Push lora 13b
Browse files- adapter_config.json +21 -0
- adapter_model.bin +3 -0
- checkpoint-1600/optimizer.pt +3 -0
- checkpoint-1600/pytorch_model.bin +3 -0
- checkpoint-1600/rng_state_0.pth +3 -0
- checkpoint-1600/rng_state_1.pth +3 -0
- checkpoint-1600/rng_state_2.pth +3 -0
- checkpoint-1600/rng_state_3.pth +3 -0
- checkpoint-1600/rng_state_4.pth +3 -0
- checkpoint-1600/rng_state_5.pth +3 -0
- checkpoint-1600/rng_state_6.pth +3 -0
- checkpoint-1600/rng_state_7.pth +3 -0
- checkpoint-1600/scaler.pt +3 -0
- checkpoint-1600/scheduler.pt +3 -0
- checkpoint-1600/trainer_state.json +1040 -0
- checkpoint-1600/training_args.bin +3 -0
- checkpoint-1800/optimizer.pt +3 -0
- checkpoint-1800/pytorch_model.bin +3 -0
- checkpoint-1800/rng_state_0.pth +3 -0
- checkpoint-1800/rng_state_1.pth +3 -0
- checkpoint-1800/rng_state_2.pth +3 -0
- checkpoint-1800/rng_state_3.pth +3 -0
- checkpoint-1800/rng_state_4.pth +3 -0
- checkpoint-1800/rng_state_5.pth +3 -0
- checkpoint-1800/rng_state_6.pth +3 -0
- checkpoint-1800/rng_state_7.pth +3 -0
- checkpoint-1800/scaler.pt +3 -0
- checkpoint-1800/scheduler.pt +3 -0
- checkpoint-1800/trainer_state.json +1168 -0
- checkpoint-1800/training_args.bin +3 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/pytorch_model.bin +3 -0
- checkpoint-2000/rng_state_0.pth +3 -0
- checkpoint-2000/rng_state_1.pth +3 -0
- checkpoint-2000/rng_state_2.pth +3 -0
- checkpoint-2000/rng_state_3.pth +3 -0
- checkpoint-2000/rng_state_4.pth +3 -0
- checkpoint-2000/rng_state_5.pth +3 -0
- checkpoint-2000/rng_state_6.pth +3 -0
- checkpoint-2000/rng_state_7.pth +3 -0
- checkpoint-2000/scaler.pt +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/trainer_state.json +1296 -0
- checkpoint-2000/training_args.bin +3 -0
adapter_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"base_model_name_or_path": "yahma/llama-13b-hf",
|
3 |
+
"bias": "none",
|
4 |
+
"enable_lora": null,
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"lora_alpha": 16,
|
9 |
+
"lora_dropout": 0.05,
|
10 |
+
"merge_weights": false,
|
11 |
+
"modules_to_save": null,
|
12 |
+
"peft_type": "LORA",
|
13 |
+
"r": 16,
|
14 |
+
"target_modules": [
|
15 |
+
"q_proj",
|
16 |
+
"k_proj",
|
17 |
+
"v_proj",
|
18 |
+
"o_proj"
|
19 |
+
],
|
20 |
+
"task_type": "CAUSAL_LM"
|
21 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7160a1255da28464221b5d10c57eb0bbb2106ee86b4855502a633de9ecd25e9
|
3 |
+
size 104973389
|
checkpoint-1600/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8234adeb14ea36133df684d372dd002ced88cf95ec4c51af0824b67b44a779fc
|
3 |
+
size 209984517
|
checkpoint-1600/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de8263e5a1fa3f73b33efba979c13093212294196e5c5f61f0881819c2da882e
|
3 |
+
size 104973389
|
checkpoint-1600/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:921b6cf0e67123dff0dc50dcdce3fa955cb3803b6f322f6081fd4dbcec493d4a
|
3 |
+
size 14583
|
checkpoint-1600/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:414911fdaf4225e8e0c97aeb88088ba86c5f8e088a07ac9ca5764a8a80da1129
|
3 |
+
size 14583
|
checkpoint-1600/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f489a67dcf9687617980f58b5b05b80314a8add9198761b746305a32951b302d
|
3 |
+
size 14583
|
checkpoint-1600/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da64f930b71614af27fb0e7601a4c9b20f8c4b2f6010318c336b585d6e563e3c
|
3 |
+
size 14583
|
checkpoint-1600/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d305866ea208d3349a706d1f6acf71ae62d4faae5e9bfdd0058c57ce180c0d35
|
3 |
+
size 14583
|
checkpoint-1600/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c00509f309ec062a8a78a6eb337349e6419d0ba77050eb76f76966fea24a914
|
3 |
+
size 14583
|
checkpoint-1600/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77e0053bee3159af0e57d15fef208e96697a6703401b4382c8c5ac8b15961b3b
|
3 |
+
size 14583
|
checkpoint-1600/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11a0fc15a2ddddc9acfca665ea4971d3c2ef317d74bb87128ec14fb267dec6fe
|
3 |
+
size 14583
|
checkpoint-1600/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db67274fde5daed529c0075a5126aea62b82b9293dc584ffe321e3bc6bac83ce
|
3 |
+
size 557
|
checkpoint-1600/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0881fddf73ebc9cddff50888198cd4e9c70e75a3fdb4f62a1a5008b47ebacd05
|
3 |
+
size 627
|
checkpoint-1600/trainer_state.json
ADDED
@@ -0,0 +1,1040 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9100631475448608,
|
3 |
+
"best_model_checkpoint": "./lora-alpaca/checkpoint-1600",
|
4 |
+
"epoch": 3.15893385982231,
|
5 |
+
"global_step": 1600,
|
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": 2.3999999999999997e-05,
|
13 |
+
"loss": 1.5473,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.04,
|
18 |
+
"learning_rate": 5.399999999999999e-05,
|
19 |
+
"loss": 1.5181,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.06,
|
24 |
+
"learning_rate": 8.4e-05,
|
25 |
+
"loss": 1.3749,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.08,
|
30 |
+
"learning_rate": 0.00011399999999999999,
|
31 |
+
"loss": 1.1669,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.1,
|
36 |
+
"learning_rate": 0.00014399999999999998,
|
37 |
+
"loss": 1.0525,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.12,
|
42 |
+
"learning_rate": 0.00017399999999999997,
|
43 |
+
"loss": 1.0376,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.14,
|
48 |
+
"learning_rate": 0.000204,
|
49 |
+
"loss": 1.0043,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.16,
|
54 |
+
"learning_rate": 0.000234,
|
55 |
+
"loss": 0.9849,
|
56 |
+
"step": 80
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.18,
|
60 |
+
"learning_rate": 0.00026399999999999997,
|
61 |
+
"loss": 0.9821,
|
62 |
+
"step": 90
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.2,
|
66 |
+
"learning_rate": 0.000294,
|
67 |
+
"loss": 0.9846,
|
68 |
+
"step": 100
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.22,
|
72 |
+
"learning_rate": 0.0002987525987525987,
|
73 |
+
"loss": 0.9635,
|
74 |
+
"step": 110
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.24,
|
78 |
+
"learning_rate": 0.00029719334719334716,
|
79 |
+
"loss": 0.9538,
|
80 |
+
"step": 120
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.26,
|
84 |
+
"learning_rate": 0.0002956340956340956,
|
85 |
+
"loss": 0.9408,
|
86 |
+
"step": 130
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.28,
|
90 |
+
"learning_rate": 0.00029407484407484405,
|
91 |
+
"loss": 0.9529,
|
92 |
+
"step": 140
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.3,
|
96 |
+
"learning_rate": 0.0002925155925155925,
|
97 |
+
"loss": 0.9622,
|
98 |
+
"step": 150
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.32,
|
102 |
+
"learning_rate": 0.00029095634095634094,
|
103 |
+
"loss": 0.9517,
|
104 |
+
"step": 160
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.34,
|
108 |
+
"learning_rate": 0.0002893970893970894,
|
109 |
+
"loss": 0.9624,
|
110 |
+
"step": 170
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.36,
|
114 |
+
"learning_rate": 0.0002878378378378378,
|
115 |
+
"loss": 0.9445,
|
116 |
+
"step": 180
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.38,
|
120 |
+
"learning_rate": 0.0002862785862785863,
|
121 |
+
"loss": 0.9428,
|
122 |
+
"step": 190
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.39,
|
126 |
+
"learning_rate": 0.0002847193347193347,
|
127 |
+
"loss": 0.9372,
|
128 |
+
"step": 200
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.39,
|
132 |
+
"eval_loss": 0.9433729648590088,
|
133 |
+
"eval_runtime": 44.3089,
|
134 |
+
"eval_samples_per_second": 45.138,
|
135 |
+
"eval_steps_per_second": 0.722,
|
136 |
+
"step": 200
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.41,
|
140 |
+
"learning_rate": 0.00028316008316008317,
|
141 |
+
"loss": 0.9388,
|
142 |
+
"step": 210
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.43,
|
146 |
+
"learning_rate": 0.00028160083160083156,
|
147 |
+
"loss": 0.9412,
|
148 |
+
"step": 220
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 0.45,
|
152 |
+
"learning_rate": 0.00028004158004158,
|
153 |
+
"loss": 0.9365,
|
154 |
+
"step": 230
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 0.47,
|
158 |
+
"learning_rate": 0.00027848232848232845,
|
159 |
+
"loss": 0.9382,
|
160 |
+
"step": 240
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 0.49,
|
164 |
+
"learning_rate": 0.0002769230769230769,
|
165 |
+
"loss": 0.9309,
|
166 |
+
"step": 250
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 0.51,
|
170 |
+
"learning_rate": 0.00027536382536382534,
|
171 |
+
"loss": 0.9256,
|
172 |
+
"step": 260
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.53,
|
176 |
+
"learning_rate": 0.0002738045738045738,
|
177 |
+
"loss": 0.9245,
|
178 |
+
"step": 270
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.55,
|
182 |
+
"learning_rate": 0.00027224532224532223,
|
183 |
+
"loss": 0.9329,
|
184 |
+
"step": 280
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.57,
|
188 |
+
"learning_rate": 0.0002706860706860707,
|
189 |
+
"loss": 0.9405,
|
190 |
+
"step": 290
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 0.59,
|
194 |
+
"learning_rate": 0.0002691268191268191,
|
195 |
+
"loss": 0.9168,
|
196 |
+
"step": 300
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 0.61,
|
200 |
+
"learning_rate": 0.00026756756756756756,
|
201 |
+
"loss": 0.92,
|
202 |
+
"step": 310
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 0.63,
|
206 |
+
"learning_rate": 0.000266008316008316,
|
207 |
+
"loss": 0.9098,
|
208 |
+
"step": 320
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 0.65,
|
212 |
+
"learning_rate": 0.00026444906444906445,
|
213 |
+
"loss": 0.9275,
|
214 |
+
"step": 330
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.67,
|
218 |
+
"learning_rate": 0.00026288981288981285,
|
219 |
+
"loss": 0.9215,
|
220 |
+
"step": 340
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.69,
|
224 |
+
"learning_rate": 0.0002613305613305613,
|
225 |
+
"loss": 0.9237,
|
226 |
+
"step": 350
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.71,
|
230 |
+
"learning_rate": 0.00025977130977130974,
|
231 |
+
"loss": 0.9237,
|
232 |
+
"step": 360
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 0.73,
|
236 |
+
"learning_rate": 0.0002582120582120582,
|
237 |
+
"loss": 0.928,
|
238 |
+
"step": 370
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 0.75,
|
242 |
+
"learning_rate": 0.0002566528066528066,
|
243 |
+
"loss": 0.9156,
|
244 |
+
"step": 380
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 0.77,
|
248 |
+
"learning_rate": 0.00025509355509355507,
|
249 |
+
"loss": 0.9255,
|
250 |
+
"step": 390
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 0.79,
|
254 |
+
"learning_rate": 0.0002535343035343035,
|
255 |
+
"loss": 0.9102,
|
256 |
+
"step": 400
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.79,
|
260 |
+
"eval_loss": 0.9269554615020752,
|
261 |
+
"eval_runtime": 44.228,
|
262 |
+
"eval_samples_per_second": 45.22,
|
263 |
+
"eval_steps_per_second": 0.724,
|
264 |
+
"step": 400
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.81,
|
268 |
+
"learning_rate": 0.00025197505197505196,
|
269 |
+
"loss": 0.9312,
|
270 |
+
"step": 410
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.83,
|
274 |
+
"learning_rate": 0.0002504158004158004,
|
275 |
+
"loss": 0.9249,
|
276 |
+
"step": 420
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.85,
|
280 |
+
"learning_rate": 0.00024885654885654885,
|
281 |
+
"loss": 0.9151,
|
282 |
+
"step": 430
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.87,
|
286 |
+
"learning_rate": 0.0002472972972972973,
|
287 |
+
"loss": 0.9265,
|
288 |
+
"step": 440
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 0.89,
|
292 |
+
"learning_rate": 0.00024573804573804574,
|
293 |
+
"loss": 0.9064,
|
294 |
+
"step": 450
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.91,
|
298 |
+
"learning_rate": 0.00024417879417879413,
|
299 |
+
"loss": 0.9185,
|
300 |
+
"step": 460
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 0.93,
|
304 |
+
"learning_rate": 0.0002426195426195426,
|
305 |
+
"loss": 0.9128,
|
306 |
+
"step": 470
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 0.95,
|
310 |
+
"learning_rate": 0.00024106029106029105,
|
311 |
+
"loss": 0.9159,
|
312 |
+
"step": 480
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.97,
|
316 |
+
"learning_rate": 0.0002395010395010395,
|
317 |
+
"loss": 0.8987,
|
318 |
+
"step": 490
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.99,
|
322 |
+
"learning_rate": 0.0002379417879417879,
|
323 |
+
"loss": 0.9217,
|
324 |
+
"step": 500
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 1.01,
