Model save
Browse files- README.md +62 -0
- all_results.json +9 -0
- runs/Sep20_23-06-53_COE-CS-sv004/events.out.tfevents.1726873650.COE-CS-sv004.1316815.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +798 -0
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama3
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: meta-llama/Meta-Llama-3-8B
|
9 |
+
model-index:
|
10 |
+
- name: llama3_preference
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# llama3_preference
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 1e-05
|
39 |
+
- train_batch_size: 8
|
40 |
+
- eval_batch_size: 1
|
41 |
+
- seed: 42
|
42 |
+
- distributed_type: multi-GPU
|
43 |
+
- num_devices: 4
|
44 |
+
- gradient_accumulation_steps: 2
|
45 |
+
- total_train_batch_size: 64
|
46 |
+
- total_eval_batch_size: 4
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: cosine
|
49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
50 |
+
- num_epochs: 1
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
|
55 |
+
|
56 |
+
### Framework versions
|
57 |
+
|
58 |
+
- PEFT 0.11.1
|
59 |
+
- Transformers 4.44.2
|
60 |
+
- Pytorch 2.3.1+cu121
|
61 |
+
- Datasets 2.19.1
|
62 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9990645463049579,
|
3 |
+
"total_flos": 2.2276586722453094e+17,
|
4 |
+
"train_loss": 1.1599709373734863,
|
5 |
+
"train_runtime": 17757.3527,
|
6 |
+
"train_samples": 98881,
|
7 |
+
"train_samples_per_second": 1.925,
|
8 |
+
"train_steps_per_second": 0.03
|
9 |
+
}
|
runs/Sep20_23-06-53_COE-CS-sv004/events.out.tfevents.1726873650.COE-CS-sv004.1316815.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c5684e125ffa8e966296407789e4587e7c36446a960511bae4ea10838fb765d
|
3 |
+
size 28255
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9990645463049579,
|
3 |
+
"total_flos": 2.2276586722453094e+17,
|
4 |
+
"train_loss": 1.1599709373734863,
|
5 |
+
"train_runtime": 17757.3527,
|
6 |
+
"train_samples": 98881,
|
7 |
+
"train_samples_per_second": 1.925,
|
8 |
+
"train_steps_per_second": 0.03
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,798 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9990645463049579,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 534,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0018709073900841909,
|
13 |
+
"grad_norm": 0.5139586586877397,
|
14 |
+
"learning_rate": 1.8518518518518518e-07,
|
15 |
+
"loss": 1.4813,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.009354536950420954,
|
20 |
+
"grad_norm": 0.5084917331083768,
|
21 |
+
"learning_rate": 9.259259259259259e-07,
|
22 |
+
"loss": 1.4869,
|
23 |
+
"step": 5
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.018709073900841908,
|
27 |
+
"grad_norm": 0.5086882763520935,
|
28 |
+
"learning_rate": 1.8518518518518519e-06,
|
29 |
+
"loss": 1.4912,
|
30 |
+
"step": 10
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.02806361085126286,
|
34 |
+
"grad_norm": 0.49639126734512623,
|
35 |
+
"learning_rate": 2.7777777777777783e-06,
|
36 |
+
"loss": 1.4813,
|
37 |
+
"step": 15
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.037418147801683815,
|
41 |
+
"grad_norm": 0.5064168113795362,
|
42 |
+
"learning_rate": 3.7037037037037037e-06,
|
43 |
+
"loss": 1.4849,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.04677268475210477,
|
48 |
+
"grad_norm": 0.474054321279664,
|
49 |
+
"learning_rate": 4.62962962962963e-06,
|
50 |
+
"loss": 1.4776,
|
51 |
+
"step": 25
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.05612722170252572,
|
55 |
+
"grad_norm": 0.40667394555209146,
|
56 |
+
"learning_rate": 5.555555555555557e-06,
|
57 |
+
"loss": 1.4756,
|
58 |
+
"step": 30
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.06548175865294668,
|
62 |
+
"grad_norm": 0.2821916256658075,
|
63 |
+
"learning_rate": 6.481481481481482e-06,
|
64 |
+
