stevenjunliu
commited on
Commit
•
03ff627
1
Parent(s):
d387308
Model save
Browse files- README.md +66 -0
- all_results.json +8 -0
- generation_config.json +6 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +298 -0
- train_results.json +8 -0
- trainer_state.json +1571 -0
README.md
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: mistralai/Mistral-7B-v0.1
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- generator
|
10 |
+
model-index:
|
11 |
+
- name: zephyr-7b-sft-full
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# zephyr-7b-sft-full
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.9393
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 2e-05
|
42 |
+
- train_batch_size: 16
|
43 |
+
- eval_batch_size: 8
|
44 |
+
- seed: 42
|
45 |
+
- distributed_type: multi-GPU
|
46 |
+
- num_devices: 8
|
47 |
+
- total_train_batch_size: 128
|
48 |
+
- total_eval_batch_size: 64
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: cosine
|
51 |
+
- lr_scheduler_warmup_ratio: 0.1
|
52 |
+
- num_epochs: 1.0
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
58 |
+
| 0.9355 | 1.0 | 1090 | 0.9393 |
|
59 |
+
|
60 |
+
|
61 |
+
### Framework versions
|
62 |
+
|
63 |
+
- Transformers 4.39.0.dev0
|
64 |
+
- Pytorch 2.3.0+cu121
|
65 |
+
- Datasets 2.14.6
|
66 |
+
- Tokenizers 0.15.2
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.9795057065989993,
|
4 |
+
"train_runtime": 15753.4108,
|
5 |
+
"train_samples": 207864,
|
6 |
+
"train_samples_per_second": 8.85,
|
7 |
+
"train_steps_per_second": 0.069
|
8 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.39.0.dev0"
|
6 |
+
}
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02e7abb1f70ebee78adb05c3af4ad264d0b8df4ee1e5b238d450618723fa1afa
|
3 |
+
size 4943162336
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d08e0fa94fcb88585837521d2f9a8b0cb1bece89826e11485b4513c7366ccde7
|
3 |
+
size 4999819336
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:420037a0066d706f55699aea4934e015a680afd12975fc76f16c4b48b2105cb7
|
3 |
+
size 4540516344
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 14483464192
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
287 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
296 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
297 |
+
}
|
298 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.9795057065989993,
|
4 |
+
"train_runtime": 15753.4108,
|
5 |
+
"train_samples": 207864,
|
6 |
+
"train_samples_per_second": 8.85,
|
7 |
+
"train_steps_per_second": 0.069
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1571 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1090,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"grad_norm": 9.77339219775282,
|
14 |
+
"learning_rate": 1.8348623853211012e-07,
|
15 |
+
"loss": 1.1557,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0,
|
20 |
+
"grad_norm": 7.7326824203360625,
|
21 |
+
"learning_rate": 9.174311926605506e-07,
|
22 |
+
"loss": 1.1259,
|
23 |
+
"step": 5
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.01,
|
27 |
+
"grad_norm": 4.217943082141626,
|
28 |
+
"learning_rate": 1.8348623853211011e-06,
|
29 |
+
"loss": 1.0814,
|
30 |
+
"step": 10
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.01,
|
34 |
+
"grad_norm": 3.1553293441150627,
|
35 |
+
"learning_rate": 2.7522935779816517e-06,
|
36 |
+
"loss": 1.0173,
|
37 |
+
"step": 15
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.02,
|
41 |
+
"grad_norm": 2.624974536136745,
|
42 |
+
"learning_rate": 3.6697247706422022e-06,
|
43 |
+
"loss": 1.01,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.02,
|
48 |
+
"grad_norm": 1.9346693086685613,
|
49 |
+
"learning_rate": 4.587155963302753e-06,
|
50 |
+
"loss": 0.9699,
|
51 |
+
"step": 25
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.03,
|
55 |
+
"grad_norm": 2.0023694879238265,
|
56 |
+
"learning_rate": 5.504587155963303e-06,
|
57 |
+
"loss": 0.9871,
|
58 |
+
"step": 30
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.03,
|
62 |
+
"grad_norm": 1.9243231029659136,
|
63 |
+
"learning_rate": 6.422018348623854e-06,
|
64 |
+
"loss": 0.9731,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.04,
|
69 |
+
"grad_norm": 2.3079689233656158,
|
70 |
+
"learning_rate": 7.3394495412844045e-06,
|
71 |
+
"loss": 0.9786,
|
72 |
+
"step": 40
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.04,
|
76 |
+
"grad_norm": 1.9848142793089458,
|
77 |
+
"learning_rate": 8.256880733944956e-06,
|
78 |
+
"loss": 0.9683,
|
79 |
+
"step": 45
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.05,
|
83 |
+
"grad_norm": 2.1601847540175347,
|
84 |
+
"learning_rate": 9.174311926605506e-06,
|
85 |
+
"loss": 0.9655,
|
86 |
+
"step": 50
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.05,
|
90 |
+
"grad_norm": 1.995827350954353,
|
91 |
+
"learning_rate": 1.0091743119266055e-05,
|
92 |
+
"loss": 0.9763,
|
93 |
+
"step": 55
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.06,
|
97 |
+
"grad_norm": 1.8778202478820005,
|
98 |
+
"learning_rate": 1.1009174311926607e-05,
|
99 |
+
"loss": 0.9828,
|
100 |
+
"step": 60
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.06,
|
104 |
+
"grad_norm": 2.6097761971016706,
|
105 |
+
"learning_rate": 1.1926605504587156e-05,
|
106 |
+
"loss": 0.9917,
|
107 |
+
"step": 65
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.06,
|
111 |
+
"grad_norm": 1.9438707878045542,
|
112 |
+
"learning_rate": 1.2844036697247708e-05,
|
113 |
+
"loss": 0.9781,
|
114 |
+
"step": 70
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.07,
|
118 |
+
"grad_norm": 2.5283537508840412,
|
119 |
+
"learning_rate": 1.3761467889908258e-05,
|
120 |
+
"loss": 0.9766,
|
121 |
+
"step": 75
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.07,
|
125 |
+
"grad_norm": 2.4698926435303807,
|
126 |
+
"learning_rate": 1.4678899082568809e-05,
|
127 |
+
"loss": 0.9744,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.08,