|
328 |
+
"learning_rate": 0.00023638253638253636,
|
329 |
+
"loss": 0.906,
|
330 |
+
"step": 510
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 1.03,
|
334 |
+
"learning_rate": 0.0002348232848232848,
|
335 |
+
"loss": 0.9066,
|
336 |
+
"step": 520
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 1.05,
|
340 |
+
"learning_rate": 0.00023326403326403325,
|
341 |
+
"loss": 0.9085,
|
342 |
+
"step": 530
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 1.07,
|
346 |
+
"learning_rate": 0.00023170478170478166,
|
347 |
+
"loss": 0.9203,
|
348 |
+
"step": 540
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 1.09,
|
352 |
+
"learning_rate": 0.0002301455301455301,
|
353 |
+
"loss": 0.9003,
|
354 |
+
"step": 550
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 1.11,
|
358 |
+
"learning_rate": 0.00022858627858627858,
|
359 |
+
"loss": 0.9071,
|
360 |
+
"step": 560
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 1.13,
|
364 |
+
"learning_rate": 0.00022702702702702703,
|
365 |
+
"loss": 0.9026,
|
366 |
+
"step": 570
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 1.15,
|
370 |
+
"learning_rate": 0.00022546777546777544,
|
371 |
+
"loss": 0.8845,
|
372 |
+
"step": 580
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 1.16,
|
376 |
+
"learning_rate": 0.0002239085239085239,
|
377 |
+
"loss": 0.9023,
|
378 |
+
"step": 590
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 1.18,
|
382 |
+
"learning_rate": 0.00022234927234927233,
|
383 |
+
"loss": 0.9169,
|
384 |
+
"step": 600
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 1.18,
|
388 |
+
"eval_loss": 0.9196034073829651,
|
389 |
+
"eval_runtime": 44.3139,
|
390 |
+
"eval_samples_per_second": 45.133,
|
391 |
+
"eval_steps_per_second": 0.722,
|
392 |
+
"step": 600
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 1.2,
|
396 |
+
"learning_rate": 0.00022079002079002078,
|
397 |
+
"loss": 0.9015,
|
398 |
+
"step": 610
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 1.22,
|
402 |
+
"learning_rate": 0.0002192307692307692,
|
403 |
+
"loss": 0.9066,
|
404 |
+
"step": 620
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 1.24,
|
408 |
+
"learning_rate": 0.00021767151767151764,
|
409 |
+
"loss": 0.8981,
|
410 |
+
"step": 630
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 1.26,
|
414 |
+
"learning_rate": 0.0002161122661122661,
|
415 |
+
"loss": 0.9023,
|
416 |
+
"step": 640
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.28,
|
420 |
+
"learning_rate": 0.00021455301455301456,
|
421 |
+
"loss": 0.9077,
|
422 |
+
"step": 650
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.3,
|
426 |
+
"learning_rate": 0.00021299376299376295,
|
427 |
+
"loss": 0.9055,
|
428 |
+
"step": 660
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 1.32,
|
432 |
+
"learning_rate": 0.00021143451143451142,
|
433 |
+
"loss": 0.9028,
|
434 |
+
"step": 670
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 1.34,
|
438 |
+
"learning_rate": 0.00020987525987525987,
|
439 |
+
"loss": 0.8874,
|
440 |
+
"step": 680
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 1.36,
|
444 |
+
"learning_rate": 0.0002083160083160083,
|
445 |
+
"loss": 0.8844,
|
446 |
+
"step": 690
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 1.38,
|
450 |
+
"learning_rate": 0.00020675675675675673,
|
451 |
+
"loss": 0.8996,
|
452 |
+
"step": 700
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 1.4,
|
456 |
+
"learning_rate": 0.00020519750519750517,
|
457 |
+
"loss": 0.9085,
|
458 |
+
"step": 710
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.42,
|
462 |
+
"learning_rate": 0.00020363825363825362,
|
463 |
+
"loss": 0.9024,
|
464 |
+
"step": 720
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 1.44,
|
468 |
+
"learning_rate": 0.00020207900207900206,
|
469 |
+
"loss": 0.899,
|
470 |
+
"step": 730
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 1.46,
|
474 |
+
"learning_rate": 0.00020051975051975048,
|
475 |
+
"loss": 0.8926,
|
476 |
+
"step": 740
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 1.48,
|
480 |
+
"learning_rate": 0.00019896049896049893,
|
481 |
+
"loss": 0.89,
|
482 |
+
"step": 750
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 1.5,
|
486 |
+
"learning_rate": 0.0001974012474012474,
|
487 |
+
"loss": 0.8858,
|
488 |
+
"step": 760
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 1.52,
|
492 |
+
"learning_rate": 0.00019584199584199584,
|
493 |
+
"loss": 0.8972,
|
494 |
+
"step": 770
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 1.54,
|
498 |
+
"learning_rate": 0.00019428274428274426,
|
499 |
+
"loss": 0.9003,
|
500 |
+
"step": 780
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 1.56,
|
504 |
+
"learning_rate": 0.0001927234927234927,
|
505 |
+
"loss": 0.8991,
|
506 |
+
"step": 790
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 1.58,
|
510 |
+
"learning_rate": 0.00019116424116424115,
|
511 |
+
"loss": 0.8912,
|
512 |
+
"step": 800
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 1.58,
|
516 |
+
"eval_loss": 0.914772093296051,
|
517 |
+
"eval_runtime": 44.1817,
|
518 |
+
"eval_samples_per_second": 45.268,
|
519 |
+
"eval_steps_per_second": 0.724,
|
520 |
+
"step": 800
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 1.6,
|
524 |
+
"learning_rate": 0.0001896049896049896,
|
525 |
+
"loss": 0.8859,
|
526 |
+
"step": 810
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 1.62,
|
530 |
+
"learning_rate": 0.00018804573804573802,
|
531 |
+
"loss": 0.8942,
|
532 |
+
"step": 820
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 1.64,
|
536 |
+
"learning_rate": 0.00018648648648648646,
|
537 |
+
"loss": 0.8953,
|
538 |
+
"step": 830
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 1.66,
|
542 |
+
"learning_rate": 0.0001849272349272349,
|
543 |
+
"loss": 0.8845,
|
544 |
+
"step": 840
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 1.68,
|
548 |
+
"learning_rate": 0.00018336798336798335,
|
549 |
+
"loss": 0.8871,
|
550 |
+
"step": 850
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 1.7,
|
554 |
+
"learning_rate": 0.00018180873180873177,
|
555 |
+
"loss": 0.8849,
|
556 |
+
"step": 860
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 1.72,
|
560 |
+
"learning_rate": 0.0001802494802494802,
|
561 |
+
"loss": 0.8672,
|
562 |
+
"step": 870
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 1.74,
|
566 |
+
"learning_rate": 0.00017869022869022869,
|
567 |
+
"loss": 0.8811,
|
568 |
+
"step": 880
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 1.76,
|
572 |
+
"learning_rate": 0.00017713097713097713,
|
573 |
+
"loss": 0.8911,
|
574 |
+
"step": 890
|
575 |
+
},
|
576 |
+
{
|
577 |
+
"epoch": 1.78,
|
578 |
+
"learning_rate": 0.00017557172557172555,
|
579 |
+
"loss": 0.8814,
|
580 |
+
"step": 900
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 1.8,
|
584 |
+
"learning_rate": 0.000174012474012474,
|
585 |
+
"loss": 0.8819,
|
586 |
+
"step": 910
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 1.82,
|
590 |
+
"learning_rate": 0.00017245322245322244,
|
591 |
+
"loss": 0.8835,
|
592 |
+
"step": 920
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 1.84,
|
596 |
+
"learning_rate": 0.00017089397089397088,
|
597 |
+
"loss": 0.8768,
|
598 |
+
"step": 930
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 1.86,
|
602 |
+
"learning_rate": 0.0001693347193347193,
|
603 |
+
"loss": 0.8829,
|
604 |
+
"step": 940
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 1.88,
|
608 |
+
"learning_rate": 0.00016777546777546775,
|
609 |
+
"loss": 0.8898,
|
610 |
+
"step": 950
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 1.9,
|
614 |
+
"learning_rate": 0.0001662162162162162,
|
615 |
+
"loss": 0.8884,
|
616 |
+
"step": 960
|
617 |
+
},
|
618 |
+
{
|
619 |
+
"epoch": 1.92,
|
620 |
+
"learning_rate": 0.00016465696465696466,
|
621 |
+
"loss": 0.87,
|
622 |
+
"step": 970
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 1.93,
|
626 |
+
"learning_rate": 0.00016309771309771305,
|
627 |
+
"loss": 0.8851,
|
628 |
+
"step": 980
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 1.95,
|
632 |
+
"learning_rate": 0.00016153846153846153,
|
633 |
+
"loss": 0.8807,
|
634 |
+
"step": 990
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 1.97,
|
638 |
+
"learning_rate": 0.00015997920997920997,
|
639 |
+
"loss": 0.8923,
|
640 |
+
"step": 1000
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 1.97,
|
644 |
+
"eval_loss": 0.9123471975326538,
|
645 |
+
"eval_runtime": 44.1751,
|
646 |
+
"eval_samples_per_second": 45.274,
|
647 |
+
"eval_steps_per_second": 0.724,
|
648 |
+
"step": 1000
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 1.99,
|
652 |
+
"learning_rate": 0.00015841995841995842,
|
653 |
+
"loss": 0.8825,
|
654 |
+
"step": 1010
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 2.01,
|
658 |
+
"learning_rate": 0.00015686070686070683,
|
659 |
+
"loss": 0.878,
|
660 |
+
"step": 1020
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 2.03,
|
664 |
+
"learning_rate": 0.00015530145530145528,
|
665 |
+
"loss": 0.861,
|
666 |
+
"step": 1030
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 2.05,
|
670 |
+
"learning_rate": 0.00015374220374220372,
|
671 |
+
"loss": 0.8652,
|
672 |
+
"step": 1040
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 2.07,
|
676 |
+
"learning_rate": 0.00015218295218295217,
|
677 |
+
"loss": 0.8589,
|
678 |
+
"step": 1050
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 2.09,
|
682 |
+
"learning_rate": 0.0001506237006237006,
|
683 |
+
"loss": 0.8688,
|
684 |
+
"step": 1060
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 2.11,
|
688 |
+
"learning_rate": 0.00014906444906444906,
|
689 |
+
"loss": 0.8796,
|
690 |
+
"step": 1070
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 2.13,
|
694 |
+
"learning_rate": 0.0001475051975051975,
|
695 |
+
"loss": 0.8719,
|
696 |
+
"step": 1080
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 2.15,
|
700 |
+
"learning_rate": 0.00014594594594594595,
|
701 |
+
"loss": 0.8798,
|
702 |
+
"step": 1090
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 2.17,
|
706 |
+
"learning_rate": 0.00014438669438669437,
|
707 |
+
"loss": 0.8669,
|
708 |
+
"step": 1100
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 2.19,
|
712 |
+
"learning_rate": 0.0001428274428274428,
|
713 |
+
"loss": 0.8661,
|
714 |
+
"step": 1110
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 2.21,
|
718 |
+
"learning_rate": 0.00014126819126819126,
|
719 |
+
"loss": 0.8684,
|
720 |
+
"step": 1120
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 2.23,
|
724 |
+
"learning_rate": 0.0001397089397089397,
|
725 |
+
"loss": 0.8591,
|
726 |
+
"step": 1130
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 2.25,
|
730 |
+
"learning_rate": 0.00013814968814968815,
|
731 |
+
"loss": 0.8659,
|
732 |
+
"step": 1140
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 2.27,
|
736 |
+
"learning_rate": 0.0001365904365904366,
|
737 |
+
"loss": 0.868,
|
738 |
+
"step": 1150
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 2.29,
|
742 |
+
"learning_rate": 0.000135031185031185,
|
743 |
+
"loss": 0.871,
|
744 |
+
"step": 1160
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 2.31,
|
748 |
+
"learning_rate": 0.00013347193347193346,
|
749 |
+
"loss": 0.8639,
|
750 |
+
"step": 1170
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 2.33,
|
754 |
+
"learning_rate": 0.0001319126819126819,
|
755 |
+
"loss": 0.8603,
|
756 |
+
"step": 1180
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 2.35,
|
760 |
+
"learning_rate": 0.00013035343035343035,
|
761 |
+
"loss": 0.8617,
|
762 |
+
"step": 1190
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 2.37,
|
766 |
+
"learning_rate": 0.0001287941787941788,
|
767 |
+
"loss": 0.8548,
|
768 |
+
"step": 1200
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 2.37,
|
772 |
+
"eval_loss": 0.9124282002449036,
|
773 |
+
"eval_runtime": 44.2512,
|
774 |
+
"eval_samples_per_second": 45.197,
|
775 |
+
"eval_steps_per_second": 0.723,
|
776 |
+
"step": 1200
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 2.39,
|
780 |
+
"learning_rate": 0.00012723492723492724,
|
781 |
+
"loss": 0.8694,
|
782 |
+
"step": 1210
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 2.41,
|
786 |
+
"learning_rate": 0.00012567567567567565,
|
787 |
+
"loss": 0.8651,
|
788 |
+
"step": 1220
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 2.43,
|
792 |
+
"learning_rate": 0.00012411642411642413,
|
793 |
+
"loss": 0.8606,
|
794 |
+
"step": 1230
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 2.45,
|
798 |
+
"learning_rate": 0.00012255717255717254,
|
799 |
+
"loss": 0.8678,
|
