 0.13,
|
1138 |
+
"learning_rate": 0.00019813155839029797,
|
1139 |
+
"loss": 1.1808,
|
1140 |
+
"step": 178
|
1141 |
+
},
|
1142 |
+
{
|
1143 |
+
"epoch": 0.13,
|
1144 |
+
"learning_rate": 0.00019810931940344176,
|
1145 |
+
"loss": 1.1179,
|
1146 |
+
"step": 179
|
1147 |
+
},
|
1148 |
+
{
|
1149 |
+
"epoch": 0.13,
|
1150 |
+
"learning_rate": 0.0001980869501124326,
|
1151 |
+
"loss": 1.1333,
|
1152 |
+
"step": 180
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 0.13,
|
1156 |
+
"eval_loss": 1.1160587072372437,
|
1157 |
+
"eval_runtime": 79.8665,
|
1158 |
+
"eval_samples_per_second": 0.701,
|
1159 |
+
"eval_steps_per_second": 0.175,
|
1160 |
+
"step": 180
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 0.13,
|
1164 |
+
"learning_rate": 0.00019806445054698039,
|
1165 |
+
"loss": 1.0633,
|
1166 |
+
"step": 181
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 0.13,
|
1170 |
+
"learning_rate": 0.00019804182073696793,
|
1171 |
+
"loss": 1.1252,
|
1172 |
+
"step": 182
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 0.13,
|
1176 |
+
"learning_rate": 0.00019801906071245111,
|
1177 |
+
"loss": 1.1522,
|
1178 |
+
"step": 183
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.13,
|
1182 |
+
"learning_rate": 0.0001979961705036587,
|
1183 |
+
"loss": 1.1706,
|
1184 |
+
"step": 184
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 0.14,
|
1188 |
+
"learning_rate": 0.00019797315014099238,
|
1189 |
+
"loss": 1.1142,
|
1190 |
+
"step": 185
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 0.14,
|
1194 |
+
"learning_rate": 0.00019794999965502672,
|
1195 |
+
"loss": 1.0345,
|
1196 |
+
"step": 186
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 0.14,
|
1200 |
+
"learning_rate": 0.0001979267190765091,
|
1201 |
+
"loss": 1.1029,
|
1202 |
+
"step": 187
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 0.14,
|
1206 |
+
"learning_rate": 0.00019790330843635966,
|
1207 |
+
"loss": 1.1628,
|
1208 |
+
"step": 188
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 0.14,
|
1212 |
+
"learning_rate": 0.00019787976776567133,
|
1213 |
+
"loss": 1.1569,
|
1214 |
+
"step": 189
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 0.14,
|
1218 |
+
"learning_rate": 0.00019785609709570973,
|
1219 |
+
"loss": 1.2024,
|
1220 |
+
"step": 190
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.14,
|
1224 |
+
"learning_rate": 0.00019783229645791307,
|
1225 |
+
"loss": 1.1602,
|
1226 |
+
"step": 191
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 0.14,
|
1230 |
+
"learning_rate": 0.00019780836588389225,
|
1231 |
+
"loss": 1.1588,
|
1232 |
+
"step": 192
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 0.14,
|
1236 |
+
"learning_rate": 0.00019778430540543077,
|
1237 |
+
"loss": 1.1104,
|
1238 |
+
"step": 193
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 0.14,
|
1242 |
+
"learning_rate": 0.00019776011505448455,
|
1243 |
+
"loss": 1.1437,
|
1244 |
+
"step": 194
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 0.14,
|
1248 |
+
"learning_rate": 0.00019773579486318213,
|
1249 |
+
"loss": 1.2098,
|
1250 |
+
"step": 195
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 0.14,
|
1254 |
+
"learning_rate": 0.00019771134486382436,
|
1255 |
+
"loss": 1.125,
|
1256 |
+
"step": 196
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 0.14,
|
1260 |
+
"learning_rate": 0.00019768676508888467,
|
1261 |
+
"loss": 1.0576,
|
1262 |
+
"step": 197
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.14,
|
1266 |
+
"learning_rate": 0.00019766205557100868,
|
1267 |
+
"loss": 1.1982,
|
1268 |
+
"step": 198
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 0.15,
|
1272 |
+
"learning_rate": 0.00019763721634301443,
|
1273 |
+
"loss": 1.1395,
|
1274 |
+
"step": 199
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 0.15,
|
1278 |
+
"learning_rate": 0.0001976122474378922,
|
1279 |
+
"loss": 1.2491,
|
1280 |
+
"step": 200
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 0.15,
|
1284 |
+
"eval_loss": 1.1136831045150757,
|
1285 |
+
"eval_runtime": 79.9646,
|
1286 |
+
"eval_samples_per_second": 0.7,
|
1287 |
+
"eval_steps_per_second": 0.175,
|
1288 |
+
"step": 200
|
1289 |
+
}
|
1290 |
+
],
|
1291 |
+
"max_steps": 2736,
|
1292 |
+
"num_train_epochs": 2,
|
1293 |
+
"total_flos": 1.588426799910912e+16,
|
1294 |
+
"trial_name": null,
|
1295 |
+
"trial_params": null
|
1296 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7fffa37d0a548ebe559d758b6453791e44af3a50d3c2450c1bd82394a361214
|
3 |
+
size 3963
|