|
132 |
+
"grad_norm": 1.7950947398875594,
|
133 |
+
"learning_rate": 1.559633027522936e-05,
|
134 |
+
"loss": 0.9925,
|
135 |
+
"step": 85
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.08,
|
139 |
+
"grad_norm": 1.849659361988556,
|
140 |
+
"learning_rate": 1.6513761467889912e-05,
|
141 |
+
"loss": 0.9951,
|
142 |
+
"step": 90
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.09,
|
146 |
+
"grad_norm": 2.091607616206256,
|
147 |
+
"learning_rate": 1.743119266055046e-05,
|
148 |
+
"loss": 1.0061,
|
149 |
+
"step": 95
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.09,
|
153 |
+
"grad_norm": 2.066221029636183,
|
154 |
+
"learning_rate": 1.834862385321101e-05,
|
155 |
+
"loss": 0.9985,
|
156 |
+
"step": 100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.1,
|
160 |
+
"grad_norm": 2.869454578032626,
|
161 |
+
"learning_rate": 1.9266055045871563e-05,
|
162 |
+
"loss": 0.9907,
|
163 |
+
"step": 105
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.1,
|
167 |
+
"grad_norm": 2.2432123776551944,
|
168 |
+
"learning_rate": 1.999994872196626e-05,
|
169 |
+
"loss": 1.0027,
|
170 |
+
"step": 110
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.11,
|
174 |
+
"grad_norm": 2.328668819896044,
|
175 |
+
"learning_rate": 1.9998154046002822e-05,
|
176 |
+
"loss": 0.9926,
|
177 |
+
"step": 115
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.11,
|
181 |
+
"grad_norm": 1.9876127666903096,
|
182 |
+
"learning_rate": 1.999379599421534e-05,
|
183 |
+
"loss": 1.0011,
|
184 |
+
"step": 120
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.11,
|
188 |
+
"grad_norm": 1.8724555785709804,
|
189 |
+
"learning_rate": 1.9986875683942535e-05,
|
190 |
+
"loss": 1.0242,
|
191 |
+
"step": 125
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.12,
|
195 |
+
"grad_norm": 2.1894981771490443,
|
196 |
+
"learning_rate": 1.9977394889447526e-05,
|
197 |
+
"loss": 1.0032,
|
198 |
+
"step": 130
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.12,
|
202 |
+
"grad_norm": 2.5051450231269605,
|
203 |
+
"learning_rate": 1.9965356041462954e-05,
|
204 |
+
"loss": 1.0154,
|
205 |
+
"step": 135
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.13,
|
209 |
+
"grad_norm": 2.01438038230488,
|
210 |
+
"learning_rate": 1.9950762226567783e-05,
|
211 |
+
"loss": 1.0023,
|
212 |
+
"step": 140
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.13,
|
216 |
+
"grad_norm": 1.974662211540992,
|
217 |
+
"learning_rate": 1.9933617186395917e-05,
|
218 |
+
"loss": 0.9996,
|
219 |
+
"step": 145
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.14,
|
223 |
+
"grad_norm": 1.7299662712917598,
|
224 |
+
"learning_rate": 1.9913925316676946e-05,
|
225 |
+
"loss": 1.0024,
|
226 |
+
"step": 150
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.14,
|
230 |
+
"grad_norm": 1.675351804082685,
|
231 |
+
"learning_rate": 1.9891691666109112e-05,
|
232 |
+
"loss": 0.9807,
|
233 |
+
"step": 155
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.15,
|
237 |
+
"grad_norm": 1.7568442047779815,
|
238 |
+
"learning_rate": 1.9866921935064907e-05,
|
239 |
+
"loss": 1.0026,
|
240 |
+
"step": 160
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.15,
|
244 |
+
"grad_norm": 1.8020826944560722,
|
245 |
+
"learning_rate": 1.9839622474129595e-05,
|
246 |
+
"loss": 0.9945,
|
247 |
+
"step": 165
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.16,
|
251 |
+
"grad_norm": 1.880978608228776,
|
252 |
+
"learning_rate": 1.9809800282473014e-05,
|
253 |
+
"loss": 1.0131,
|
254 |
+
"step": 170
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.16,
|
258 |
+
"grad_norm": 1.9533970099597644,
|
259 |
+
"learning_rate": 1.977746300605507e-05,
|
260 |
+
"loss": 1.0154,
|
261 |
+
"step": 175
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.17,
|
265 |
+
"grad_norm": 1.8000655097775127,
|
266 |
+
"learning_rate": 1.9742618935665478e-05,
|
267 |
+
"loss": 0.9994,
|
268 |
+
"step": 180
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.17,
|
272 |
+
"grad_norm": 1.6150313589958014,
|
273 |
+
"learning_rate": 1.9705277004798072e-05,
|
274 |
+
"loss": 1.0017,
|
275 |
+
"step": 185
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.17,
|
279 |
+
"grad_norm": 1.6236825548036045,
|
280 |
+
"learning_rate": 1.9665446787360444e-05,
|
281 |
+
"loss": 1.0084,
|
282 |
+
"step": 190
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.18,
|
286 |
+
"grad_norm": 1.681320814042372,
|
287 |
+
"learning_rate": 1.9623138495219292e-05,
|
288 |
+
"loss": 1.0185,
|
289 |
+
"step": 195
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.18,
|
293 |
+
"grad_norm": 1.909108842556375,
|
294 |
+
"learning_rate": 1.957836297558229e-05,
|
295 |
+
"loss": 1.0128,
|
296 |
+
"step": 200
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.19,
|
300 |
+
"grad_norm": 1.6634688766473966,
|
301 |
+
"learning_rate": 1.9531131708217005e-05,
|
302 |
+
"loss": 1.0145,
|
303 |
+
"step": 205
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.19,
|
307 |
+
"grad_norm": 1.556894984467879,
|
308 |
+
"learning_rate": 1.948145680250766e-05,
|
309 |
+
"loss": 0.9924,
|
310 |
+
"step": 210
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.2,
|
314 |
+
"grad_norm": 1.620552922782101,
|
315 |
+
"learning_rate": 1.9429350994350483e-05,
|
316 |
+
"loss": 1.0044,
|
317 |
+
"step": 215
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.2,
|
321 |
+
"grad_norm": 1.635093025466642,
|
322 |
+
"learning_rate": 1.93748276428884e-05,
|
323 |
+
"loss": 0.9856,
|
324 |
+
"step": 220
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.21,
|
328 |
+
"grad_norm": 1.674299362647312,
|
329 |
+
"learning_rate": 1.931790072708596e-05,
|
330 |
+
"loss": 0.9934,
|
331 |
+
"step": 225
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.21,
|
335 |
+
"grad_norm": 1.6887591497181855,
|
336 |
+
"learning_rate": 1.9258584842145342e-05,
|
337 |
+
"loss": 1.0112,
|
338 |
+
"step": 230