800 |
+
"step": 1240
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 2.47,
|
804 |
+
"learning_rate": 0.00012099792099792099,
|
805 |
+
"loss": 0.8676,
|
806 |
+
"step": 1250
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 2.49,
|
810 |
+
"learning_rate": 0.00011943866943866943,
|
811 |
+
"loss": 0.8602,
|
812 |
+
"step": 1260
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 2.51,
|
816 |
+
"learning_rate": 0.00011787941787941788,
|
817 |
+
"loss": 0.8718,
|
818 |
+
"step": 1270
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 2.53,
|
822 |
+
"learning_rate": 0.00011632016632016631,
|
823 |
+
"loss": 0.8618,
|
824 |
+
"step": 1280
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 2.55,
|
828 |
+
"learning_rate": 0.00011476091476091475,
|
829 |
+
"loss": 0.8677,
|
830 |
+
"step": 1290
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 2.57,
|
834 |
+
"learning_rate": 0.00011320166320166319,
|
835 |
+
"loss": 0.844,
|
836 |
+
"step": 1300
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 2.59,
|
840 |
+
"learning_rate": 0.00011164241164241164,
|
841 |
+
"loss": 0.8653,
|
842 |
+
"step": 1310
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 2.61,
|
846 |
+
"learning_rate": 0.00011008316008316008,
|
847 |
+
"loss": 0.8639,
|
848 |
+
"step": 1320
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 2.63,
|
852 |
+
"learning_rate": 0.00010852390852390852,
|
853 |
+
"loss": 0.873,
|
854 |
+
"step": 1330
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 2.65,
|
858 |
+
"learning_rate": 0.00010696465696465695,
|
859 |
+
"loss": 0.8639,
|
860 |
+
"step": 1340
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 2.67,
|
864 |
+
"learning_rate": 0.0001054054054054054,
|
865 |
+
"loss": 0.8545,
|
866 |
+
"step": 1350
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 2.69,
|
870 |
+
"learning_rate": 0.00010384615384615383,
|
871 |
+
"loss": 0.8654,
|
872 |
+
"step": 1360
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 2.7,
|
876 |
+
"learning_rate": 0.00010228690228690229,
|
877 |
+
"loss": 0.8555,
|
878 |
+
"step": 1370
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 2.72,
|
882 |
+
"learning_rate": 0.00010072765072765072,
|
883 |
+
"loss": 0.8707,
|
884 |
+
"step": 1380
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 2.74,
|
888 |
+
"learning_rate": 9.916839916839916e-05,
|
889 |
+
"loss": 0.8452,
|
890 |
+
"step": 1390
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 2.76,
|
894 |
+
"learning_rate": 9.76091476091476e-05,
|
895 |
+
"loss": 0.8512,
|
896 |
+
"step": 1400
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 2.76,
|
900 |
+
"eval_loss": 0.9109137058258057,
|
901 |
+
"eval_runtime": 44.368,
|
902 |
+
"eval_samples_per_second": 45.077,
|
903 |
+
"eval_steps_per_second": 0.721,
|
904 |
+
"step": 1400
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 2.78,
|
908 |
+
"learning_rate": 9.604989604989604e-05,
|
909 |
+
"loss": 0.8485,
|
910 |
+
"step": 1410
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"epoch": 2.8,
|
914 |
+
"learning_rate": 9.449064449064449e-05,
|
915 |
+
"loss": 0.8635,
|
916 |
+
"step": 1420
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 2.82,
|
920 |
+
"learning_rate": 9.293139293139293e-05,
|
921 |
+
"loss": 0.8499,
|
922 |
+
"step": 1430
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 2.84,
|
926 |
+
"learning_rate": 9.137214137214136e-05,
|
927 |
+
"loss": 0.855,
|
928 |
+
"step": 1440
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 2.86,
|
932 |
+
"learning_rate": 8.98128898128898e-05,
|
933 |
+
"loss": 0.8437,
|
934 |
+
"step": 1450
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 2.88,
|
938 |
+
"learning_rate": 8.825363825363824e-05,
|
939 |
+
"loss": 0.8552,
|
940 |
+
"step": 1460
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 2.9,
|
944 |
+
"learning_rate": 8.66943866943867e-05,
|
945 |
+
"loss": 0.845,
|
946 |
+
"step": 1470
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 2.92,
|
950 |
+
"learning_rate": 8.513513513513513e-05,
|
951 |
+
"loss": 0.8591,
|
952 |
+
"step": 1480
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 2.94,
|
956 |
+
"learning_rate": 8.357588357588357e-05,
|
957 |
+
"loss": 0.8559,
|
958 |
+
"step": 1490
|
959 |
+
},
|
960 |
+
{
|
961 |
+
"epoch": 2.96,
|
962 |
+
"learning_rate": 8.2016632016632e-05,
|
963 |
+
"loss": 0.8562,
|
964 |
+
"step": 1500
|
965 |
+
},
|
966 |
+
{
|
967 |
+
"epoch": 2.98,
|
968 |
+
"learning_rate": 8.045738045738045e-05,
|
969 |
+
"loss": 0.8585,
|
970 |
+
"step": 1510
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 3.0,
|
974 |
+
"learning_rate": 7.889812889812888e-05,
|
975 |
+
"loss": 0.8627,
|
976 |
+
"step": 1520
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 3.02,
|
980 |
+
"learning_rate": 7.733887733887734e-05,
|
981 |
+
"loss": 0.849,
|
982 |
+
"step": 1530
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 3.04,
|
986 |
+
"learning_rate": 7.577962577962577e-05,
|
987 |
+
"loss": 0.8479,
|
988 |
+
"step": 1540
|
989 |
+
},
|
990 |
+
{
|
991 |
+
"epoch": 3.06,
|
992 |
+
"learning_rate": 7.422037422037422e-05,
|
993 |
+
"loss": 0.8522,
|
994 |
+
"step": 1550
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 3.08,
|
998 |
+
"learning_rate": 7.266112266112266e-05,
|
999 |
+
"loss": 0.8535,
|
1000 |
+
"step": 1560
|
1001 |
+
},
|
1002 |
+
{
|
1003 |
+
"epoch": 3.1,
|
1004 |
+
"learning_rate": 7.11018711018711e-05,
|
1005 |
+
"loss": 0.862,
|
1006 |
+
"step": 1570
|
1007 |
+
},
|
1008 |
+
{
|
1009 |
+
"epoch": 3.12,
|
1010 |
+
"learning_rate": 6.954261954261954e-05,
|
1011 |
+
"loss": 0.8618,
|
1012 |
+
"step": 1580
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"epoch": 3.14,
|
1016 |
+
"learning_rate": 6.798336798336798e-05,
|
1017 |
+
"loss": 0.8478,
|
1018 |
+
"step": 1590
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 3.16,
|
1022 |
+
"learning_rate": 6.642411642411643e-05,
|
1023 |
+
"loss": 0.8467,
|
1024 |
+
"step": 1600
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 3.16,
|
1028 |
+
"eval_loss": 0.9100631475448608,
|
1029 |
+
"eval_runtime": 44.1701,
|
1030 |
+
"eval_samples_per_second": 45.279,
|
1031 |
+
"eval_steps_per_second": 0.724,
|
1032 |
+
"step": 1600
|
1033 |
+
}
|
1034 |
+
],
|
1035 |
+
"max_steps": 2024,
|
1036 |
+
"num_train_epochs": 4,
|
1037 |
+
"total_flos": 6.463426043855241e+18,
|
1038 |
+
"trial_name": null,
|
1039 |
+
"trial_params": null
|
1040 |
+
}
|
checkpoint-1600/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:421eeaebb0bf48e1dc571c1d5708e71cf221377fdbb08f85d14f26308c08f2d3
|
3 |
+
size 3579
|
checkpoint-1800/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c72d18ee0325ef9ba159988d9b9826821c7ad11dc2cfe33a90e73a80156a70b5
|
3 |
+
size 209984517
|
checkpoint-1800/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba02c114434faf8b1dca36b810ab6c7427e43e3f6282a2d11c352b6ddac55c20
|
3 |
+
size 104973389
|
checkpoint-1800/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd548388ab19fd42bf394dd82b8523a52f1698d04d765499c7a134e8230900af
|
3 |
+
size 14583
|
checkpoint-1800/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38d84b15f55fe9b3bc8b59220f664b8716febf6c796400693b0d3ad04ff6b5dd
|
3 |
+
size 14583
|
checkpoint-1800/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0f4265693300d34fa81892c88fe9d0634d7dbfd627c79c2d6f82af0b6d8dcdc
|
3 |
+
size 14583
|
checkpoint-1800/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e391ee975f8df8baba97e8f810e32da3e169e446b30d281698f10fd1665d12ea
|
3 |
+
size 14583
|
checkpoint-1800/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5d599b99889ac699c341ec7c72e66429a7777fc591500f4fa41ac13f1566812
|
3 |
+
size 14583
|
checkpoint-1800/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77cdfe23a98f304e1d8d3d0d7d9088ce7a9aa0ebfa7bcafaaad23bb59fb414ac
|
3 |
+
size 14583
|
checkpoint-1800/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e417293866703b744e94745f2542fb8056718560eb97419255868f24144b9f0
|
3 |
+
size 14583
|
checkpoint-1800/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95aa570f4b62401cce558d445eb68fde630d9ddbc679ff0c17c059a931caf896
|
3 |
+
size 14583
|
checkpoint-1800/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78f9984dfed69108b5e9f4231cdff5fa6f419ba9be80a4bf7f7678243f7d1d36
|
3 |
+
size 557
|
checkpoint-1800/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84e73ec2284d3afc40e79a0356e1a365dc6f8567a247df57a5bff0656c901f86
|
3 |
+
size 627
|
checkpoint-1800/trainer_state.json
ADDED
@@ -0,0 +1,1168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9100631475448608,
|
3 |
+
"best_model_checkpoint": "./lora-alpaca/checkpoint-1600",
|
4 |
+
"epoch": 3.5538005923000986,
|
5 |
+
"global_step": 1800,
|
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": 2.3999999999999997e-05,
|
13 |
+
"loss": 1.5473,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.04,
|
18 |
+
"learning_rate": 5.399999999999999e-05,
|
19 |
+
"loss": 1.5181,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.06,
|
24 |
+
"learning_rate": 8.4e-05,
|
25 |
+
"loss": 1.3749,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.08,
|
30 |
+
"learning_rate": 0.00011399999999999999,
|
31 |
+
"loss": 1.1669,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.1,
|
36 |
+
"learning_rate": 0.00014399999999999998,
|
37 |
+
"loss": 1.0525,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.12,
|
42 |
+
"learning_rate": 0.00017399999999999997,
|
43 |
+
"loss": 1.0376,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.14,
|
48 |
+
"learning_rate": 0.000204,
|
49 |
+
"loss": 1.0043,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.16,
|
54 |
+
"learning_rate": 0.000234,
|
55 |
+
"loss": 0.9849,
|
56 |
+
"step": 80
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.18,
|
60 |
+
"learning_rate": 0.00026399999999999997,
|
61 |
+
"loss": 0.9821,
|
62 |
+
"step": 90
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.2,
|
66 |
+
"learning_rate": 0.000294,
|
67 |
+
"loss": 0.9846,
|
68 |
+
"step": 100
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.22,
|
72 |
+
"learning_rate": 0.0002987525987525987,
|
73 |
+
"loss": 0.9635,
|
74 |
+
"step": 110
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.24,
|
78 |
+
"learning_rate": 0.00029719334719334716,
|
79 |
+
"loss": 0.9538,
|
80 |
+
"step": 120
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.26,
|
84 |
+
"learning_rate": 0.0002956340956340956,
|
85 |
+
"loss": 0.9408,
|
86 |
+
"step": 130
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.28,
|
90 |
+
"learning_rate": 0.00029407484407484405,
|
91 |
+
"loss": 0.9529,
|
92 |
+
"step": 140
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.3,
|
96 |
+
"learning_rate": 0.0002925155925155925,
|
97 |
+
"loss": 0.9622,
|
98 |
+
"step": 150
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.32,
|
102 |
+
"learning_rate": 0.00029095634095634094,
|
103 |
+
"loss": 0.9517,
|
104 |
+
"step": 160
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.34,
|
108 |
+
"learning_rate": 0.0002893970893970894,
|
109 |
+
"loss": 0.9624,
|
110 |
+
"step": 170
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.36,
|
114 |
+
"learning_rate": 0.0002878378378378378,
|
115 |
+
"loss": 0.9445,
|
116 |
+
"step": 180
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.38,
|
120 |
+
"learning_rate": 0.0002862785862785863,
|
121 |
+
"loss": 0.9428,
|
122 |
+
"step": 190
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.39,
|
126 |
+
"learning_rate": 0.0002847193347193347,
|
127 |
+
"loss": 0.9372,
|
128 |
+
"step": 200
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.39,
|
132 |
+
"eval_loss": 0.9433729648590088,
|
133 |
+
"eval_runtime": 44.3089,
|
134 |
+
"eval_samples_per_second": 45.138,
|
135 |
+
"eval_steps_per_second": 0.722,
|
136 |
+
"step": 200
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.41,
|
140 |
+
"learning_rate": 0.00028316008316008317,
|
141 |
+
"loss": 0.9388,
|
142 |
+
"step": 210
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.43,
|
146 |
+
"learning_rate": 0.00028160083160083156,
|
147 |
+
"loss": 0.9412,
|
148 |
+
"step": 220
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 0.45,
|
152 |
+
"learning_rate": 0.00028004158004158,
|
153 |
+
"loss": 0.9365,
|
154 |
+
"step": 230
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 0.47,
|
158 |
+
"learning_rate": 0.00027848232848232845,
|
159 |
+
"loss": 0.9382,
|
160 |
+
"step": 240
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 0.49,
|
164 |
+
"learning_rate": 0.0002769230769230769,
|
165 |
+
"loss": 0.9309,
|
166 |
+
"step": 250
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 0.51,