"loss": 1.4585,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.07483629560336763,
|
69 |
+
"grad_norm": 0.2369804283848295,
|
70 |
+
"learning_rate": 7.4074074074074075e-06,
|
71 |
+
"loss": 1.4529,
|
72 |
+
"step": 40
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.08419083255378859,
|
76 |
+
"grad_norm": 0.23752287185591942,
|
77 |
+
"learning_rate": 8.333333333333334e-06,
|
78 |
+
"loss": 1.4356,
|
79 |
+
"step": 45
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.09354536950420954,
|
83 |
+
"grad_norm": 0.233703618586824,
|
84 |
+
"learning_rate": 9.25925925925926e-06,
|
85 |
+
"loss": 1.4195,
|
86 |
+
"step": 50
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.1028999064546305,
|
90 |
+
"grad_norm": 0.21334448181657395,
|
91 |
+
"learning_rate": 9.999892908320647e-06,
|
92 |
+
"loss": 1.4009,
|
93 |
+
"step": 55
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.11225444340505145,
|
97 |
+
"grad_norm": 0.21146314339445296,
|
98 |
+
"learning_rate": 9.996145181203616e-06,
|
99 |
+
"loss": 1.3904,
|
100 |
+
"step": 60
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.1216089803554724,
|
104 |
+
"grad_norm": 0.20882987047024354,
|
105 |
+
"learning_rate": 9.98704745668676e-06,
|
106 |
+
"loss": 1.3718,
|
107 |
+
"step": 65
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.13096351730589337,
|
111 |
+
"grad_norm": 0.21207151944716085,
|
112 |
+
"learning_rate": 9.972609476841368e-06,
|
113 |
+
"loss": 1.3591,
|
114 |
+
"step": 70
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.1403180542563143,
|
118 |
+
"grad_norm": 0.22054679673319932,
|
119 |
+
"learning_rate": 9.952846702217886e-06,
|
120 |
+
"loss": 1.342,
|
121 |
+
"step": 75
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.14967259120673526,
|
125 |
+
"grad_norm": 0.27057760894999794,
|
126 |
+
"learning_rate": 9.92778029529039e-06,
|
127 |
+
"loss": 1.3213,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.15902712815715622,
|
132 |
+
"grad_norm": 0.29764481463424675,
|
133 |
+
"learning_rate": 9.897437097795257e-06,
|
134 |
+
"loss": 1.2966,
|
135 |
+
"step": 85
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.16838166510757718,
|
139 |
+
"grad_norm": 0.3056628343357791,
|
140 |
+
"learning_rate": 9.861849601988384e-06,
|
141 |
+
"loss": 1.2748,
|
142 |
+
"step": 90
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.17773620205799812,
|
146 |
+
"grad_norm": 0.3099000095239784,
|
147 |
+
"learning_rate": 9.821055915851647e-06,
|
148 |
+
"loss": 1.2542,
|
149 |
+
"step": 95
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.18709073900841908,
|
153 |
+
"grad_norm": 0.2668477842603494,
|
154 |
+
"learning_rate": 9.775099722285934e-06,
|
155 |
+
"loss": 1.2217,
|
156 |
+
"step": 100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.19644527595884004,
|
160 |
+
"grad_norm": 0.2595557434588695,
|
161 |
+
"learning_rate": 9.72403023233439e-06,
|
162 |
+
"loss": 1.2122,
|
163 |
+
"step": 105
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.205799812909261,
|
167 |
+
"grad_norm": 0.2099058809011832,
|
168 |
+
"learning_rate": 9.667902132486009e-06,
|
169 |
+
"loss": 1.1948,
|
170 |
+
"step": 110
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.21515434985968196,
|
174 |
+
"grad_norm": 0.20126316643616676,
|
175 |
+
"learning_rate": 9.606775526115963e-06,
|
176 |
+
"loss": 1.1774,
|
177 |
+
"step": 115
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.2245088868101029,
|
181 |
+
"grad_norm": 0.17345905255518454,
|
182 |
+
"learning_rate": 9.540715869125407e-06,
|
183 |
+
"loss": 1.1681,
|
184 |
+
"step": 120
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.23386342376052385,
|
188 |
+
"grad_norm": 0.25572107838360714,
|
189 |
+
"learning_rate": 9.469793899849663e-06,
|
190 |
+
"loss": 1.1716,
|
191 |
+
"step": 125
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.2432179607109448,