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.22,
|
342 |
+
"grad_norm": 1.645113774478941,
|
343 |
+
"learning_rate": 1.9196895195764363e-05,
|
344 |
+
"loss": 1.0066,
|
345 |
+
"step": 235
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.22,
|
349 |
+
"grad_norm": 1.6845020042548609,
|
350 |
+
"learning_rate": 1.913284760423745e-05,
|
351 |
+
"loss": 1.0158,
|
352 |
+
"step": 240
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.22,
|
356 |
+
"grad_norm": 1.647832284848899,
|
357 |
+
"learning_rate": 1.9066458488400586e-05,
|
358 |
+
"loss": 1.0086,
|
359 |
+
"step": 245
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.23,
|
363 |
+
"grad_norm": 1.697080815625411,
|
364 |
+
"learning_rate": 1.8997744869421248e-05,
|
365 |
+
"loss": 1.0155,
|
366 |
+
"step": 250
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.23,
|
370 |
+
"grad_norm": 1.7170796898803107,
|
371 |
+
"learning_rate": 1.8926724364434447e-05,
|
372 |
+
"loss": 1.0041,
|
373 |
+
"step": 255
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.24,
|
377 |
+
"grad_norm": 1.706074031599582,
|
378 |
+
"learning_rate": 1.8853415182025953e-05,
|
379 |
+
"loss": 0.9922,
|
380 |
+
"step": 260
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.24,
|
384 |
+
"grad_norm": 1.8989841472640996,
|
385 |
+
"learning_rate": 1.8777836117563894e-05,
|
386 |
+
"loss": 0.9941,
|
387 |
+
"step": 265
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.25,
|
391 |
+
"grad_norm": 1.7121367648810273,
|
392 |
+
"learning_rate": 1.8700006548379898e-05,
|
393 |
+
"loss": 1.0023,
|
394 |
+
"step": 270
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.25,
|
398 |
+
"grad_norm": 1.9417882651127933,
|
399 |
+
"learning_rate": 1.861994642880105e-05,
|
400 |
+
"loss": 1.0081,
|
401 |
+
"step": 275
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.26,
|
405 |
+
"grad_norm": 1.7496252675391932,
|
406 |
+
"learning_rate": 1.8537676285033886e-05,
|
407 |
+
"loss": 1.0012,
|
408 |
+
"step": 280
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.26,
|
412 |
+
"grad_norm": 1.5992757261270931,
|
413 |
+
"learning_rate": 1.845321720990181e-05,
|
414 |
+
"loss": 0.9882,
|
415 |
+
"step": 285
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.27,
|
419 |
+
"grad_norm": 1.5982026868074015,
|
420 |
+
"learning_rate": 1.8366590857437182e-05,
|
421 |
+
"loss": 0.9935,
|
422 |
+
"step": 290
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.27,
|
426 |
+
"grad_norm": 2.0122073912291203,
|
427 |
+
"learning_rate": 1.8277819437329577e-05,
|
428 |
+
"loss": 1.0075,
|
429 |
+
"step": 295
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.28,
|
433 |
+
"grad_norm": 21.05626958615313,
|
434 |
+
"learning_rate": 1.8186925709231534e-05,
|
435 |
+
"loss": 1.0239,
|
436 |
+
"step": 300
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.28,
|
440 |
+
"grad_norm": 5.626174907352815,
|
441 |
+
"learning_rate": 1.809393297692334e-05,
|
442 |
+
"loss": 1.1336,
|
443 |
+
"step": 305
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.28,
|
447 |
+
"grad_norm": 3.5588583574219355,
|
448 |
+
"learning_rate": 1.799886508233829e-05,
|
449 |
+
"loss": 1.0703,
|
450 |
+
"step": 310
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.29,
|
454 |
+
"grad_norm": 52.257959922882186,
|
455 |
+
"learning_rate": 1.790174639944997e-05,
|
456 |
+
"loss": 1.2478,
|
457 |
+
"step": 315
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.29,
|
461 |
+
"grad_norm": 8.296874056632827,
|
462 |
+
"learning_rate": 1.780260182802314e-05,
|
463 |
+
"loss": 1.4918,
|
464 |
+
"step": 320
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.3,
|
468 |
+
"grad_norm": 17.554936318206273,
|
469 |
+
"learning_rate": 1.7701456787229805e-05,
|
470 |
+
"loss": 1.2285,
|
471 |
+
"step": 325
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.3,
|
475 |
+
"grad_norm": 8.45205253267018,
|
476 |
+
"learning_rate": 1.7598337209132142e-05,
|
477 |
+
"loss": 1.1503,
|
478 |
+
"step": 330
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.31,
|
482 |
+
"grad_norm": 6.266748541585308,
|
483 |
+
"learning_rate": 1.7493269532033882e-05,
|
484 |
+
"loss": 1.1033,
|
485 |
+
"step": 335
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.31,
|
489 |
+
"grad_norm": 111.52289151968921,
|
490 |
+
"learning_rate": 1.738628069370195e-05,
|
491 |
+
"loss": 1.1048,
|
492 |
+
"step": 340
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.32,
|
496 |
+
"grad_norm": 7.688414643609198,
|
497 |
+
"learning_rate": 1.7277398124460022e-05,
|
498 |
+
"loss": 1.1117,
|
499 |
+
"step": 345
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.32,
|
503 |
+
"grad_norm": 4.031319921903212,
|
504 |
+
"learning_rate": 1.71666497401558e-05,
|
505 |
+
"loss": 1.0816,
|
506 |
+
"step": 350
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.33,
|
510 |
+
"grad_norm": 11.431111354306312,
|
511 |
+
"learning_rate": 1.7054063935003813e-05,
|
512 |
+
"loss": 1.0609,
|
513 |
+
"step": 355
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.33,
|
517 |
+
"grad_norm": 2.2441387172030134,
|
518 |
+
"learning_rate": 1.6939669574305565e-05,
|
519 |
+
"loss": 1.0462,
|
520 |
+
"step": 360
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.33,
|
524 |
+
"grad_norm": 2.0523696752811604,
|
525 |
+
"learning_rate": 1.6823495987048922e-05,
|
526 |
+
"loss": 1.0476,
|
527 |
+
"step": 365
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.34,
|
531 |
+
"grad_norm": 1.8895154393147975,
|
532 |
+
"learning_rate": 1.6705572958388576e-05,
|
533 |
+
"loss": 1.0311,
|
534 |
+
"step": 370
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.34,
|
538 |
+
"grad_norm": 1.8139444627013965,
|
539 |
+
"learning_rate": 1.6585930722009602e-05,
|
540 |
+
"loss": 1.0371,
|
541 |
+
"step": 375
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.35,
|
545 |
+
"grad_norm": 1.7032921177242157,
|
546 |
+
"learning_rate": 1.6464599952375998e-05,