|
170 |
+
"learning_rate": 0.00027536382536382534,
|
171 |
+
"loss": 0.9256,
|
172 |
+
"step": 260
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.53,
|
176 |
+
"learning_rate": 0.0002738045738045738,
|
177 |
+
"loss": 0.9245,
|
178 |
+
"step": 270
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.55,
|
182 |
+
"learning_rate": 0.00027224532224532223,
|
183 |
+
"loss": 0.9329,
|
184 |
+
"step": 280
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.57,
|
188 |
+
"learning_rate": 0.0002706860706860707,
|
189 |
+
"loss": 0.9405,
|
190 |
+
"step": 290
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 0.59,
|
194 |
+
"learning_rate": 0.0002691268191268191,
|
195 |
+
"loss": 0.9168,
|
196 |
+
"step": 300
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 0.61,
|
200 |
+
"learning_rate": 0.00026756756756756756,
|
201 |
+
"loss": 0.92,
|
202 |
+
"step": 310
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 0.63,
|
206 |
+
"learning_rate": 0.000266008316008316,
|
207 |
+
"loss": 0.9098,
|
208 |
+
"step": 320
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 0.65,
|
212 |
+
"learning_rate": 0.00026444906444906445,
|
213 |
+
"loss": 0.9275,
|
214 |
+
"step": 330
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.67,
|
218 |
+
"learning_rate": 0.00026288981288981285,
|
219 |
+
"loss": 0.9215,
|
220 |
+
"step": 340
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.69,
|
224 |
+
"learning_rate": 0.0002613305613305613,
|
225 |
+
"loss": 0.9237,
|
226 |
+
"step": 350
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.71,
|
230 |
+
"learning_rate": 0.00025977130977130974,
|
231 |
+
"loss": 0.9237,
|
232 |
+
"step": 360
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 0.73,
|
236 |
+
"learning_rate": 0.0002582120582120582,
|
237 |
+
"loss": 0.928,
|
238 |
+
"step": 370
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 0.75,
|
242 |
+
"learning_rate": 0.0002566528066528066,
|
243 |
+
"loss": 0.9156,
|
244 |
+
"step": 380
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 0.77,
|
248 |
+
"learning_rate": 0.00025509355509355507,
|
249 |
+
"loss": 0.9255,
|
250 |
+
"step": 390
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 0.79,
|
254 |
+
"learning_rate": 0.0002535343035343035,
|
255 |
+
"loss": 0.9102,
|
256 |
+
"step": 400
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.79,
|
260 |
+
"eval_loss": 0.9269554615020752,
|
261 |
+
"eval_runtime": 44.228,
|
262 |
+
"eval_samples_per_second": 45.22,
|
263 |
+
"eval_steps_per_second": 0.724,
|
264 |
+
"step": 400
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.81,
|
268 |
+
"learning_rate": 0.00025197505197505196,
|
269 |
+
"loss": 0.9312,
|
270 |
+
"step": 410
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.83,
|
274 |
+
"learning_rate": 0.0002504158004158004,
|
275 |
+
"loss": 0.9249,
|
276 |
+
"step": 420
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.85,
|
280 |
+
"learning_rate": 0.00024885654885654885,
|
281 |
+
"loss": 0.9151,
|
282 |
+
"step": 430
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.87,
|
286 |
+
"learning_rate": 0.0002472972972972973,
|
287 |
+
"loss": 0.9265,
|
288 |
+
"step": 440
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 0.89,
|
292 |
+
"learning_rate": 0.00024573804573804574,
|
293 |
+
"loss": 0.9064,
|
294 |
+
"step": 450
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.91,
|
298 |
+
"learning_rate": 0.00024417879417879413,
|
299 |
+
"loss": 0.9185,
|
300 |
+
"step": 460
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 0.93,
|
304 |
+
"learning_rate": 0.0002426195426195426,
|
305 |
+
"loss": 0.9128,
|
306 |
+
"step": 470
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 0.95,
|
310 |
+
"learning_rate": 0.00024106029106029105,
|
311 |
+
"loss": 0.9159,
|
312 |
+
"step": 480
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.97,
|
316 |
+
"learning_rate": 0.0002395010395010395,
|
317 |
+
"loss": 0.8987,
|
318 |
+
"step": 490
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.99,
|
322 |
+
"learning_rate": 0.0002379417879417879,
|
323 |
+
"loss": 0.9217,
|
324 |
+
"step": 500
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 1.01,
|
328 |
+
"learning_rate": 0.00023638253638253636,
|
329 |
+
"loss": 0.906,
|
330 |
+
"step": 510
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 1.03,
|
334 |
+
"learning_rate": 0.0002348232848232848,
|
335 |
+
"loss": 0.9066,
|
336 |
+
"step": 520
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 1.05,
|
340 |
+
"learning_rate": 0.00023326403326403325,
|
341 |
+
"loss": 0.9085,
|
342 |
+
"step": 530
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 1.07,
|
346 |
+
"learning_rate": 0.00023170478170478166,
|
347 |
+
"loss": 0.9203,
|
348 |
+
"step": 540
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 1.09,
|
352 |
+
"learning_rate": 0.0002301455301455301,
|
353 |
+
"loss": 0.9003,
|
354 |
+
"step": 550
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 1.11,
|
358 |
+
"learning_rate": 0.00022858627858627858,
|
359 |
+
"loss": 0.9071,
|
360 |
+
"step": 560
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 1.13,
|
364 |
+
"learning_rate": 0.00022702702702702703,
|
365 |
+
"loss": 0.9026,
|
366 |
+
"step": 570
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 1.15,
|
370 |
+
"learning_rate": 0.00022546777546777544,
|
371 |
+
"loss": 0.8845,
|
372 |
+
"step": 580
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 1.16,
|
376 |
+
"learning_rate": 0.0002239085239085239,
|
377 |
+
"loss": 0.9023,
|
378 |
+
"step": 590
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 1.18,
|
382 |
+
"learning_rate": 0.00022234927234927233,
|
383 |
+
"loss": 0.9169,
|
384 |
+
"step": 600
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 1.18,
|
388 |
+
"eval_loss": 0.9196034073829651,
|
389 |
+
"eval_runtime": 44.3139,
|
390 |
+
"eval_samples_per_second": 45.133,
|
391 |
+
"eval_steps_per_second": 0.722,
|
392 |
+
"step": 600
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 1.2,
|
396 |
+
"learning_rate": 0.00022079002079002078,
|
397 |
+
"loss": 0.9015,
|
398 |
+
"step": 610
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 1.22,
|
402 |
+
"learning_rate": 0.0002192307692307692,
|
403 |
+
"loss": 0.9066,
|
404 |
+
"step": 620
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 1.24,
|
408 |
+
"learning_rate": 0.00021767151767151764,
|
409 |
+
"loss": 0.8981,
|
410 |
+
"step": 630
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 1.26,
|
414 |
+
"learning_rate": 0.0002161122661122661,
|
415 |
+
"loss": 0.9023,
|
416 |
+
"step": 640
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.28,
|
420 |
+
"learning_rate": 0.00021455301455301456,
|
421 |
+
"loss": 0.9077,
|
422 |
+
"step": 650
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.3,
|
426 |
+
"learning_rate": 0.00021299376299376295,
|
427 |
+
"loss": 0.9055,
|
428 |
+
"step": 660
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 1.32,
|
432 |
+
"learning_rate": 0.00021143451143451142,
|
433 |
+
"loss": 0.9028,
|
434 |
+
"step": 670
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 1.34,
|
438 |
+
"learning_rate": 0.00020987525987525987,
|
439 |
+
"loss": 0.8874,
|
440 |
+
"step": 680
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 1.36,
|
444 |
+
"learning_rate": 0.0002083160083160083,
|
445 |
+
"loss": 0.8844,
|
446 |
+
"step": 690
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 1.38,
|
450 |
+
"learning_rate": 0.00020675675675675673,
|
451 |
+
"loss": 0.8996,
|
452 |
+
"step": 700
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 1.4,
|
456 |
+
"learning_rate": 0.00020519750519750517,
|
457 |
+
"loss": 0.9085,
|
458 |
+
"step": 710
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.42,
|
462 |
+
"learning_rate": 0.00020363825363825362,
|
463 |
+
"loss": 0.9024,
|
464 |
+
"step": 720
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 1.44,
|
468 |
+
"learning_rate": 0.00020207900207900206,
|
469 |
+
"loss": 0.899,
|
470 |
+
"step": 730
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 1.46,
|
474 |
+
"learning_rate": 0.00020051975051975048,
|
475 |
+
"loss": 0.8926,
|
476 |
+
"step": 740
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 1.48,
|
480 |
+
"learning_rate": 0.00019896049896049893,
|
481 |
+
"loss": 0.89,
|
482 |
+
"step": 750
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 1.5,
|
486 |
+
"learning_rate": 0.0001974012474012474,
|
487 |
+
"loss": 0.8858,
|
488 |
+
"step": 760
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 1.52,
|
492 |
+
"learning_rate": 0.00019584199584199584,
|
493 |
+
"loss": 0.8972,
|
494 |
+
"step": 770
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 1.54,
|
498 |
+
"learning_rate": 0.00019428274428274426,
|
499 |
+
"loss": 0.9003,
|
500 |
+
"step": 780
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 1.56,
|
504 |
+
"learning_rate": 0.0001927234927234927,
|
505 |
+
"loss": 0.8991,
|
506 |
+
"step": 790
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 1.58,
|
510 |
+
"learning_rate": 0.00019116424116424115,
|
511 |
+
"loss": 0.8912,
|
512 |
+
"step": 800
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 1.58,
|
516 |
+
"eval_loss": 0.914772093296051,
|
517 |
+
"eval_runtime": 44.1817,
|
518 |
+
"eval_samples_per_second": 45.268,
|
519 |
+
"eval_steps_per_second": 0.724,
|
520 |
+
"step": 800
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 1.6,
|
524 |
+
"learning_rate": 0.0001896049896049896,
|
525 |
+
"loss": 0.8859,
|
526 |
+
"step": 810
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 1.62,
|
530 |
+
"learning_rate": 0.00018804573804573802,
|
531 |
+
"loss": 0.8942,
|
532 |
+
"step": 820
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 1.64,
|
536 |
+
"learning_rate": 0.00018648648648648646,
|
537 |
+
"loss": 0.8953,
|
538 |
+
"step": 830
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 1.66,
|
542 |
+
"learning_rate": 0.0001849272349272349,
|
543 |
+
"loss": 0.8845,
|
544 |
+
"step": 840
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 1.68,
|
548 |
+
"learning_rate": 0.00018336798336798335,
|
549 |
+
"loss": 0.8871,
|
550 |
+
"step": 850
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 1.7,
|
554 |
+
"learning_rate": 0.00018180873180873177,
|
555 |
+
"loss": 0.8849,
|
556 |
+
"step": 860
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 1.72,
|
560 |
+
"learning_rate": 0.0001802494802494802,
|
561 |
+
"loss": 0.8672,
|
562 |
+
"step": 870
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 1.74,
|
566 |
+
"learning_rate": 0.00017869022869022869,
|
567 |
+
"loss": 0.8811,
|
568 |
+
"step": 880
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 1.76,
|
572 |
+
"learning_rate": 0.00017713097713097713,
|
573 |
+
"loss": 0.8911,
|
574 |
+
"step": 890
|
575 |
+
},
|
576 |
+
{
|
577 |
+
"epoch": 1.78,
|
578 |
+
"learning_rate": 0.00017557172557172555,
|
579 |
+
"loss": 0.8814,
|
580 |
+
"step": 900
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 1.8,
|
584 |
+
"learning_rate": 0.000174012474012474,
|
585 |
+
"loss": 0.8819,
|
586 |
+
"step": 910
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 1.82,
|
590 |
+
"learning_rate": 0.00017245322245322244,
|
591 |
+
"loss": 0.8835,
|
592 |
+
"step": 920
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 1.84,
|
596 |
+
"learning_rate": 0.00017089397089397088,
|
597 |
+
"loss": 0.8768,
|
598 |
+
"step": 930
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 1.86,
|
602 |
+
"learning_rate": 0.0001693347193347193,
|
603 |
+
"loss": 0.8829,
|
604 |
+
"step": 940
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 1.88,
|
608 |
+
"learning_rate": 0.00016777546777546775,
|
609 |
+
"loss": 0.8898,
|
610 |
+
"step": 950
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 1.9,
|
614 |
+
"learning_rate": 0.0001662162162162162,
|
615 |
+
"loss": 0.8884,
|
616 |
+
"step": 960
|
617 |
+
},
|
618 |
+
{
|
619 |
+
"epoch": 1.92,
|
620 |
+
"learning_rate": 0.00016465696465696466,
|
621 |
+
"loss": 0.87,
|
622 |
+
"step": 970
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 1.93,
|
626 |
+
"learning_rate": 0.00016309771309771305,
|
627 |
+
"loss": 0.8851,
|
628 |
+
"step": 980
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 1.95,
|
632 |
+
"learning_rate": 0.00016153846153846153,
|
633 |
+
"loss": 0.8807,
|
634 |
+
"step": 990
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 1.97,
|
638 |
+
"learning_rate": 0.00015997920997920997,
|
639 |
+
"loss": 0.8923,
|
640 |
+
"step": 1000
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 1.97,
|
644 |
+
"eval_loss": 0.9123471975326538,
|
645 |
+
"eval_runtime": 44.1751,