|
195 |
+
"grad_norm": 0.15018874182675532,
|
196 |
+
"learning_rate": 9.394085563309827e-06,
|
197 |
+
"loss": 1.1569,
|
198 |
+
"step": 130
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.25257249766136575,
|
202 |
+
"grad_norm": 0.15353642479045185,
|
203 |
+
"learning_rate": 9.31367192988896e-06,
|
204 |
+
"loss": 1.148,
|
205 |
+
"step": 135
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.26192703461178674,
|
209 |
+
"grad_norm": 0.16296485857684445,
|
210 |
+
"learning_rate": 9.228639108519867e-06,
|
211 |
+
"loss": 1.1504,
|
212 |
+
"step": 140
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.27128157156220767,
|
216 |
+
"grad_norm": 0.14482935533275312,
|
217 |
+
"learning_rate": 9.139078154477512e-06,
|
218 |
+
"loss": 1.1423,
|
219 |
+
"step": 145
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.2806361085126286,
|
223 |
+
"grad_norm": 0.1566349158870611,
|
224 |
+
"learning_rate": 9.045084971874738e-06,
|
225 |
+
"loss": 1.137,
|
226 |
+
"step": 150
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.2899906454630496,
|
230 |
+
"grad_norm": 0.14554164847096335,
|
231 |
+
"learning_rate": 8.94676021096575e-06,
|
232 |
+
"loss": 1.1363,
|
233 |
+
"step": 155
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.2993451824134705,
|
237 |
+
"grad_norm": 0.1508011037252777,
|
238 |
+
"learning_rate": 8.844209160367298e-06,
|
239 |
+
"loss": 1.1304,
|
240 |
+
"step": 160
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.3086997193638915,
|
244 |
+
"grad_norm": 0.14045125665102134,
|
245 |
+
"learning_rate": 8.737541634312985e-06,
|
246 |
+
"loss": 1.1332,
|
247 |
+
"step": 165
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.31805425631431244,
|
251 |
+
"grad_norm": 0.14175186310915225,
|
252 |
+
"learning_rate": 8.626871855061438e-06,
|
253 |
+
"loss": 1.1341,
|
254 |
+
"step": 170
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.3274087932647334,
|
258 |
+
"grad_norm": 0.14507855935792988,
|
259 |
+
"learning_rate": 8.51231833058426e-06,
|
260 |
+
"loss": 1.1302,
|
261 |
+
"step": 175
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.33676333021515437,
|
265 |
+
"grad_norm": 0.1444068343697475,
|
266 |
+
"learning_rate": 8.39400372766471e-06,
|
267 |
+
"loss": 1.1333,
|
268 |
+
"step": 180
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.3461178671655753,
|
272 |
+
"grad_norm": 0.14780446060701052,
|
273 |
+
"learning_rate": 8.272054740543053e-06,
|
274 |
+
"loss": 1.1324,
|
275 |
+
"step": 185
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.35547240411599623,
|
279 |
+
"grad_norm": 0.14569418896265066,
|
280 |
+
"learning_rate": 8.146601955249187e-06,
|
281 |
+
"loss": 1.1173,
|
282 |
+
"step": 190
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.3648269410664172,
|
286 |
+
"grad_norm": 0.14203531449915593,
|
287 |
+
"learning_rate": 8.017779709767857e-06,
|
288 |
+
"loss": 1.115,
|
289 |
+
"step": 195
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.37418147801683815,
|
293 |
+
"grad_norm": 0.13692219577509893,
|
294 |
+
"learning_rate": 7.88572595018617e-06,
|
295 |
+
"loss": 1.1135,
|
296 |
+
"step": 200
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.38353601496725914,
|
300 |
+
"grad_norm": 0.14078263930837534,
|
301 |
+
"learning_rate": 7.750582082977468e-06,
|
302 |
+
"loss": 1.1159,
|
303 |
+
"step": 205
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.3928905519176801,
|
307 |
+
"grad_norm": 0.15520280646196877,
|
308 |
+
"learning_rate": 7.612492823579744e-06,
|
309 |
+
"loss": 1.1162,
|
310 |
+
"step": 210
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.402245088868101,
|
314 |
+
"grad_norm": 0.14752002744879342,
|
315 |
+
"learning_rate": 7.471606041430724e-06,
|
316 |
+
"loss": 1.1131,
|
317 |
+
"step": 215