|
547 |
+
"loss": 1.0436,
|
548 |
+
"step": 380
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.35,
|
552 |
+
"grad_norm": 1.7285341229493167,
|
553 |
+
"learning_rate": 1.63416117568662e-05,
|
554 |
+
"loss": 1.0119,
|
555 |
+
"step": 385
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.36,
|
559 |
+
"grad_norm": 1.722890751549469,
|
560 |
+
"learning_rate": 1.621699766779763e-05,
|
561 |
+
"loss": 1.0317,
|
562 |
+
"step": 390
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.36,
|
566 |
+
"grad_norm": 1.599051242781322,
|
567 |
+
"learning_rate": 1.6090789634342278e-05,
|
568 |
+
"loss": 1.0147,
|
569 |
+
"step": 395
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.37,
|
573 |
+
"grad_norm": 2.011875168952266,
|
574 |
+
"learning_rate": 1.5963020014335437e-05,
|
575 |
+
"loss": 1.0109,
|
576 |
+
"step": 400
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.37,
|
580 |
+
"grad_norm": 1.7745695288261167,
|
581 |
+
"learning_rate": 1.583372156597961e-05,
|
582 |
+
"loss": 1.0226,
|
583 |
+
"step": 405
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.38,
|
587 |
+
"grad_norm": 1.7032574663832216,
|
588 |
+
"learning_rate": 1.570292743944583e-05,
|
589 |
+
"loss": 0.9938,
|
590 |
+
"step": 410
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.38,
|
594 |
+
"grad_norm": 1.710578272048905,
|
595 |
+
"learning_rate": 1.557067116837444e-05,
|
596 |
+
"loss": 0.9883,
|
597 |
+
"step": 415
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.39,
|
601 |
+
"grad_norm": 1.6957880003939496,
|
602 |
+
"learning_rate": 1.5436986661277578e-05,
|
603 |
+
"loss": 0.9908,
|
604 |
+
"step": 420
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.39,
|
608 |
+
"grad_norm": 1.6008040760391928,
|
609 |
+
"learning_rate": 1.530190819284555e-05,
|
610 |
+
"loss": 1.0016,
|
611 |
+
"step": 425
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.39,
|
615 |
+
"grad_norm": 1.7382539416393734,
|
616 |
+
"learning_rate": 1.5165470395159314e-05,
|
617 |
+
"loss": 0.9929,
|
618 |
+
"step": 430
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.4,
|
622 |
+
"grad_norm": 1.8011281382514583,
|
623 |
+
"learning_rate": 1.5027708248811331e-05,
|
624 |
+
"loss": 0.9953,
|
625 |
+
"step": 435
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.4,
|
629 |
+
"grad_norm": 1.6996850685052767,
|
630 |
+
"learning_rate": 1.4888657073937077e-05,
|
631 |
+
"loss": 0.9906,
|
632 |
+
"step": 440
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.41,
|
636 |
+
"grad_norm": 1.618144358393542,
|
637 |
+
"learning_rate": 1.4748352521159492e-05,
|
638 |
+
"loss": 1.0065,
|
639 |
+
"step": 445
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.41,
|
643 |
+
"grad_norm": 1.52251331168285,
|
644 |
+
"learning_rate": 1.4606830562448692e-05,
|
645 |
+
"loss": 0.9944,
|
646 |
+
"step": 450
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.42,
|
650 |
+
"grad_norm": 1.9393071866897407,
|
651 |
+
"learning_rate": 1.4464127481899312e-05,
|
652 |
+
"loss": 0.9765,
|
653 |
+
"step": 455
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.42,
|
657 |
+
"grad_norm": 1.6893250353047762,
|
658 |
+
"learning_rate": 1.4320279866427798e-05,
|
659 |
+
"loss": 1.0034,
|
660 |
+
"step": 460
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.43,
|
664 |
+
"grad_norm": 1.5907871510849094,
|
665 |
+
"learning_rate": 1.4175324596392075e-05,
|
666 |
+
"loss": 0.9839,
|
667 |
+
"step": 465
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.43,
|
671 |
+
"grad_norm": 1.6419259125990346,
|
672 |
+
"learning_rate": 1.402929883613599e-05,
|
673 |
+
"loss": 1.004,
|
674 |
+
"step": 470
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.44,
|
678 |
+
"grad_norm": 1.5792169432621945,
|
679 |
+
"learning_rate": 1.3882240024460928e-05,
|
680 |
+
"loss": 0.9583,
|
681 |
+
"step": 475
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.44,
|
685 |
+
"grad_norm": 1.5453338942420716,
|
686 |
+
"learning_rate": 1.3734185865027061e-05,
|
687 |
+
"loss": 0.9818,
|
688 |
+
"step": 480
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.44,
|
692 |
+
"grad_norm": 1.6532156284337152,
|
693 |
+
"learning_rate": 1.358517431668672e-05,
|
694 |
+
"loss": 0.9812,
|
695 |
+
"step": 485
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.45,
|
699 |
+
"grad_norm": 1.8030804926474087,
|
700 |
+
"learning_rate": 1.3435243583752294e-05,
|
701 |
+
"loss": 0.9799,
|
702 |
+
"step": 490
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.45,
|
706 |
+
"grad_norm": 1.6418123185067888,
|
707 |
+
"learning_rate": 1.3284432106201233e-05,
|
708 |
+
"loss": 0.9916,
|
709 |
+
"step": 495
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.46,
|
713 |
+
"grad_norm": 1.6258591855391478,
|
714 |
+
"learning_rate": 1.313277854982062e-05,
|
715 |
+
"loss": 0.9917,
|
716 |
+
"step": 500
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.46,
|
720 |
+
"grad_norm": 2.02063585594681,
|
721 |
+
"learning_rate": 1.2980321796293838e-05,
|
722 |
+
"loss": 0.9821,
|
723 |
+
"step": 505
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.47,
|
727 |
+
"grad_norm": 1.4641044058112402,
|
728 |
+
"learning_rate": 1.2827100933231904e-05,
|
729 |
+
"loss": 0.9669,
|
730 |
+
"step": 510
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.47,
|
734 |
+
"grad_norm": 1.4734009074897523,
|
735 |
+
"learning_rate": 1.2673155244151985e-05,
|
736 |
+
"loss": 0.9887,
|
737 |
+
"step": 515
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.48,
|
741 |
+
"grad_norm": 1.504049205573269,
|
742 |
+
"learning_rate": 1.2518524198405699e-05,
|
743 |
+
"loss": 0.9752,
|
744 |
+
"step": 520
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.48,
|
748 |
+
"grad_norm": 1.5871801520121447,
|
749 |
+
"learning_rate": 1.2363247441059775e-05,
|
750 |
+
"loss": 0.986,
|
751 |
+
"step": 525
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.49,
|
755 |