|
646 |
+
"eval_samples_per_second": 45.274,
|
647 |
+
"eval_steps_per_second": 0.724,
|
648 |
+
"step": 1000
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 1.99,
|
652 |
+
"learning_rate": 0.00015841995841995842,
|
653 |
+
"loss": 0.8825,
|
654 |
+
"step": 1010
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 2.01,
|
658 |
+
"learning_rate": 0.00015686070686070683,
|
659 |
+
"loss": 0.878,
|
660 |
+
"step": 1020
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 2.03,
|
664 |
+
"learning_rate": 0.00015530145530145528,
|
665 |
+
"loss": 0.861,
|
666 |
+
"step": 1030
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 2.05,
|
670 |
+
"learning_rate": 0.00015374220374220372,
|
671 |
+
"loss": 0.8652,
|
672 |
+
"step": 1040
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 2.07,
|
676 |
+
"learning_rate": 0.00015218295218295217,
|
677 |
+
"loss": 0.8589,
|
678 |
+
"step": 1050
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 2.09,
|
682 |
+
"learning_rate": 0.0001506237006237006,
|
683 |
+
"loss": 0.8688,
|
684 |
+
"step": 1060
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 2.11,
|
688 |
+
"learning_rate": 0.00014906444906444906,
|
689 |
+
"loss": 0.8796,
|
690 |
+
"step": 1070
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 2.13,
|
694 |
+
"learning_rate": 0.0001475051975051975,
|
695 |
+
"loss": 0.8719,
|
696 |
+
"step": 1080
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 2.15,
|
700 |
+
"learning_rate": 0.00014594594594594595,
|
701 |
+
"loss": 0.8798,
|
702 |
+
"step": 1090
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 2.17,
|
706 |
+
"learning_rate": 0.00014438669438669437,
|
707 |
+
"loss": 0.8669,
|
708 |
+
"step": 1100
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 2.19,
|
712 |
+
"learning_rate": 0.0001428274428274428,
|
713 |
+
"loss": 0.8661,
|
714 |
+
"step": 1110
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 2.21,
|
718 |
+
"learning_rate": 0.00014126819126819126,
|
719 |
+
"loss": 0.8684,
|
720 |
+
"step": 1120
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 2.23,
|
724 |
+
"learning_rate": 0.0001397089397089397,
|
725 |
+
"loss": 0.8591,
|
726 |
+
"step": 1130
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 2.25,
|
730 |
+
"learning_rate": 0.00013814968814968815,
|
731 |
+
"loss": 0.8659,
|
732 |
+
"step": 1140
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 2.27,
|
736 |
+
"learning_rate": 0.0001365904365904366,
|
737 |
+
"loss": 0.868,
|
738 |
+
"step": 1150
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 2.29,
|
742 |
+
"learning_rate": 0.000135031185031185,
|
743 |
+
"loss": 0.871,
|
744 |
+
"step": 1160
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 2.31,
|
748 |
+
"learning_rate": 0.00013347193347193346,
|
749 |
+
"loss": 0.8639,
|
750 |
+
"step": 1170
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 2.33,
|
754 |
+
"learning_rate": 0.0001319126819126819,
|
755 |
+
"loss": 0.8603,
|
756 |
+
"step": 1180
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 2.35,
|
760 |
+
"learning_rate": 0.00013035343035343035,
|
761 |
+
"loss": 0.8617,
|
762 |
+
"step": 1190
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 2.37,
|
766 |
+
"learning_rate": 0.0001287941787941788,
|
767 |
+
"loss": 0.8548,
|
768 |
+
"step": 1200
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 2.37,
|
772 |
+
"eval_loss": 0.9124282002449036,
|
773 |
+
"eval_runtime": 44.2512,
|
774 |
+
"eval_samples_per_second": 45.197,
|
775 |
+
"eval_steps_per_second": 0.723,
|
776 |
+
"step": 1200
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 2.39,
|
780 |
+
"learning_rate": 0.00012723492723492724,
|
781 |
+
"loss": 0.8694,
|
782 |
+
"step": 1210
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 2.41,
|
786 |
+
"learning_rate": 0.00012567567567567565,
|
787 |
+
"loss": 0.8651,
|
788 |
+
"step": 1220
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 2.43,
|
792 |
+
"learning_rate": 0.00012411642411642413,
|
793 |
+
"loss": 0.8606,
|
794 |
+
"step": 1230
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 2.45,
|
798 |
+
"learning_rate": 0.00012255717255717254,
|
799 |
+
"loss": 0.8678,
|
800 |
+
"step": 1240
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 2.47,
|
804 |
+
"learning_rate": 0.00012099792099792099,
|
805 |
+
"loss": 0.8676,
|
806 |
+
"step": 1250
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 2.49,
|
810 |
+
"learning_rate": 0.00011943866943866943,
|
811 |
+
"loss": 0.8602,
|
812 |
+
"step": 1260
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 2.51,
|
816 |
+
"learning_rate": 0.00011787941787941788,
|
817 |
+
"loss": 0.8718,
|
818 |
+
"step": 1270
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 2.53,
|
822 |
+
"learning_rate": 0.00011632016632016631,
|
823 |
+
"loss": 0.8618,
|
824 |
+
"step": 1280
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 2.55,
|
828 |
+
"learning_rate": 0.00011476091476091475,
|
829 |
+
"loss": 0.8677,
|
830 |
+
"step": 1290
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 2.57,
|
834 |
+
"learning_rate": 0.00011320166320166319,
|
835 |
+
"loss": 0.844,
|
836 |
+
"step": 1300
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 2.59,
|
840 |
+
"learning_rate": 0.00011164241164241164,
|
841 |
+
"loss": 0.8653,
|
842 |
+
"step": 1310
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 2.61,
|
846 |
+
"learning_rate": 0.00011008316008316008,
|
847 |
+
"loss": 0.8639,
|
848 |
+
"step": 1320
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 2.63,
|
852 |
+
"learning_rate": 0.00010852390852390852,
|
853 |
+
"loss": 0.873,
|
854 |
+
"step": 1330
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 2.65,
|
858 |
+
"learning_rate": 0.00010696465696465695,
|
859 |
+
"loss": 0.8639,
|
860 |
+
"step": 1340
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 2.67,
|
864 |
+
"learning_rate": 0.0001054054054054054,
|
865 |
+
"loss": 0.8545,
|
866 |
+
"step": 1350
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 2.69,
|
870 |
+
"learning_rate": 0.00010384615384615383,
|
871 |
+
"loss": 0.8654,
|
872 |
+
"step": 1360
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 2.7,
|
876 |
+
"learning_rate": 0.00010228690228690229,
|
877 |
+
"loss": 0.8555,
|
878 |
+
"step": 1370
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 2.72,
|
882 |
+
"learning_rate": 0.00010072765072765072,
|
883 |
+
"loss": 0.8707,
|
884 |
+
"step": 1380
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 2.74,
|
888 |
+
"learning_rate": 9.916839916839916e-05,
|
889 |
+
"loss": 0.8452,
|
890 |
+
"step": 1390
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 2.76,
|
894 |
+
"learning_rate": 9.76091476091476e-05,
|
895 |
+
"loss": 0.8512,
|
896 |
+
"step": 1400
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 2.76,
|
900 |
+
"eval_loss": 0.9109137058258057,
|
901 |
+
"eval_runtime": 44.368,
|
902 |
+
"eval_samples_per_second": 45.077,
|
903 |
+
"eval_steps_per_second": 0.721,
|
904 |
+
"step": 1400
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 2.78,
|
908 |
+
"learning_rate": 9.604989604989604e-05,
|
909 |
+
"loss": 0.8485,
|
910 |
+
"step": 1410
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"epoch": 2.8,
|
914 |
+
"learning_rate": 9.449064449064449e-05,
|
915 |
+
"loss": 0.8635,
|
916 |
+
"step": 1420
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 2.82,
|
920 |
+
"learning_rate": 9.293139293139293e-05,
|
921 |
+
"loss": 0.8499,
|
922 |
+
"step": 1430
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 2.84,
|
926 |
+
"learning_rate": 9.137214137214136e-05,
|
927 |
+
"loss": 0.855,
|
928 |
+
"step": 1440
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 2.86,
|
932 |
+
"learning_rate": 8.98128898128898e-05,
|
933 |
+
"loss": 0.8437,
|
934 |
+
"step": 1450
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 2.88,
|
938 |
+
"learning_rate": 8.825363825363824e-05,
|
939 |
+
"loss": 0.8552,
|
940 |
+
"step": 1460
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 2.9,
|
944 |
+
"learning_rate": 8.66943866943867e-05,
|
945 |
+
"loss": 0.845,
|
946 |
+
"step": 1470
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 2.92,
|
950 |
+
"learning_rate": 8.513513513513513e-05,
|
951 |
+
"loss": 0.8591,
|
952 |
+
"step": 1480
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 2.94,
|
956 |
+
"learning_rate": 8.357588357588357e-05,
|
957 |
+
"loss": 0.8559,
|
958 |
+
"step": 1490
|
959 |
+
},
|
960 |
+
{
|
961 |
+
"epoch": 2.96,
|
962 |
+
"learning_rate": 8.2016632016632e-05,
|
963 |
+
"loss": 0.8562,
|
964 |
+
"step": 1500
|
965 |
+
},
|
966 |
+
{
|
967 |
+
"epoch": 2.98,
|
968 |
+
"learning_rate": 8.045738045738045e-05,
|
969 |
+
"loss": 0.8585,
|
970 |
+
"step": 1510
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 3.0,
|
974 |
+
"learning_rate": 7.889812889812888e-05,
|
975 |
+
"loss": 0.8627,
|
976 |
+
"step": 1520
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 3.02,
|
980 |
+
"learning_rate": 7.733887733887734e-05,
|
981 |
+
"loss": 0.849,
|
982 |
+
"step": 1530
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 3.04,
|
986 |
+
"learning_rate": 7.577962577962577e-05,
|
987 |
+
"loss": 0.8479,
|
988 |
+
"step": 1540
|
989 |
+
},
|
990 |
+
{
|
991 |
+
"epoch": 3.06,
|
992 |
+
"learning_rate": 7.422037422037422e-05,
|
993 |
+
"loss": 0.8522,
|
994 |
+
"step": 1550
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 3.08,
|
998 |
+
"learning_rate": 7.266112266112266e-05,
|
999 |
+
"loss": 0.8535,
|
1000 |
+
"step": 1560
|
1001 |
+
},
|
1002 |
+
{
|
1003 |
+
"epoch": 3.1,
|
1004 |
+
"learning_rate": 7.11018711018711e-05,
|
1005 |
+
"loss": 0.862,
|
1006 |
+
"step": 1570
|
1007 |
+
},
|
1008 |
+
{
|
1009 |
+
"epoch": 3.12,
|
1010 |
+
"learning_rate": 6.954261954261954e-05,
|
1011 |
+
"loss": 0.8618,
|
1012 |
+
"step": 1580
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"epoch": 3.14,
|
1016 |
+
"learning_rate": 6.798336798336798e-05,
|
1017 |
+
"loss": 0.8478,
|
1018 |
+
"step": 1590
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 3.16,
|
1022 |
+
"learning_rate": 6.642411642411643e-05,
|
1023 |
+
"loss": 0.8467,
|
1024 |
+
"step": 1600
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 3.16,
|
1028 |
+
"eval_loss": 0.9100631475448608,
|
1029 |
+
"eval_runtime": 44.1701,
|
1030 |
+
"eval_samples_per_second": 45.279,
|
1031 |
+
"eval_steps_per_second": 0.724,
|
1032 |
+
"step": 1600
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 3.18,
|
1036 |
+
"learning_rate": 6.486486486486486e-05,
|
1037 |
+
"loss": 0.8471,
|
1038 |
+
"step": 1610
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 3.2,
|
1042 |
+
"learning_rate": 6.33056133056133e-05,
|
1043 |
+
"loss": 0.8511,
|
1044 |
+
"step": 1620
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 3.22,
|
1048 |
+
"learning_rate": 6.174636174636175e-05,
|
1049 |
+
"loss": 0.8517,
|
1050 |
+
"step": 1630
|
1051 |
+
},
|
1052 |
+
{
|
1053 |
+
"epoch": 3.24,
|
1054 |
+
"learning_rate": 6.018711018711019e-05,
|
1055 |
+
"loss": 0.8537,
|
1056 |
+
"step": 1640
|
1057 |
+
},
|
1058 |
+
{
|
1059 |
+
"epoch": 3.26,
|
1060 |
+
"learning_rate": 5.8627858627858625e-05,
|
1061 |
+
"loss": 0.8479,
|
1062 |
+
"step": 1650
|
1063 |
+
},
|
1064 |
+
{
|
1065 |
+
"epoch": 3.28,
|
1066 |
+
"learning_rate": 5.7068607068607063e-05,
|
1067 |
+
"loss": 0.8473,
|
1068 |
+
"step": 1660
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 3.3,
|
1072 |
+
"learning_rate": 5.550935550935551e-05,
|
1073 |
+
"loss": 0.8394,
|
1074 |
+
"step": 1670
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 3.32,
|
1078 |
+
"learning_rate": 5.395010395010395e-05,
|
1079 |
+
"loss": 0.8528,
|
1080 |
+
"step": 1680
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 3.34,
|
1084 |
+
"learning_rate": 5.239085239085239e-05,
|
1085 |
+
"loss": 0.8356,
|
1086 |
+
"step": 1690
|
1087 |
+
},
|
1088 |
+
{
|
1089 |
+
"epoch": 3.36,
|
1090 |
+
"learning_rate": 5.083160083160083e-05,
|
1091 |
+
"loss": 0.8543,
|
1092 |
+
"step": 1700
|
1093 |
+
},
|
1094 |
+
{
|
1095 |
+
"epoch": 3.38,
|
1096 |
+
"learning_rate": 4.927234927234927e-05,
|
1097 |
+
"loss": 0.8332,
|
1098 |
+
"step": 1710
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 3.4,
|
1102 |
+
"learning_rate": 4.771309771309771e-05,
|
1103 |
+
"loss": 0.8511,
|
1104 |
+
"step": 1720
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 3.42,
|
1108 |
+
"learning_rate": 4.615384615384615e-05,
|
1109 |
+
"loss": 0.8542,
|
1110 |
+
"step": 1730
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 3.44,
|
1114 |
+
"learning_rate": 4.4594594594594596e-05,
|
1115 |
+
"loss": 0.8238,
|
1116 |
+
"step": 1740