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.411599625818522,
|
321 |
+
"grad_norm": 0.1509280644564414,
|
322 |
+
"learning_rate": 7.328072601625558e-06,
|
323 |
+
"loss": 1.1118,
|
324 |
+
"step": 220
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.42095416276894293,
|
328 |
+
"grad_norm": 0.1616348908118278,
|
329 |
+
"learning_rate": 7.18204620336671e-06,
|
330 |
+
"loss": 1.1044,
|
331 |
+
"step": 225
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.4303086997193639,
|
335 |
+
"grad_norm": 0.16062290714439983,
|
336 |
+
"learning_rate": 7.033683215379002e-06,
|
337 |
+
"loss": 1.1049,
|
338 |
+
"step": 230
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.43966323666978485,
|
342 |
+
"grad_norm": 0.14900564691058804,
|
343 |
+
"learning_rate": 6.883142508466054e-06,
|
344 |
+
"loss": 1.1072,
|
345 |
+
"step": 235
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.4490177736202058,
|
349 |
+
"grad_norm": 0.14583649841999052,
|
350 |
+
"learning_rate": 6.730585285387465e-06,
|
351 |
+
"loss": 1.1062,
|
352 |
+
"step": 240
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.4583723105706268,
|
356 |
+
"grad_norm": 0.15656333466816236,
|
357 |
+
"learning_rate": 6.57617490823885e-06,
|
358 |
+
"loss": 1.1038,
|
359 |
+
"step": 245
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.4677268475210477,
|
363 |
+
"grad_norm": 0.16642188631242563,
|
364 |
+
"learning_rate": 6.420076723519615e-06,
|
365 |
+
"loss": 1.112,
|
366 |
+
"step": 250
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.47708138447146864,
|
370 |
+
"grad_norm": 0.266837548538648,
|
371 |
+
"learning_rate": 6.26245788507579e-06,
|
372 |
+
"loss": 1.1104,
|
373 |
+
"step": 255
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.4864359214218896,
|
377 |
+
"grad_norm": 0.15891960204556085,
|
378 |
+
"learning_rate": 6.103487175107508e-06,
|
379 |
+
"loss": 1.1013,
|
380 |
+
"step": 260
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.49579045837231056,
|
384 |
+
"grad_norm": 0.15199420768584646,
|
385 |
+
"learning_rate": 5.943334823432777e-06,
|
386 |
+
"loss": 1.0965,
|
387 |
+
"step": 265
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.5051449953227315,
|
391 |
+
"grad_norm": 0.1649301263523591,
|
392 |
+
"learning_rate": 5.782172325201155e-06,
|
393 |
+
"loss": 1.1015,
|
394 |
+
"step": 270
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.5144995322731525,
|
398 |
+
"grad_norm": 0.17068364714449247,
|
399 |
+
"learning_rate": 5.620172257252427e-06,
|
400 |
+
"loss": 1.1048,
|
401 |
+
"step": 275
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.5238540692235735,
|
405 |
+
"grad_norm": 0.1560964872722369,
|
406 |
+
"learning_rate": 5.457508093317013e-06,
|
407 |
+
"loss": 1.1048,
|
408 |
+
"step": 280
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.5332086061739943,
|
412 |
+
"grad_norm": 0.15004408686462048,
|
413 |
+
"learning_rate": 5.294354018255945e-06,
|
414 |
+
"loss": 1.1001,
|
415 |
+
"step": 285
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.5425631431244153,
|
419 |
+
"grad_norm": 0.1563742845945151,
|
420 |
+
"learning_rate": 5.130884741539367e-06,
|
421 |
+
"loss": 1.0959,
|
422 |
+
"step": 290
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.5519176800748363,
|
426 |
+
"grad_norm": 0.15549310467355393,
|
427 |
+
"learning_rate": 4.967275310163241e-06,
|
428 |
+
"loss": 1.097,
|
429 |
+
"step": 295
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.5612722170252572,
|
433 |
+
"grad_norm": 0.17033773254724513,
|
434 |
+
"learning_rate": 4.803700921204659e-06,
|
435 |
+
"loss": 1.0991,
|
436 |
+
"step": 300
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.5706267539756782,
|
440 |
+
"grad_norm": 0.16793233585056505,
|
441 |
+
"learning_rate": 4.640336734216403e-06,
|
442 |
+
"loss": 1.1011,
|
443 |
+
"step": 305