+
"grad_norm": 1.5031034877601523,
|
756 |
+
"learning_rate": 1.2207364782731657e-05,
|
757 |
+
"loss": 0.9827,
|
758 |
+
"step": 530
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.49,
|
762 |
+
"grad_norm": 1.680552260004968,
|
763 |
+
"learning_rate": 1.2050916189382646e-05,
|
764 |
+
"loss": 0.977,
|
765 |
+
"step": 535
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.5,
|
769 |
+
"grad_norm": 1.5439369139377679,
|
770 |
+
"learning_rate": 1.189394177207125e-05,
|
771 |
+
"loss": 0.9746,
|
772 |
+
"step": 540
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.5,
|
776 |
+
"grad_norm": 1.4901425478827495,
|
777 |
+
"learning_rate": 1.1736481776669307e-05,
|
778 |
+
"loss": 0.9653,
|
779 |
+
"step": 545
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.5,
|
783 |
+
"grad_norm": 1.468475262540055,
|
784 |
+
"learning_rate": 1.1578576573543541e-05,
|
785 |
+
"loss": 0.9887,
|
786 |
+
"step": 550
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.51,
|
790 |
+
"grad_norm": 1.4398608054707567,
|
791 |
+
"learning_rate": 1.1420266647205232e-05,
|
792 |
+
"loss": 0.9761,
|
793 |
+
"step": 555
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.51,
|
797 |
+
"grad_norm": 1.5422374491434532,
|
798 |
+
"learning_rate": 1.1261592585930576e-05,
|
799 |
+
"loss": 0.9582,
|
800 |
+
"step": 560
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.52,
|
804 |
+
"grad_norm": 1.5286775911829815,
|
805 |
+
"learning_rate": 1.1102595071354471e-05,
|
806 |
+
"loss": 0.9738,
|
807 |
+
"step": 565
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.52,
|
811 |
+
"grad_norm": 1.4817522889069266,
|
812 |
+
"learning_rate": 1.0943314868040365e-05,
|
813 |
+
"loss": 0.9813,
|
814 |
+
"step": 570
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.53,
|
818 |
+
"grad_norm": 1.4293384597101042,
|
819 |
+
"learning_rate": 1.0783792813028828e-05,
|
820 |
+
"loss": 0.9674,
|
821 |
+
"step": 575
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.53,
|
825 |
+
"grad_norm": 1.5261318491484366,
|
826 |
+
"learning_rate": 1.0624069805367558e-05,
|
827 |
+
"loss": 0.985,
|
828 |
+
"step": 580
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.54,
|
832 |
+
"grad_norm": 1.5097693128941394,
|
833 |
+
"learning_rate": 1.0464186795625481e-05,
|
834 |
+
"loss": 0.9639,
|
835 |
+
"step": 585
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.54,
|
839 |
+
"grad_norm": 1.5846698306417735,
|
840 |
+
"learning_rate": 1.0304184775393642e-05,
|
841 |
+
"loss": 0.9701,
|
842 |
+
"step": 590
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.55,
|
846 |
+
"grad_norm": 1.4231247673906455,
|
847 |
+
"learning_rate": 1.0144104766775574e-05,
|
848 |
+
"loss": 0.9684,
|
849 |
+
"step": 595
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.55,
|
853 |
+
"grad_norm": 1.4645243353450357,
|
854 |
+
"learning_rate": 9.983987811869863e-06,
|
855 |
+
"loss": 0.9726,
|
856 |
+
"step": 600
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.56,
|
860 |
+
"grad_norm": 1.6188671105629062,
|
861 |
+
"learning_rate": 9.823874962247565e-06,
|
862 |
+
"loss": 0.9562,
|
863 |
+
"step": 605
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.56,
|
867 |
+
"grad_norm": 1.4748824240542495,
|
868 |
+
"learning_rate": 9.663807268427197e-06,
|
869 |
+
"loss": 0.9677,
|
870 |
+
"step": 610
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.56,
|
874 |
+
"grad_norm": 1.427861703011802,
|
875 |
+
"learning_rate": 9.503825769350016e-06,
|
876 |
+
"loss": 0.9645,
|
877 |
+
"step": 615
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.57,
|
881 |
+
"grad_norm": 1.4151510701857246,
|
882 |
+
"learning_rate": 9.343971481858246e-06,
|
883 |
+
"loss": 0.9423,
|
884 |
+
"step": 620
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.57,
|
888 |
+
"grad_norm": 1.4516242963328596,
|
889 |
+
"learning_rate": 9.184285390178978e-06,
|
890 |
+
"loss": 0.9656,
|
891 |
+
"step": 625
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.58,
|
895 |
+
"grad_norm": 1.7062684460068769,
|
896 |
+
"learning_rate": 9.024808435416435e-06,
|
897 |
+
"loss": 0.9637,
|
898 |
+
"step": 630
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.58,
|
902 |
+
"grad_norm": 1.4522675784960328,
|
903 |
+
"learning_rate": 8.865581505055292e-06,
|
904 |
+
"loss": 0.9786,
|
905 |
+
"step": 635
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.59,
|
909 |
+
"grad_norm": 1.4328537035514395,
|
910 |
+
"learning_rate": 8.706645422477739e-06,
|
911 |
+
"loss": 0.948,
|
912 |
+
"step": 640
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.59,
|
916 |
+
"grad_norm": 1.5567683964703176,
|
917 |
+
"learning_rate": 8.548040936496989e-06,
|
918 |
+
"loss": 0.9613,
|
919 |
+
"step": 645
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.6,
|
923 |
+
"grad_norm": 1.5074863131808958,
|
924 |
+
"learning_rate": 8.389808710909881e-06,
|
925 |
+
"loss": 0.9514,
|
926 |
+
"step": 650
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.6,
|
930 |
+
"grad_norm": 1.4273894196530337,
|
931 |
+
"learning_rate": 8.231989314071318e-06,
|
932 |
+
"loss": 0.9656,
|
933 |
+
"step": 655
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.61,
|
937 |
+
"grad_norm": 1.471995206720774,
|
938 |
+
"learning_rate": 8.07462320849313e-06,
|
939 |
+
"loss": 0.9475,
|
940 |
+
"step": 660
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.61,
|
944 |
+
"grad_norm": 1.568608987104535,
|
945 |
+
"learning_rate": 7.917750740470116e-06,
|
946 |
+
"loss": 0.9769,
|
947 |
+
"step": 665
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.61,
|
951 |
+
"grad_norm": 1.3745365175696858,
|
952 |
+
"learning_rate": 7.761412129735853e-06,
|
953 |
+
"loss": 0.9603,
|
954 |
+
"step": 670
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.62,
|
958 |
+
"grad_norm": 1.466522406606583,
|
959 |
+
"learning_rate": 7.605647459150961e-06,
|
960 |
+
"loss": 0.9332,
|
961 |
+
"step": 675