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 3.46,
|
1120 |
+
"learning_rate": 4.3035343035343035e-05,
|
1121 |
+
"loss": 0.8424,
|
1122 |
+
"step": 1750
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 3.47,
|
1126 |
+
"learning_rate": 4.147609147609147e-05,
|
1127 |
+
"loss": 0.8455,
|
1128 |
+
"step": 1760
|
1129 |
+
},
|
1130 |
+
{
|
1131 |
+
"epoch": 3.49,
|
1132 |
+
"learning_rate": 3.991683991683992e-05,
|
1133 |
+
"loss": 0.8554,
|
1134 |
+
"step": 1770
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 3.51,
|
1138 |
+
"learning_rate": 3.8357588357588356e-05,
|
1139 |
+
"loss": 0.8491,
|
1140 |
+
"step": 1780
|
1141 |
+
},
|
1142 |
+
{
|
1143 |
+
"epoch": 3.53,
|
1144 |
+
"learning_rate": 3.6798336798336794e-05,
|
1145 |
+
"loss": 0.8506,
|
1146 |
+
"step": 1790
|
1147 |
+
},
|
1148 |
+
{
|
1149 |
+
"epoch": 3.55,
|
1150 |
+
"learning_rate": 3.523908523908524e-05,
|
1151 |
+
"loss": 0.8357,
|
1152 |
+
"step": 1800
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 3.55,
|
1156 |
+
"eval_loss": 0.9110742211341858,
|
1157 |
+
"eval_runtime": 44.3239,
|
1158 |
+
"eval_samples_per_second": 45.122,
|
1159 |
+
"eval_steps_per_second": 0.722,
|
1160 |
+
"step": 1800
|
1161 |
+
}
|
1162 |
+
],
|
1163 |
+
"max_steps": 2024,
|
1164 |
+
"num_train_epochs": 4,
|
1165 |
+
"total_flos": 7.272260203502895e+18,
|
1166 |
+
"trial_name": null,
|
1167 |
+
"trial_params": null
|
1168 |
+
}
|
checkpoint-1800/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:421eeaebb0bf48e1dc571c1d5708e71cf221377fdbb08f85d14f26308c08f2d3
|
3 |
+
size 3579
|
checkpoint-2000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e151316644d9244d900dbc5c6da0be77ccc431e20ab9e6baf71611855092d95
|
3 |
+
size 209984517
|
checkpoint-2000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ae3ffe322e77ab38cf0c1a9d79335be67d61a5ca2b55acb2b722381573ec137
|
3 |
+
size 104973389
|
checkpoint-2000/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07b20c1297647cb36030d9ac8539c2dfa658474971bf62dea48ee2eb5fd63dae
|
3 |
+
size 14583
|
checkpoint-2000/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34648eb2b8fce18a363d97d67066c346c46ea19f008a300636e8b5ce2cefe279
|
3 |
+
size 14583
|
checkpoint-2000/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e51d589270c4b3907496f5333a74f7775787b255ff44a41fc6f70331c2722f0
|
3 |
+
size 14583
|
checkpoint-2000/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:001fb35263ab6b198b05ab5197ee994e000ed7e3705a72f1366abeeba7c6bd57
|
3 |
+
size 14583
|
checkpoint-2000/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40818d4baed5e8725fd91c9d290e15a9c200c9152fe136b516c73598bd25febb
|
3 |
+
size 14583
|
checkpoint-2000/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a14b4f44e56c3c69dd42d7c0a71bf853801c6b132471d01e5875a6fc45dca11
|
3 |
+
size 14583
|
checkpoint-2000/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c5988a087c1e32b8bdfc384b79a89cddcdd3bf794cb000cd2f99b652ad4d0a4
|
3 |
+
size 14583
|
checkpoint-2000/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b121fcb71c5b113de494fe1924a39ef03c4cb0d94ab0e9a113994ef05eeb01f7
|
3 |
+
size 14583
|
checkpoint-2000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b52c3e387341445c8ba39921ab29ef6b3666f5695d208629ac56d41f19e06def
|
3 |
+
size 557
|
checkpoint-2000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e645d9c1d7d035989711d0a7b1dddd0781a4c8a91756299fe70e63a321b483ba
|
3 |
+
size 627
|
checkpoint-2000/trainer_state.json
ADDED
@@ -0,0 +1,1296 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9100631475448608,
|
3 |
+
"best_model_checkpoint": "./lora-alpaca/checkpoint-1600",
|
4 |
+
"epoch": 3.9486673247778876,
|
5 |
+
"global_step": 2000,
|
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": 2.3999999999999997e-05,
|
13 |
+
"loss": 1.5473,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.04,
|
18 |
+
"learning_rate": 5.399999999999999e-05,
|
19 |
+
"loss": 1.5181,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.06,
|
24 |
+
"learning_rate": 8.4e-05,
|
25 |
+
"loss": 1.3749,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.08,
|
30 |
+
"learning_rate": 0.00011399999999999999,
|
31 |
+
"loss": 1.1669,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.1,
|
36 |
+
"learning_rate": 0.00014399999999999998,
|
37 |
+
"loss": 1.0525,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.12,
|
42 |
+
"learning_rate": 0.00017399999999999997,
|
43 |
+
"loss": 1.0376,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.14,
|
48 |
+
"learning_rate": 0.000204,
|
49 |
+
"loss": 1.0043,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.16,
|
54 |
+
"learning_rate": 0.000234,
|
55 |
+
"loss": 0.9849,
|
56 |
+
"step": 80
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.18,
|
60 |
+
"learning_rate": 0.00026399999999999997,
|
61 |
+
"loss": 0.9821,
|
62 |
+
"step": 90
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.2,
|
66 |
+
"learning_rate": 0.000294,
|
67 |
+
"loss": 0.9846,
|
68 |
+
"step": 100
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.22,
|
72 |
+
"learning_rate": 0.0002987525987525987,
|
73 |
+
"loss": 0.9635,
|
74 |
+
"step": 110
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.24,
|
78 |
+
"learning_rate": 0.00029719334719334716,
|
79 |
+
"loss": 0.9538,
|
80 |
+
"step": 120
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.26,
|
84 |
+
"learning_rate": 0.0002956340956340956,
|
85 |
+
"loss": 0.9408,
|
86 |
+
"step": 130
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.28,
|
90 |
+
"learning_rate": 0.00029407484407484405,
|
91 |
+
"loss": 0.9529,
|
92 |
+
"step": 140
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.3,
|
96 |
+
"learning_rate": 0.0002925155925155925,
|
97 |
+
"loss": 0.9622,
|
98 |
+
"step": 150
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.32,
|
102 |
+
"learning_rate": 0.00029095634095634094,
|
103 |
+
"loss": 0.9517,
|
104 |
+
"step": 160
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.34,
|
108 |
+
"learning_rate": 0.0002893970893970894,
|
109 |
+
"loss": 0.9624,
|
110 |
+
"step": 170
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.36,
|
114 |
+
"learning_rate": 0.0002878378378378378,
|
115 |
+
"loss": 0.9445,
|
116 |
+
"step": 180
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.38,
|
120 |
+
"learning_rate": 0.0002862785862785863,
|
121 |
+
"loss": 0.9428,
|
122 |
+
"step": 190
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.39,
|
126 |
+
"learning_rate": 0.0002847193347193347,
|
127 |
+
"loss": 0.9372,
|
128 |
+
"step": 200
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.39,
|
132 |
+
"eval_loss": 0.9433729648590088,
|
133 |
+
"eval_runtime": 44.3089,
|
134 |
+
"eval_samples_per_second": 45.138,
|
135 |
+
"eval_steps_per_second": 0.722,
|
136 |
+
"step": 200
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.41,
|
140 |
+
"learning_rate": 0.00028316008316008317,
|
141 |
+
"loss": 0.9388,
|
142 |
+
"step": 210
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.43,
|
146 |
+
"learning_rate": 0.00028160083160083156,
|
147 |
+
"loss": 0.9412,
|
148 |
+
"step": 220
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 0.45,
|
152 |
+
"learning_rate": 0.00028004158004158,
|
153 |
+
"loss": 0.9365,
|
154 |
+
"step": 230
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 0.47,
|
158 |
+
"learning_rate": 0.00027848232848232845,
|
159 |
+
"loss": 0.9382,
|
160 |
+
"step": 240
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 0.49,
|
164 |
+
"learning_rate": 0.0002769230769230769,
|
165 |
+
"loss": 0.9309,
|
166 |
+
"step": 250
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 0.51,
|
170 |
+
"learning_rate": 0.00027536382536382534,
|
171 |
+
"loss": 0.9256,
|
172 |
+
"step": 260
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.53,
|
176 |
+
"learning_rate": 0.0002738045738045738,
|
177 |
+
"loss": 0.9245,
|
178 |
+
"step": 270
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.55,
|
182 |
+
"learning_rate": 0.00027224532224532223,
|
183 |
+
"loss": 0.9329,
|
184 |
+
"step": 280
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.57,
|
188 |
+
"learning_rate": 0.0002706860706860707,
|
189 |
+
"loss": 0.9405,
|
190 |
+
"step": 290
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 0.59,
|
194 |
+
"learning_rate": 0.0002691268191268191,
|
195 |
+
"loss": 0.9168,
|
196 |
+
"step": 300
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 0.61,
|
200 |
+
"learning_rate": 0.00026756756756756756,
|
201 |
+
"loss": 0.92,
|
202 |
+
"step": 310
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 0.63,
|
206 |
+
"learning_rate": 0.000266008316008316,
|
207 |
+
"loss": 0.9098,
|
208 |
+
"step": 320
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 0.65,
|
212 |
+
"learning_rate": 0.00026444906444906445,
|
213 |
+
"loss": 0.9275,
|
214 |
+
"step": 330
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.67,
|
218 |
+
"learning_rate": 0.00026288981288981285,
|
219 |
+
"loss": 0.9215,
|
220 |
+
"step": 340
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.69,
|
224 |
+
"learning_rate": 0.0002613305613305613,
|
225 |
+
"loss": 0.9237,
|
226 |
+
"step": 350
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.71,
|
230 |
+
"learning_rate": 0.00025977130977130974,
|
231 |
+
"loss": 0.9237,
|
232 |
+
"step": 360
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 0.73,
|
236 |
+
"learning_rate": 0.0002582120582120582,
|
237 |
+
"loss": 0.928,
|
238 |
+
"step": 370
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 0.75,
|
242 |
+
"learning_rate": 0.0002566528066528066,
|
243 |
+
"loss": 0.9156,
|
244 |
+
"step": 380
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 0.77,
|
248 |
+
"learning_rate": 0.00025509355509355507,
|
249 |
+
"loss": 0.9255,
|
250 |
+
"step": 390
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 0.79,
|
254 |
+
"learning_rate": 0.0002535343035343035,
|
255 |
+
"loss": 0.9102,
|
256 |
+
"step": 400
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.79,
|
260 |
+
"eval_loss": 0.9269554615020752,
|
261 |
+
"eval_runtime": 44.228,
|
262 |
+
"eval_samples_per_second": 45.22,
|
263 |
+
"eval_steps_per_second": 0.724,
|
264 |
+
"step": 400
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.81,
|
268 |
+
"learning_rate": 0.00025197505197505196,
|
269 |
+
"loss": 0.9312,
|
270 |
+
"step": 410
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.83,
|
274 |
+
"learning_rate": 0.0002504158004158004,
|
275 |
+
"loss": 0.9249,
|
276 |
+
"step": 420
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.85,
|
280 |
+
"learning_rate": 0.00024885654885654885,
|
281 |
+
"loss": 0.9151,
|
282 |
+
"step": 430
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.87,
|
286 |
+
"learning_rate": 0.0002472972972972973,
|
287 |
+
"loss": 0.9265,
|
288 |
+
"step": 440
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 0.89,
|
292 |
+
"learning_rate": 0.00024573804573804574,
|
293 |
+
"loss": 0.9064,
|
294 |
+
"step": 450
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.91,
|
298 |
+
"learning_rate": 0.00024417879417879413,
|
299 |
+
"loss": 0.9185,
|
300 |
+
"step": 460
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 0.93,
|
304 |
+
"learning_rate": 0.0002426195426195426,
|
305 |
+
"loss": 0.9128,
|
306 |
+
"step": 470
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 0.95,
|
310 |
+
"learning_rate": 0.00024106029106029105,
|
311 |
+
"loss": 0.9159,
|
312 |
+
"step": 480
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.97,
|
316 |
+
"learning_rate": 0.0002395010395010395,
|
317 |
+
"loss": 0.8987,
|
318 |
+
"step": 490
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.99,
|
322 |
+
"learning_rate": 0.0002379417879417879,
|
323 |
+
"loss": 0.9217,
|
324 |
+
"step": 500
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 1.01,
|
328 |
+
"learning_rate": 0.00023638253638253636,
|
329 |
+
"loss": 0.906,
|
330 |
+
"step": 510
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 1.03,
|
334 |
+
"learning_rate": 0.0002348232848232848,
|
335 |
+
"loss": 0.9066,
|
336 |
+
"step": 520
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 1.05,
|
340 |
+
"learning_rate": 0.00023326403326403325,
|
341 |
+
"loss": 0.9085,
|
342 |
+
"step": 530
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 1.07,
|
346 |
+
"learning_rate": 0.00023170478170478166,
|
347 |
+
"loss": 0.9203,
|
348 |
+
"step": 540
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 1.09,
|
352 |
+
"learning_rate": 0.0002301455301455301,
|
353 |
+
"loss": 0.9003,
|
354 |
+
"step": 550
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 1.11,
|
358 |
+
"learning_rate": 0.00022858627858627858,
|
359 |
+