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.5799812909260992,
|
447 |
+
"grad_norm": 0.15858153553414958,
|
448 |
+
"learning_rate": 4.477357683661734e-06,
|
449 |
+
"loss": 1.0953,
|
450 |
+
"step": 310
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.5893358278765201,
|
454 |
+
"grad_norm": 0.18459161802082374,
|
455 |
+
"learning_rate": 4.314938291590161e-06,
|
456 |
+
"loss": 1.0905,
|
457 |
+
"step": 315
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.598690364826941,
|
461 |
+
"grad_norm": 0.16567092468891204,
|
462 |
+
"learning_rate": 4.1532524807548776e-06,
|
463 |
+
"loss": 1.0906,
|
464 |
+
"step": 320
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.608044901777362,
|
468 |
+
"grad_norm": 0.16035972271379115,
|
469 |
+
"learning_rate": 3.992473388371914e-06,
|
470 |
+
"loss": 1.0924,
|
471 |
+
"step": 325
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.617399438727783,
|
475 |
+
"grad_norm": 0.18108290101376773,
|
476 |
+
"learning_rate": 3.832773180720475e-06,
|
477 |
+
"loss": 1.092,
|
478 |
+
"step": 330
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.6267539756782039,
|
482 |
+
"grad_norm": 0.16657617125834437,
|
483 |
+
"learning_rate": 3.6743228687829596e-06,
|
484 |
+
"loss": 1.0887,
|
485 |
+
"step": 335
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.6361085126286249,
|
489 |
+
"grad_norm": 0.1783833220121851,
|
490 |
+
"learning_rate": 3.517292125122146e-06,
|
491 |
+
"loss": 1.0938,
|
492 |
+
"step": 340
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.6454630495790459,
|
496 |
+
"grad_norm": 0.15395137633162537,
|
497 |
+
"learning_rate": 3.3618491021915334e-06,
|
498 |
+
"loss": 1.0902,
|
499 |
+
"step": 345
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.6548175865294668,
|
503 |
+
"grad_norm": 0.16256299187537024,
|
504 |
+
"learning_rate": 3.2081602522734987e-06,
|
505 |
+
"loss": 1.0875,
|
506 |
+
"step": 350
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.6641721234798877,
|
510 |
+
"grad_norm": 0.15781917797031997,
|
511 |
+
"learning_rate": 3.056390149238022e-06,
|
512 |
+
"loss": 1.0897,
|
513 |
+
"step": 355
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.6735266604303087,
|
517 |
+
"grad_norm": 0.15450725652248593,
|
518 |
+
"learning_rate": 2.906701312312861e-06,
|
519 |
+
"loss": 1.0883,
|
520 |
+
"step": 360
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.6828811973807296,
|
524 |
+
"grad_norm": 0.16092272691343973,
|
525 |
+
"learning_rate": 2.759254032053888e-06,
|
526 |
+
"loss": 1.0908,
|
527 |
+
"step": 365
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.6922357343311506,
|
531 |
+
"grad_norm": 0.15881876352311045,
|
532 |
+
"learning_rate": 2.614206198701958e-06,
|
533 |
+
"loss": 1.0964,
|
534 |
+
"step": 370
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.7015902712815716,
|
538 |
+
"grad_norm": 0.16123816798728421,
|
539 |
+
"learning_rate": 2.471713133110078e-06,
|
540 |
+
"loss": 1.0826,
|
541 |
+
"step": 375
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.7109448082319925,
|
545 |
+
"grad_norm": 0.17326937796971717,
|
546 |
+
"learning_rate": 2.3319274204219427e-06,
|
547 |
+
"loss": 1.0857,
|
548 |
+
"step": 380
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.7202993451824135,
|
552 |
+
"grad_norm": 0.15824306754559836,
|
553 |
+
"learning_rate": 2.1949987466799524e-06,
|
554 |
+
"loss": 1.0926,
|
555 |
+
"step": 385
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.7296538821328344,
|
559 |
+
"grad_norm": 0.15676499958123513,
|
560 |
+
"learning_rate": 2.061073738537635e-06,
|
561 |
+
"loss": 1.091,
|
562 |
+
"step": 390
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.7390084190832554,
|
566 |
+
"grad_norm": 0.15899394910820866,
|
567 |
+
"learning_rate": 1.9302958062481673e-06,
|
568 |
+
"loss": 1.0845,
|
569 |