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.62,
|
965 |
+
"grad_norm": 1.3463238948259868,
|
966 |
+
"learning_rate": 7.4504966644264775e-06,
|
967 |
+
"loss": 0.9436,
|
968 |
+
"step": 680
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.63,
|
972 |
+
"grad_norm": 1.4997500356384885,
|
973 |
+
"learning_rate": 7.295999523884921e-06,
|
974 |
+
"loss": 0.9363,
|
975 |
+
"step": 685
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.63,
|
979 |
+
"grad_norm": 1.4849900349578966,
|
980 |
+
"learning_rate": 7.142195648261747e-06,
|
981 |
+
"loss": 0.9699,
|
982 |
+
"step": 690
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.64,
|
986 |
+
"grad_norm": 1.4732303903444304,
|
987 |
+
"learning_rate": 6.989124470549746e-06,
|
988 |
+
"loss": 0.9582,
|
989 |
+
"step": 695
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.64,
|
993 |
+
"grad_norm": 1.3881607197451564,
|
994 |
+
"learning_rate": 6.83682523588902e-06,
|
995 |
+
"loss": 0.9457,
|
996 |
+
"step": 700
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.65,
|
1000 |
+
"grad_norm": 1.441527770787461,
|
1001 |
+
"learning_rate": 6.685336991505122e-06,
|
1002 |
+
"loss": 0.961,
|
1003 |
+
"step": 705
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.65,
|
1007 |
+
"grad_norm": 1.5093653951413892,
|
1008 |
+
"learning_rate": 6.5346985766979384e-06,
|
1009 |
+
"loss": 0.9557,
|
1010 |
+
"step": 710
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.66,
|
1014 |
+
"grad_norm": 1.3906632586548848,
|
1015 |
+
"learning_rate": 6.384948612883872e-06,
|
1016 |
+
"loss": 0.9274,
|
1017 |
+
"step": 715
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.66,
|
1021 |
+
"grad_norm": 1.4296014203069103,
|
1022 |
+
"learning_rate": 6.2361254936939e-06,
|
1023 |
+
"loss": 0.9333,
|
1024 |
+
"step": 720
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.67,
|
1028 |
+
"grad_norm": 1.4300856178576173,
|
1029 |
+
"learning_rate": 6.0882673751300235e-06,
|
1030 |
+
"loss": 0.9462,
|
1031 |
+
"step": 725
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.67,
|
1035 |
+
"grad_norm": 1.3936601183930903,
|
1036 |
+
"learning_rate": 5.941412165782645e-06,
|
1037 |
+
"loss": 0.9479,
|
1038 |
+
"step": 730
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.67,
|
1042 |
+
"grad_norm": 1.6621722765974563,
|
1043 |
+
"learning_rate": 5.79559751711138e-06,
|
1044 |
+
"loss": 0.9459,
|
1045 |
+
"step": 735
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.68,
|
1049 |
+
"grad_norm": 1.4433022742228918,
|
1050 |
+
"learning_rate": 5.650860813791786e-06,
|
1051 |
+
"loss": 0.9308,
|
1052 |
+
"step": 740
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.68,
|
1056 |
+
"grad_norm": 1.3734643883063014,
|
1057 |
+
"learning_rate": 5.507239164130501e-06,
|
1058 |
+
"loss": 0.9487,
|
1059 |
+
"step": 745
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.69,
|
1063 |
+
"grad_norm": 1.387981074803405,
|
1064 |
+
"learning_rate": 5.364769390551225e-06,
|
1065 |
+
"loss": 0.9545,
|
1066 |
+
"step": 750
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.69,
|
1070 |
+
"grad_norm": 1.391011395848312,
|
1071 |
+
"learning_rate": 5.223488020154028e-06,
|
1072 |
+
"loss": 0.9419,
|
1073 |
+
"step": 755
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.7,
|
1077 |
+
"grad_norm": 1.4792090950991559,
|
1078 |
+
"learning_rate": 5.083431275350312e-06,
|
1079 |
+
"loss": 0.9426,
|
1080 |
+
"step": 760
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.7,
|
1084 |
+
"grad_norm": 1.3955718332534048,
|
1085 |
+
"learning_rate": 4.9446350645759885e-06,
|
1086 |
+
"loss": 0.9303,
|
1087 |
+
"step": 765
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.71,
|
1091 |
+
"grad_norm": 1.4552341272988114,
|
1092 |
+
"learning_rate": 4.807134973085036e-06,
|
1093 |
+
"loss": 0.9551,
|
1094 |
+
"step": 770
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.71,
|
1098 |
+
"grad_norm": 1.4197472248094545,
|
1099 |
+
"learning_rate": 4.670966253826027e-06,
|
1100 |
+
"loss": 0.948,
|
1101 |
+
"step": 775
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.72,
|
1105 |
+
"grad_norm": 1.3903141656921318,
|
1106 |
+
"learning_rate": 4.53616381840377e-06,
|
1107 |
+
"loss": 0.9404,
|
1108 |
+
"step": 780
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.72,
|
1112 |
+
"grad_norm": 1.4683373587462776,
|
1113 |
+
"learning_rate": 4.402762228128531e-06,
|
1114 |
+
"loss": 0.9393,
|
1115 |
+
"step": 785
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.72,
|
1119 |
+
"grad_norm": 1.3895342562056905,
|
1120 |
+
"learning_rate": 4.270795685155001e-06,
|
1121 |
+
"loss": 0.9295,
|
1122 |
+
"step": 790
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.73,
|
1126 |
+
"grad_norm": 1.3645654190042658,
|
1127 |
+
"learning_rate": 4.140298023713416e-06,
|
1128 |
+
"loss": 0.9322,
|
1129 |
+
"step": 795
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.73,
|
1133 |
+
"grad_norm": 1.3831028295258314,
|
1134 |
+
"learning_rate": 4.0113027014349374e-06,
|
1135 |
+
"loss": 0.9393,
|
1136 |
+
"step": 800
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.74,
|
1140 |
+
"grad_norm": 1.402507806165818,
|
1141 |
+
"learning_rate": 3.883842790773647e-06,
|
1142 |
+
"loss": 0.9407,
|
1143 |
+
"step": 805
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.74,
|
1147 |
+
"grad_norm": 1.3477220628229905,
|
1148 |
+
"learning_rate": 3.757950970527249e-06,
|
1149 |
+
"loss": 0.9399,
|
1150 |
+
"step": 810
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.75,
|
1154 |
+
"grad_norm": 1.4105862702544307,
|
1155 |
+
"learning_rate": 3.633659517458736e-06,
|
1156 |
+
"loss": 0.9429,
|
1157 |
+
"step": 815
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.75,
|
1161 |
+
"grad_norm": 1.4134155318530202,
|
1162 |
+
"learning_rate": 3.511000298021098e-06,
|
1163 |
+
"loss": 0.9267,
|
1164 |
+
"step": 820
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.76,