"loss": 0.9071,
|
360 |
+
"step": 560
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 1.13,
|
364 |
+
"learning_rate": 0.00022702702702702703,
|
365 |
+
"loss": 0.9026,
|
366 |
+
"step": 570
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 1.15,
|
370 |
+
"learning_rate": 0.00022546777546777544,
|
371 |
+
"loss": 0.8845,
|
372 |
+
"step": 580
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 1.16,
|
376 |
+
"learning_rate": 0.0002239085239085239,
|
377 |
+
"loss": 0.9023,
|
378 |
+
"step": 590
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 1.18,
|
382 |
+
"learning_rate": 0.00022234927234927233,
|
383 |
+
"loss": 0.9169,
|
384 |
+
"step": 600
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 1.18,
|
388 |
+
"eval_loss": 0.9196034073829651,
|
389 |
+
"eval_runtime": 44.3139,
|
390 |
+
"eval_samples_per_second": 45.133,
|
391 |
+
"eval_steps_per_second": 0.722,
|
392 |
+
"step": 600
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 1.2,
|
396 |
+
"learning_rate": 0.00022079002079002078,
|
397 |
+
"loss": 0.9015,
|
398 |
+
"step": 610
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 1.22,
|
402 |
+
"learning_rate": 0.0002192307692307692,
|
403 |
+
"loss": 0.9066,
|
404 |
+
"step": 620
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 1.24,
|
408 |
+
"learning_rate": 0.00021767151767151764,
|
409 |
+
"loss": 0.8981,
|
410 |
+
"step": 630
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 1.26,
|
414 |
+
"learning_rate": 0.0002161122661122661,
|
415 |
+
"loss": 0.9023,
|
416 |
+
"step": 640
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.28,
|
420 |
+
"learning_rate": 0.00021455301455301456,
|
421 |
+
"loss": 0.9077,
|
422 |
+
"step": 650
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.3,
|
426 |
+
"learning_rate": 0.00021299376299376295,
|
427 |
+
"loss": 0.9055,
|
428 |
+
"step": 660
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 1.32,
|
432 |
+
"learning_rate": 0.00021143451143451142,
|
433 |
+
"loss": 0.9028,
|
434 |
+
"step": 670
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 1.34,
|
438 |
+
"learning_rate": 0.00020987525987525987,
|
439 |
+
"loss": 0.8874,
|
440 |
+
"step": 680
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 1.36,
|
444 |
+
"learning_rate": 0.0002083160083160083,
|
445 |
+
"loss": 0.8844,
|
446 |
+
"step": 690
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 1.38,
|
450 |
+
"learning_rate": 0.00020675675675675673,
|
451 |
+
"loss": 0.8996,
|
452 |
+
"step": 700
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 1.4,
|
456 |
+
"learning_rate": 0.00020519750519750517,
|
457 |
+
"loss": 0.9085,
|
458 |
+
"step": 710
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.42,
|
462 |
+
"learning_rate": 0.00020363825363825362,
|
463 |
+
"loss": 0.9024,
|
464 |
+
"step": 720
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 1.44,
|
468 |
+
"learning_rate": 0.00020207900207900206,
|
469 |
+
"loss": 0.899,
|
470 |
+
"step": 730
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 1.46,
|
474 |
+
"learning_rate": 0.00020051975051975048,
|
475 |
+
"loss": 0.8926,
|
476 |
+
"step": 740
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 1.48,
|
480 |
+
"learning_rate": 0.00019896049896049893,
|
481 |
+
"loss": 0.89,
|
482 |
+
"step": 750
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 1.5,
|
486 |
+
"learning_rate": 0.0001974012474012474,
|
487 |
+
"loss": 0.8858,
|
488 |
+
"step": 760
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 1.52,
|
492 |
+
"learning_rate": 0.00019584199584199584,
|
493 |
+
"loss": 0.8972,
|
494 |
+
"step": 770
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 1.54,
|
498 |
+
"learning_rate": 0.00019428274428274426,
|
499 |
+
"loss": 0.9003,
|
500 |
+
"step": 780
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 1.56,
|
504 |
+
"learning_rate": 0.0001927234927234927,
|
505 |
+
"loss": 0.8991,
|
506 |
+
"step": 790
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 1.58,
|
510 |
+
"learning_rate": 0.00019116424116424115,
|
511 |
+
"loss": 0.8912,
|
512 |
+
"step": 800
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 1.58,
|
516 |
+
"eval_loss": 0.914772093296051,
|
517 |
+
"eval_runtime": 44.1817,
|
518 |
+
"eval_samples_per_second": 45.268,
|
519 |
+
"eval_steps_per_second": 0.724,
|
520 |
+
"step": 800
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 1.6,
|
524 |
+
"learning_rate": 0.0001896049896049896,
|
525 |
+
"loss": 0.8859,
|
526 |
+
"step": 810
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 1.62,
|
530 |
+
"learning_rate": 0.00018804573804573802,
|
531 |
+
"loss": 0.8942,
|
532 |
+
"step": 820
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 1.64,
|
536 |
+
"learning_rate": 0.00018648648648648646,
|
537 |
+
"loss": 0.8953,
|
538 |
+
"step": 830
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 1.66,
|
542 |
+
"learning_rate": 0.0001849272349272349,
|
543 |
+
"loss": 0.8845,
|
544 |
+
"step": 840
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 1.68,
|
548 |
+
"learning_rate": 0.00018336798336798335,
|
549 |
+
"loss": 0.8871,
|
550 |
+
"step": 850
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 1.7,
|
554 |
+
"learning_rate": 0.00018180873180873177,
|
555 |
+
"loss": 0.8849,
|
556 |
+
"step": 860
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 1.72,
|
560 |
+
"learning_rate": 0.0001802494802494802,
|
561 |
+
"loss": 0.8672,
|
562 |
+
"step": 870
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 1.74,
|
566 |
+
"learning_rate": 0.00017869022869022869,
|
567 |
+
"loss": 0.8811,
|
568 |
+
"step": 880
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 1.76,
|
572 |
+
"learning_rate": 0.00017713097713097713,
|
573 |
+
"loss": 0.8911,
|
574 |
+
"step": 890
|
575 |
+
},
|
576 |
+
{
|
577 |
+
"epoch": 1.78,
|
578 |
+
"learning_rate": 0.00017557172557172555,
|
579 |
+
"loss": 0.8814,
|
580 |
+
"step": 900
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 1.8,
|
584 |
+
"learning_rate": 0.000174012474012474,
|
585 |
+
"loss": 0.8819,
|
586 |
+
"step": 910
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 1.82,
|
590 |
+
"learning_rate": 0.00017245322245322244,
|
591 |
+
"loss": 0.8835,
|
592 |
+
"step": 920
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 1.84,
|
596 |
+
"learning_rate": 0.00017089397089397088,
|
597 |
+
"loss": 0.8768,
|
598 |
+
"step": 930
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 1.86,
|
602 |
+
"learning_rate": 0.0001693347193347193,
|
603 |
+
"loss": 0.8829,
|
604 |
+
"step": 940
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 1.88,
|
608 |
+
"learning_rate": 0.00016777546777546775,
|
609 |
+
"loss": 0.8898,
|
610 |
+
"step": 950
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 1.9,
|
614 |
+
"learning_rate": 0.0001662162162162162,
|
615 |
+
"loss": 0.8884,
|
616 |
+
"step": 960
|
617 |
+
},
|
618 |
+
{
|
619 |
+
"epoch": 1.92,
|
620 |
+
"learning_rate": 0.00016465696465696466,
|
621 |
+
"loss": 0.87,
|
622 |
+
"step": 970
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 1.93,
|
626 |
+
"learning_rate": 0.00016309771309771305,
|
627 |
+
"loss": 0.8851,
|
628 |
+
"step": 980
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 1.95,
|
632 |
+
"learning_rate": 0.00016153846153846153,
|
633 |
+
"loss": 0.8807,
|
634 |
+
"step": 990
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 1.97,
|
638 |
+
"learning_rate": 0.00015997920997920997,
|
639 |
+
"loss": 0.8923,
|
640 |
+
"step": 1000
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 1.97,
|
644 |
+
"eval_loss": 0.9123471975326538,
|
645 |
+
"eval_runtime": 44.1751,
|
646 |
+
"eval_samples_per_second": 45.274,
|
647 |
+
"eval_steps_per_second": 0.724,
|
648 |
+
"step": 1000
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 1.99,
|
652 |
+
"learning_rate": 0.00015841995841995842,
|
653 |
+
"loss": 0.8825,
|
654 |
+
"step": 1010
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 2.01,
|
658 |
+
"learning_rate": 0.00015686070686070683,
|
659 |
+
"loss": 0.878,
|
660 |
+
"step": 1020
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 2.03,
|
664 |
+
"learning_rate": 0.00015530145530145528,
|
665 |
+
"loss": 0.861,
|
666 |
+
"step": 1030
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 2.05,
|
670 |
+
"learning_rate": 0.00015374220374220372,
|
671 |
+
"loss": 0.8652,
|
672 |
+
"step": 1040
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 2.07,
|
676 |
+
"learning_rate": 0.00015218295218295217,
|
677 |
+
"loss": 0.8589,
|
678 |
+
"step": 1050
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 2.09,
|
682 |
+
"learning_rate": 0.0001506237006237006,
|
683 |
+
"loss": 0.8688,
|
684 |
+
"step": 1060
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 2.11,
|
688 |
+
"learning_rate": 0.00014906444906444906,
|
689 |
+
"loss": 0.8796,
|
690 |
+
"step": 1070
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 2.13,
|
694 |
+
"learning_rate": 0.0001475051975051975,
|
695 |
+
"loss": 0.8719,
|
696 |
+
"step": 1080
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 2.15,
|
700 |
+
"learning_rate": 0.00014594594594594595,
|
701 |
+
"loss": 0.8798,
|
702 |
+
"step": 1090
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 2.17,
|
706 |
+
"learning_rate": 0.00014438669438669437,
|
707 |
+
"loss": 0.8669,
|
708 |
+
"step": 1100
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 2.19,
|
712 |
+
"learning_rate": 0.0001428274428274428,
|
713 |
+
"loss": 0.8661,
|
714 |
+
"step": 1110
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 2.21,
|
718 |
+
"learning_rate": 0.00014126819126819126,
|
719 |
+
"loss": 0.8684,
|
720 |
+
"step": 1120
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 2.23,
|
724 |
+
"learning_rate": 0.0001397089397089397,
|
725 |
+
"loss": 0.8591,
|
726 |
+
"step": 1130
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 2.25,
|
730 |
+
"learning_rate": 0.00013814968814968815,
|
731 |
+
"loss": 0.8659,
|
732 |
+
"step": 1140
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 2.27,
|
736 |
+
"learning_rate": 0.0001365904365904366,
|
737 |
+
"loss": 0.868,
|
738 |
+
"step": 1150
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 2.29,
|
742 |
+
"learning_rate": 0.000135031185031185,
|
743 |
+
"loss": 0.871,
|
744 |
+
"step": 1160
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 2.31,
|
748 |
+
"learning_rate": 0.00013347193347193346,
|
749 |
+
"loss": 0.8639,
|
750 |
+
"step": 1170
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 2.33,
|
754 |
+
"learning_rate": 0.0001319126819126819,
|
755 |
+
"loss": 0.8603,
|
756 |
+
"step": 1180
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 2.35,
|
760 |
+
"learning_rate": 0.00013035343035343035,
|
761 |
+
"loss": 0.8617,
|
762 |
+
"step": 1190
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 2.37,
|
766 |
+
"learning_rate": 0.0001287941787941788,
|
767 |
+
"loss": 0.8548,
|
768 |
+
"step": 1200
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 2.37,
|
772 |
+
"eval_loss": 0.9124282002449036,
|
773 |
+
"eval_runtime": 44.2512,
|
774 |
+
"eval_samples_per_second": 45.197,
|
775 |
+
"eval_steps_per_second": 0.723,
|
776 |
+
"step": 1200
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 2.39,
|
780 |
+
"learning_rate": 0.00012723492723492724,
|
781 |
+
"loss": 0.8694,
|
782 |
+
"step": 1210
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 2.41,
|
786 |
+
"learning_rate": 0.00012567567567567565,
|
787 |
+
"loss": 0.8651,
|
788 |
+
"step": 1220
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 2.43,
|
792 |
+
"learning_rate": 0.00012411642411642413,
|
793 |
+
"loss": 0.8606,
|
794 |
+
"step": 1230
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 2.45,
|
798 |
+
"learning_rate": 0.00012255717255717254,
|
799 |
+
"loss": 0.8678,
|
800 |
+
"step": 1240
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 2.47,
|
804 |
+
"learning_rate": 0.00012099792099792099,
|
805 |
+
"loss": 0.8676,
|
806 |
+
"step": 1250
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 2.49,
|
810 |
+
"learning_rate": 0.00011943866943866943,
|
811 |
+
"loss": 0.8602,
|
812 |
+
"step": 1260
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 2.51,
|
816 |
+
"learning_rate": 0.00011787941787941788,
|
817 |
+
"loss": 0.8718,
|
818 |
+
"step": 1270
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 2.53,
|
822 |
+
"learning_rate": 0.00011632016632016631,
|
823 |
+
"loss": 0.8618,
|
824 |
+
"step": 1280
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 2.55,
|
828 |
+
"learning_rate": 0.00011476091476091475,
|
829 |
+
"loss": 0.8677,
|
830 |
+
"step": 1290
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 2.57,