|
1168 |
+
"grad_norm": 2.671468704931624,
|
1169 |
+
"learning_rate": 3.39000476018726e-06,
|
1170 |
+
"loss": 0.9405,
|
1171 |
+
"step": 825
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.76,
|
1175 |
+
"grad_norm": 1.518363690298914,
|
1176 |
+
"learning_rate": 3.2707039253872796e-06,
|
1177 |
+
"loss": 0.9499,
|
1178 |
+
"step": 830
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.77,
|
1182 |
+
"grad_norm": 1.391445796072115,
|
1183 |
+
"learning_rate": 3.153128380554941e-06,
|
1184 |
+
"loss": 0.9397,
|
1185 |
+
"step": 835
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.77,
|
1189 |
+
"grad_norm": 1.4199198449516006,
|
1190 |
+
"learning_rate": 3.037308270285709e-06,
|
1191 |
+
"loss": 0.9374,
|
1192 |
+
"step": 840
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.78,
|
1196 |
+
"grad_norm": 1.3725059360040226,
|
1197 |
+
"learning_rate": 2.923273289108115e-06,
|
1198 |
+
"loss": 0.9289,
|
1199 |
+
"step": 845
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.78,
|
1203 |
+
"grad_norm": 1.402432038179815,
|
1204 |
+
"learning_rate": 2.8110526738705345e-06,
|
1205 |
+
"loss": 0.9399,
|
1206 |
+
"step": 850
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.78,
|
1210 |
+
"grad_norm": 1.3538150837811775,
|
1211 |
+
"learning_rate": 2.700675196245288e-06,
|
1212 |
+
"loss": 0.9235,
|
1213 |
+
"step": 855
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.79,
|
1217 |
+
"grad_norm": 1.3719901639969891,
|
1218 |
+
"learning_rate": 2.592169155352031e-06,
|
1219 |
+
"loss": 0.9305,
|
1220 |
+
"step": 860
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.79,
|
1224 |
+
"grad_norm": 1.3417159608633782,
|
1225 |
+
"learning_rate": 2.485562370502279e-06,
|
1226 |
+
"loss": 0.93,
|
1227 |
+
"step": 865
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.8,
|
1231 |
+
"grad_norm": 1.447083155674768,
|
1232 |
+
"learning_rate": 2.3808821740669608e-06,
|
1233 |
+
"loss": 0.9444,
|
1234 |
+
"step": 870
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.8,
|
1238 |
+
"grad_norm": 1.457818919394179,
|
1239 |
+
"learning_rate": 2.2781554044688015e-06,
|
1240 |
+
"loss": 0.944,
|
1241 |
+
"step": 875
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.81,
|
1245 |
+
"grad_norm": 1.3423569321240763,
|
1246 |
+
"learning_rate": 2.1774083993013715e-06,
|
1247 |
+
"loss": 0.9284,
|
1248 |
+
"step": 880
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.81,
|
1252 |
+
"grad_norm": 1.4022698745517062,
|
1253 |
+
"learning_rate": 2.0786669885765044e-06,
|
1254 |
+
"loss": 0.943,
|
1255 |
+
"step": 885
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.82,
|
1259 |
+
"grad_norm": 1.3695761420314987,
|
1260 |
+
"learning_rate": 1.981956488101898e-06,
|
1261 |
+
"loss": 0.9419,
|
1262 |
+
"step": 890
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.82,
|
1266 |
+
"grad_norm": 1.351231324123156,
|
1267 |
+
"learning_rate": 1.8873016929904942e-06,
|
1268 |
+
"loss": 0.9315,
|
1269 |
+
"step": 895
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.83,
|
1273 |
+
"grad_norm": 1.4420470493119792,
|
1274 |
+
"learning_rate": 1.7947268713034128e-06,
|
1275 |
+
"loss": 0.9247,
|
1276 |
+
"step": 900
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.83,
|
1280 |
+
"grad_norm": 1.376296944069193,
|
1281 |
+
"learning_rate": 1.704255757827963e-06,
|
1282 |
+
"loss": 0.9443,
|
1283 |
+
"step": 905
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.83,
|
1287 |
+
"grad_norm": 1.3432275033995362,
|
1288 |
+
"learning_rate": 1.6159115479924259e-06,
|
1289 |
+
"loss": 0.9453,
|
1290 |
+
"step": 910
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.84,
|
1294 |
+
"grad_norm": 1.408037299795807,
|
1295 |
+
"learning_rate": 1.529716891919074e-06,
|
1296 |
+
"loss": 0.9168,
|
1297 |
+
"step": 915
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.84,
|
1301 |
+
"grad_norm": 1.3321909436006458,
|
1302 |
+
"learning_rate": 1.4456938886170413e-06,
|
1303 |
+
"loss": 0.9284,
|
1304 |
+
"step": 920
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.85,
|
1308 |
+
"grad_norm": 1.4347603275075604,
|
1309 |
+
"learning_rate": 1.3638640803164516e-06,
|
1310 |
+
"loss": 0.928,
|
1311 |
+
"step": 925
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.85,
|
1315 |
+
"grad_norm": 1.414525145641175,
|
1316 |
+
"learning_rate": 1.2842484469453365e-06,
|
1317 |
+
"loss": 0.9247,
|
1318 |
+
"step": 930
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.86,
|
1322 |
+
"grad_norm": 1.3556935778322545,
|
1323 |
+
"learning_rate": 1.2068674007506787e-06,
|
1324 |
+
"loss": 0.9212,
|
1325 |
+
"step": 935
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.86,
|
1329 |
+
"grad_norm": 1.4388764825242009,
|
1330 |
+
"learning_rate": 1.1317407810650372e-06,
|
1331 |
+
"loss": 0.9168,
|
1332 |
+
"step": 940
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 0.87,
|
1336 |
+
"grad_norm": 1.3989979018945433,
|
1337 |
+
"learning_rate": 1.0588878492200261e-06,
|
1338 |
+
"loss": 0.9288,
|
1339 |
+
"step": 945
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.87,
|
1343 |
+
"grad_norm": 1.3566434474333582,
|
1344 |
+
"learning_rate": 9.883272836080116e-07,
|
1345 |
+
"loss": 0.926,
|
1346 |
+
"step": 950
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.88,
|
1350 |
+
"grad_norm": 1.4319194447938426,
|
1351 |
+
"learning_rate": 9.200771748932513e-07,
|
1352 |
+
"loss": 0.9455,
|
1353 |
+
"step": 955
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.88,
|
1357 |
+
"grad_norm": 1.3526304536258829,
|
1358 |
+
"learning_rate": 8.541550213737171e-07,
|
1359 |
+
"loss": 0.9261,
|
1360 |
+
"step": 960
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.89,
|
1364 |
+
"grad_norm": 1.399241882005225,
|
1365 |
+
"learning_rate": 7.905777244947954e-07,
|
1366 |
+
"loss": 0.9316,
|
1367 |
+
"step": 965
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.89,
|
1371 |
+
"grad_norm": 1.4094250992512831,
|
1372 |
+
"learning_rate": 7.293615845160196e-07,
|
1373 |
+
"loss": 0.9275,
|
1374 |
+
"step": 970
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.89,
|
1378 |
+
"grad_norm": 1.3526180756349577,
|
1379 |
+
"learning_rate": 6.705222963319191e-07,
|
1380 |
+
"loss": 0.9363,
|
1381 |
+
"step": 975
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.9,
|
1385 |
+
"grad_norm": 1.416809797785314,
|
1386 |
+
"learning_rate": 6.140749454480932e-07,
|
1387 |
+
"loss": 0.9297,
|
1388 |
+
"step": 980
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.9,
|
1392 |
+
"grad_norm": 1.351887149750103,
|
1393 |
+
"learning_rate": 5.600340041135133e-07,
|
1394 |
+
"loss": 0.9393,
|
1395 |
+
"step": 985
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.91,
|
1399 |
+
"grad_norm": 1.3895523431306795,
|
1400 |
+
"learning_rate": 5.0841332761005e-07,
|
1401 |
+
"loss": 0.9383,
|
1402 |
+
"step": 990
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.91,
|
1406 |
+
"grad_norm": 1.3424090925296945,
|
1407 |
+
"learning_rate": 4.592261507001994e-07,
|
1408 |
+
"loss": 0.9215,
|
1409 |
+
"step": 995
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.92,
|
1413 |
+
"grad_norm": 1.3838142145295658,
|
1414 |
+
"learning_rate": 4.124850842338779e-07,
|
1415 |
+
"loss": 0.9369,
|
1416 |
+
"step": 1000
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.92,
|
1420 |
+
"grad_norm": 1.4019675844003927,
|
1421 |
+
"learning_rate": 3.6820211191520127e-07,
|
1422 |
+
"loss": 0.9269,
|
1423 |
+
"step": 1005
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 0.93,
|
1427 |
+
"grad_norm": 1.4513095530474966,
|
1428 |
+
"learning_rate": 3.263885872300343e-07,
|
1429 |
+
"loss": 0.9507,
|
1430 |
+
"step": 1010
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 0.93,
|
1434 |
+
"grad_norm": 1.361924533980129,
|
1435 |
+
"learning_rate": 2.870552305351382e-07,
|
1436 |
+
"loss": 0.9196,
|
1437 |
+
"step": 1015
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.94,
|
1441 |
+
"grad_norm": 1.3927244960089797,
|
1442 |
+
"learning_rate": 2.5021212630962246e-07,
|
1443 |
+
"loss": 0.9328,
|
1444 |
+
"step": 1020
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 0.94,
|
1448 |
+
"grad_norm": 1.3290530166960066,
|
1449 |
+
"learning_rate": 2.158687205694443e-07,
|
1450 |
+
"loss": 0.9405,
|
1451 |
+
"step": 1025
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 0.94,
|
1455 |
+
"grad_norm": 1.3680987060349954,
|
1456 |
+
"learning_rate": 1.840338184455881e-07,
|
1457 |
+
"loss": 0.9276,
|
1458 |
+
"step": 1030
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 0.95,
|
1462 |
+
"grad_norm": 1.3438546650666667,
|
1463 |
+
"learning_rate": 1.5471558192656776e-07,
|
1464 |
+
"loss": 0.9221,
|
1465 |
+
"step": 1035
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.95,
|
1469 |
+
"grad_norm": 1.4512371380173261,
|
1470 |
+
"learning_rate": 1.279215277658097e-07,
|
1471 |
+
"loss": 0.9336,
|
1472 |
+
"step": 1040
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 0.96,
|
1476 |
+
"grad_norm": 1.362018016831518,
|
1477 |
+
"learning_rate": 1.0365852555447642e-07,
|
1478 |
+
"loss": 0.9175,
|
1479 |
+
"step": 1045
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.96,
|
1483 |
+
"grad_norm": 1.359560038203717,
|
1484 |
+
"learning_rate": 8.19327959602012e-08,
|
1485 |
+
"loss": 0.91,
|
1486 |
+
"step": 1050
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 0.97,
|
1490 |
+
"grad_norm": 1.3944491658597338,
|
1491 |
+
"learning_rate": 6.274990913221035e-08,
|
1492 |
+
"loss": 0.946,
|
1493 |
+
"step": 1055
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 0.97,
|
1497 |
+
"grad_norm": 1.3012436329306727,
|
1498 |
+
"learning_rate": 4.6114783273213395e-08,
|
1499 |
+
"loss": 0.9316,
|
1500 |
+
"step": 1060
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 0.98,
|
1504 |
+
"grad_norm": 1.4375328358464377,
|
1505 |
+
"learning_rate": 3.203168337845508e-08,
|
1506 |
+
"loss": 0.9098,
|
1507 |
+
"step": 1065
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 0.98,
|
1511 |
+
"grad_norm": 1.321439340704291,
|
1512 |
+
"learning_rate": 2.05042201422323e-08,
|
1513 |
+
"loss": 0.9084,
|
1514 |
+
"step": 1070
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 0.99,
|
1518 |
+
"grad_norm": 1.4259870829955092,
|
1519 |
+
"learning_rate": 1.1535349032167908e-08,
|
1520 |
+
"loss": 0.9399,
|
1521 |
+
"step": 1075
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.99,
|
1525 |
+
"grad_norm": 1.4012106970656215,
|
1526 |
+
"learning_rate": 5.127369531473525e-09,
|
1527 |
+
"loss": 0.9261,
|
1528 |
+
"step": 1080
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 1.0,
|
1532 |
+
"grad_norm": 1.3831302460073325,
|
1533 |
+
"learning_rate": 1.2819245493955746e-09,
|
1534 |
+
"loss": 0.9336,
|
1535 |
+
"step": 1085
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 1.0,
|
1539 |
+
"grad_norm": 1.3587054894081556,
|
1540 |
+
"learning_rate": 0.0,
|
1541 |
+
"loss": 0.9355,
|
1542 |
+
"step": 1090
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 1.0,
|
1546 |
+
"eval_loss": 0.9393356442451477,
|
1547 |
+
"eval_runtime": 322.3924,
|
1548 |
+
"eval_samples_per_second": 47.864,
|
1549 |
+
"eval_steps_per_second": 0.751,
|
1550 |
+
"step": 1090
|
1551 |
+
},
|
1552 |
+
{
|
1553 |
+
"epoch": 1.0,
|
1554 |
+
"step": 1090,
|
1555 |
+
"total_flos": 456447649382400.0,
|
1556 |
+
"train_loss": 0.9795057065989993,
|
1557 |
+
"train_runtime": 15753.4108,
|
1558 |
+
"train_samples_per_second": 8.85,
|
1559 |
+
"train_steps_per_second": 0.069
|
1560 |
+
}
|
1561 |
+
],
|
1562 |
+
"logging_steps": 5,
|
1563 |
+
"max_steps": 1090,
|
1564 |
+
"num_input_tokens_seen": 0,
|
1565 |
+
"num_train_epochs": 1,
|
1566 |
+
"save_steps": 100,
|
1567 |
+
"total_flos": 456447649382400.0,
|
1568 |
+
"train_batch_size": 16,
|
1569 |
+
"trial_name": null,
|
1570 |
+
"trial_params": null
|
1571 |
+
}
|