|
834 |
+
"learning_rate": 0.00011320166320166319,
|
835 |
+
"loss": 0.844,
|
836 |
+
"step": 1300
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 2.59,
|
840 |
+
"learning_rate": 0.00011164241164241164,
|
841 |
+
"loss": 0.8653,
|
842 |
+
"step": 1310
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 2.61,
|
846 |
+
"learning_rate": 0.00011008316008316008,
|
847 |
+
"loss": 0.8639,
|
848 |
+
"step": 1320
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 2.63,
|
852 |
+
"learning_rate": 0.00010852390852390852,
|
853 |
+
"loss": 0.873,
|
854 |
+
"step": 1330
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 2.65,
|
858 |
+
"learning_rate": 0.00010696465696465695,
|
859 |
+
"loss": 0.8639,
|
860 |
+
"step": 1340
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 2.67,
|
864 |
+
"learning_rate": 0.0001054054054054054,
|
865 |
+
"loss": 0.8545,
|
866 |
+
"step": 1350
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 2.69,
|
870 |
+
"learning_rate": 0.00010384615384615383,
|
871 |
+
"loss": 0.8654,
|
872 |
+
"step": 1360
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 2.7,
|
876 |
+
"learning_rate": 0.00010228690228690229,
|
877 |
+
"loss": 0.8555,
|
878 |
+
"step": 1370
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 2.72,
|
882 |
+
"learning_rate": 0.00010072765072765072,
|
883 |
+
"loss": 0.8707,
|
884 |
+
"step": 1380
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 2.74,
|
888 |
+
"learning_rate": 9.916839916839916e-05,
|
889 |
+
"loss": 0.8452,
|
890 |
+
"step": 1390
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 2.76,
|
894 |
+
"learning_rate": 9.76091476091476e-05,
|
895 |
+
"loss": 0.8512,
|
896 |
+
"step": 1400
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 2.76,
|
900 |
+
"eval_loss": 0.9109137058258057,
|
901 |
+
"eval_runtime": 44.368,
|
902 |
+
"eval_samples_per_second": 45.077,
|
903 |
+
"eval_steps_per_second": 0.721,
|
904 |
+
"step": 1400
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 2.78,
|
908 |
+
"learning_rate": 9.604989604989604e-05,
|
909 |
+
"loss": 0.8485,
|
910 |
+
"step": 1410
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"epoch": 2.8,
|
914 |
+
"learning_rate": 9.449064449064449e-05,
|
915 |
+
"loss": 0.8635,
|
916 |
+
"step": 1420
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 2.82,
|
920 |
+
"learning_rate": 9.293139293139293e-05,
|
921 |
+
"loss": 0.8499,
|
922 |
+
"step": 1430
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 2.84,
|
926 |
+
"learning_rate": 9.137214137214136e-05,
|
927 |
+
"loss": 0.855,
|
928 |
+
"step": 1440
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 2.86,
|
932 |
+
"learning_rate": 8.98128898128898e-05,
|
933 |
+
"loss": 0.8437,
|
934 |
+
"step": 1450
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 2.88,
|
938 |
+
"learning_rate": 8.825363825363824e-05,
|
939 |
+
"loss": 0.8552,
|
940 |
+
"step": 1460
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 2.9,
|
944 |
+
"learning_rate": 8.66943866943867e-05,
|
945 |
+
"loss": 0.845,
|
946 |
+
"step": 1470
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 2.92,
|
950 |
+
"learning_rate": 8.513513513513513e-05,
|
951 |
+
"loss": 0.8591,
|
952 |
+
"step": 1480
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 2.94,
|
956 |
+
"learning_rate": 8.357588357588357e-05,
|
957 |
+
"loss": 0.8559,
|
958 |
+
"step": 1490
|
959 |
+
},
|
960 |
+
{
|
961 |
+
"epoch": 2.96,
|
962 |
+
"learning_rate": 8.2016632016632e-05,
|
963 |
+
"loss": 0.8562,
|
964 |
+
"step": 1500
|
965 |
+
},
|
966 |
+
{
|
967 |
+
"epoch": 2.98,
|
968 |
+
"learning_rate": 8.045738045738045e-05,
|
969 |
+
"loss": 0.8585,
|
970 |
+
"step": 1510
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 3.0,
|
974 |
+
"learning_rate": 7.889812889812888e-05,
|
975 |
+
"loss": 0.8627,
|
976 |
+
"step": 1520
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 3.02,
|
980 |
+
"learning_rate": 7.733887733887734e-05,
|
981 |
+
"loss": 0.849,
|
982 |
+
"step": 1530
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 3.04,
|
986 |
+
"learning_rate": 7.577962577962577e-05,
|
987 |
+
"loss": 0.8479,
|
988 |
+
"step": 1540
|
989 |
+
},
|
990 |
+
{
|
991 |
+
"epoch": 3.06,
|
992 |
+
"learning_rate": 7.422037422037422e-05,
|
993 |
+
"loss": 0.8522,
|
994 |
+
"step": 1550
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 3.08,
|
998 |
+
"learning_rate": 7.266112266112266e-05,
|
999 |
+
"loss": 0.8535,
|
1000 |
+
"step": 1560
|
1001 |
+
},
|
1002 |
+
{
|
1003 |
+
"epoch": 3.1,
|
1004 |
+
"learning_rate": 7.11018711018711e-05,
|
1005 |
+
"loss": 0.862,
|
1006 |
+
"step": 1570
|
1007 |
+
},
|
1008 |
+
{
|
1009 |
+
"epoch": 3.12,
|
1010 |
+
"learning_rate": 6.954261954261954e-05,
|
1011 |
+
"loss": 0.8618,
|
1012 |
+
"step": 1580
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"epoch": 3.14,
|
1016 |
+
"learning_rate": 6.798336798336798e-05,
|
1017 |
+
"loss": 0.8478,
|
1018 |
+
"step": 1590
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 3.16,
|
1022 |
+
"learning_rate": 6.642411642411643e-05,
|
1023 |
+
"loss": 0.8467,
|
1024 |
+
"step": 1600
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 3.16,
|
1028 |
+
"eval_loss": 0.9100631475448608,
|
1029 |
+
"eval_runtime": 44.1701,
|
1030 |
+
"eval_samples_per_second": 45.279,
|
1031 |
+
"eval_steps_per_second": 0.724,
|
1032 |
+
"step": 1600
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 3.18,
|
1036 |
+
"learning_rate": 6.486486486486486e-05,
|
1037 |
+
"loss": 0.8471,
|
1038 |
+
"step": 1610
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 3.2,
|
1042 |
+
"learning_rate": 6.33056133056133e-05,
|
1043 |
+
"loss": 0.8511,
|
1044 |
+
"step": 1620
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 3.22,
|
1048 |
+
"learning_rate": 6.174636174636175e-05,
|
1049 |
+
"loss": 0.8517,
|
1050 |
+
"step": 1630
|
1051 |
+
},
|
1052 |
+
{
|
1053 |
+
"epoch": 3.24,
|
1054 |
+
"learning_rate": 6.018711018711019e-05,
|
1055 |
+
"loss": 0.8537,
|
1056 |
+
"step": 1640
|
1057 |
+
},
|
1058 |
+
{
|
1059 |
+
"epoch": 3.26,
|
1060 |
+
"learning_rate": 5.8627858627858625e-05,
|
1061 |
+
"loss": 0.8479,
|
1062 |
+
"step": 1650
|
1063 |
+
},
|
1064 |
+
{
|
1065 |
+
"epoch": 3.28,
|
1066 |
+
"learning_rate": 5.7068607068607063e-05,
|
1067 |
+
"loss": 0.8473,
|
1068 |
+
"step": 1660
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 3.3,
|
1072 |
+
"learning_rate": 5.550935550935551e-05,
|
1073 |
+
"loss": 0.8394,
|
1074 |
+
"step": 1670
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 3.32,
|
1078 |
+
"learning_rate": 5.395010395010395e-05,
|
1079 |
+
"loss": 0.8528,
|
1080 |
+
"step": 1680
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 3.34,
|
1084 |
+
"learning_rate": 5.239085239085239e-05,
|
1085 |
+
"loss": 0.8356,
|
1086 |
+
"step": 1690
|
1087 |
+
},
|
1088 |
+
{
|
1089 |
+
"epoch": 3.36,
|
1090 |
+
"learning_rate": 5.083160083160083e-05,
|
1091 |
+
"loss": 0.8543,
|
1092 |
+
"step": 1700
|
1093 |
+
},
|
1094 |
+
{
|
1095 |
+
"epoch": 3.38,
|
1096 |
+
"learning_rate": 4.927234927234927e-05,
|
1097 |
+
"loss": 0.8332,
|
1098 |
+
"step": 1710
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 3.4,
|
1102 |
+
"learning_rate": 4.771309771309771e-05,
|
1103 |
+
"loss": 0.8511,
|
1104 |
+
"step": 1720
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 3.42,
|
1108 |
+
"learning_rate": 4.615384615384615e-05,
|
1109 |
+
"loss": 0.8542,
|
1110 |
+
"step": 1730
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 3.44,
|
1114 |
+
"learning_rate": 4.4594594594594596e-05,
|
1115 |
+
"loss": 0.8238,
|
1116 |
+
"step": 1740
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 3.46,
|
1120 |
+
"learning_rate": 4.3035343035343035e-05,
|
1121 |
+
"loss": 0.8424,
|
1122 |
+
"step": 1750
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 3.47,
|
1126 |
+
"learning_rate": 4.147609147609147e-05,
|
1127 |
+
"loss": 0.8455,
|
1128 |
+
"step": 1760
|
1129 |
+
},
|
1130 |
+
{
|
1131 |
+
"epoch": 3.49,
|
1132 |
+
"learning_rate": 3.991683991683992e-05,
|
1133 |
+
"loss": 0.8554,
|
1134 |
+
"step": 1770
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 3.51,
|
1138 |
+
"learning_rate": 3.8357588357588356e-05,
|
1139 |
+
"loss": 0.8491,
|
1140 |
+
"step": 1780
|
1141 |
+
},
|
1142 |
+
{
|
1143 |
+
"epoch": 3.53,
|
1144 |
+
"learning_rate": 3.6798336798336794e-05,
|
1145 |
+
"loss": 0.8506,
|
1146 |
+
"step": 1790
|
1147 |
+
},
|
1148 |
+
{
|
1149 |
+
"epoch": 3.55,
|
1150 |
+
"learning_rate": 3.523908523908524e-05,
|
1151 |
+
"loss": 0.8357,
|
1152 |
+
"step": 1800
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 3.55,
|
1156 |
+
"eval_loss": 0.9110742211341858,
|
1157 |
+
"eval_runtime": 44.3239,
|
1158 |
+
"eval_samples_per_second": 45.122,
|
1159 |
+
"eval_steps_per_second": 0.722,
|
1160 |
+
"step": 1800
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 3.57,
|
1164 |
+
"learning_rate": 3.367983367983368e-05,
|
1165 |
+
"loss": 0.8606,
|
1166 |
+
"step": 1810
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 3.59,
|
1170 |
+
"learning_rate": 3.212058212058212e-05,
|
1171 |
+
"loss": 0.8471,
|
1172 |
+
"step": 1820
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 3.61,
|
1176 |
+
"learning_rate": 3.056133056133056e-05,
|
1177 |
+
"loss": 0.8419,
|
1178 |
+
"step": 1830
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 3.63,
|
1182 |
+
"learning_rate": 2.9002079002079002e-05,
|
1183 |
+
"loss": 0.8328,
|
1184 |
+
"step": 1840
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 3.65,
|
1188 |
+
"learning_rate": 2.744282744282744e-05,
|
1189 |
+
"loss": 0.8442,
|
1190 |
+
"step": 1850
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 3.67,
|
1194 |
+
"learning_rate": 2.5883575883575882e-05,
|
1195 |
+
"loss": 0.835,
|
1196 |
+
"step": 1860
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 3.69,
|
1200 |
+
"learning_rate": 2.4324324324324324e-05,
|
1201 |
+
"loss": 0.8432,
|
1202 |
+
"step": 1870
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 3.71,
|
1206 |
+
"learning_rate": 2.2765072765072765e-05,
|
1207 |
+
"loss": 0.8378,
|
1208 |
+
"step": 1880
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 3.73,
|
1212 |
+
"learning_rate": 2.1205821205821204e-05,
|
1213 |
+
"loss": 0.8394,
|
1214 |
+
"step": 1890
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 3.75,
|
1218 |
+
"learning_rate": 1.9646569646569645e-05,
|
1219 |
+
"loss": 0.8364,
|
1220 |
+
"step": 1900
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 3.77,
|
1224 |
+
"learning_rate": 1.8087318087318087e-05,
|
1225 |
+
"loss": 0.849,
|
1226 |
+
"step": 1910
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 3.79,
|
1230 |
+
"learning_rate": 1.652806652806653e-05,
|
1231 |
+
"loss": 0.8542,
|
1232 |
+
"step": 1920
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 3.81,
|
1236 |
+
"learning_rate": 1.4968814968814968e-05,
|
1237 |
+
"loss": 0.8464,
|
1238 |
+
"step": 1930
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 3.83,
|
1242 |
+
"learning_rate": 1.340956340956341e-05,
|
1243 |
+
"loss": 0.837,
|
1244 |
+
"step": 1940
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 3.85,
|
1248 |
+
"learning_rate": 1.185031185031185e-05,
|
1249 |
+
"loss": 0.8385,
|
1250 |
+
"step": 1950
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 3.87,
|
1254 |
+
"learning_rate": 1.0291060291060291e-05,
|
1255 |
+
"loss": 0.8399,
|
1256 |
+
"step": 1960
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 3.89,
|
1260 |
+
"learning_rate": 8.731808731808731e-06,
|
1261 |
+
"loss": 0.839,
|
1262 |
+
"step": 1970
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 3.91,
|
1266 |
+
"learning_rate": 7.172557172557172e-06,
|
1267 |
+
"loss": 0.8424,
|
1268 |
+
"step": 1980
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 3.93,
|
1272 |
+
"learning_rate": 5.613305613305613e-06,
|
1273 |
+
"loss": 0.8398,
|
1274 |
+
"step": 1990
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 3.95,
|
1278 |
+
"learning_rate": 4.054054054054054e-06,
|
1279 |
+
"loss": 0.8435,
|
1280 |
+
"step": 2000
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 3.95,
|
1284 |
+
"eval_loss": 0.9102190732955933,
|
1285 |
+
"eval_runtime": 44.2725,
|
1286 |
+
"eval_samples_per_second": 45.175,
|
1287 |
+
"eval_steps_per_second": 0.723,
|
1288 |
+
"step": 2000
|
1289 |
+
}
|
1290 |
+
],
|
1291 |
+
"max_steps": 2024,
|
1292 |
+
"num_train_epochs": 4,
|
1293 |
+
"total_flos": 8.080540492757991e+18,
|
1294 |
+
"trial_name": null,
|
1295 |
+
"trial_params": null
|
1296 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:421eeaebb0bf48e1dc571c1d5708e71cf221377fdbb08f85d14f26308c08f2d3
|
3 |
+
size 3579
|