+
"step": 395
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.7483629560336763,
|
573 |
+
"grad_norm": 0.16579475502144433,
|
574 |
+
"learning_rate": 1.8028049900970768e-06,
|
575 |
+
"loss": 1.0854,
|
576 |
+
"step": 400
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.7577174929840973,
|
580 |
+
"grad_norm": 0.15812690411171398,
|
581 |
+
"learning_rate": 1.6787378104435931e-06,
|
582 |
+
"loss": 1.0867,
|
583 |
+
"step": 405
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.7670720299345183,
|
587 |
+
"grad_norm": 0.1562749678781465,
|
588 |
+
"learning_rate": 1.5582271215312294e-06,
|
589 |
+
"loss": 1.0869,
|
590 |
+
"step": 410
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.7764265668849392,
|
594 |
+
"grad_norm": 0.1573904723461426,
|
595 |
+
"learning_rate": 1.4414019692241437e-06,
|
596 |
+
"loss": 1.0968,
|
597 |
+
"step": 415
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.7857811038353602,
|
601 |
+
"grad_norm": 0.1663255000536237,
|
602 |
+
"learning_rate": 1.3283874528215735e-06,
|
603 |
+
"loss": 1.0896,
|
604 |
+
"step": 420
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.7951356407857811,
|
608 |
+
"grad_norm": 0.1565901532094871,
|
609 |
+
"learning_rate": 1.2193045910983864e-06,
|
610 |
+
"loss": 1.0892,
|
611 |
+
"step": 425
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.804490177736202,
|
615 |
+
"grad_norm": 0.15886041285660657,
|
616 |
+
"learning_rate": 1.1142701927151456e-06,
|
617 |
+
"loss": 1.086,
|
618 |
+
"step": 430
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.813844714686623,
|
622 |
+
"grad_norm": 0.1653805801993096,
|
623 |
+
"learning_rate": 1.013396731136465e-06,
|
624 |
+
"loss": 1.0846,
|
625 |
+
"step": 435
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.823199251637044,
|
629 |
+
"grad_norm": 0.1659489588893349,
|
630 |
+
"learning_rate": 9.167922241916055e-07,
|
631 |
+
"loss": 1.0882,
|
632 |
+
"step": 440
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.8325537885874649,
|
636 |
+
"grad_norm": 0.14935331942375346,
|
637 |
+
"learning_rate": 8.245601184062851e-07,
|
638 |
+
"loss": 1.0919,
|
639 |
+
"step": 445
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.8419083255378859,
|
643 |
+
"grad_norm": 0.1612238398597313,
|
644 |
+
"learning_rate": 7.367991782295392e-07,
|
645 |
+
"loss": 1.0956,
|
646 |
+
"step": 450
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.8512628624883068,
|
650 |
+
"grad_norm": 0.16096449999893725,
|
651 |
+
"learning_rate": 6.536033802742814e-07,
|
652 |
+
"loss": 1.0892,
|
653 |
+
"step": 455
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.8606173994387278,
|
657 |
+
"grad_norm": 0.18591172254707147,
|
658 |
+
"learning_rate": 5.750618126847912e-07,
|
659 |
+
"loss": 1.0814,
|
660 |
+
"step": 460
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.8699719363891487,
|
664 |
+
"grad_norm": 0.16230740670761631,
|
665 |
+
"learning_rate": 5.012585797388936e-07,
|
666 |
+
"loss": 1.0863,
|
667 |
+
"step": 465
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.8793264733395697,
|
671 |
+
"grad_norm": 0.16399177374939766,
|
672 |
+
"learning_rate": 4.322727117869951e-07,
|
673 |
+
"loss": 1.0836,
|
674 |
+
"step": 470
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.8886810102899907,
|
678 |
+
"grad_norm": 0.19550575898363698,
|
679 |
+
"learning_rate": 3.6817808062440953e-07,
|
680 |
+
"loss": 1.091,
|
681 |
+
"step": 475
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.8980355472404116,
|
685 |
+
"grad_norm": 0.15359012389254986,
|
686 |
+
"learning_rate": 3.0904332038757977e-07,
|
687 |
+
"loss": 1.0937,
|
688 |
+
"step": 480
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.9073900841908326,
|
692 |
+
"grad_norm": 0.1606805442454799,
|
693 |
+
"learning_rate": 2.5493175405893076e-07,
|
694 |
+
"loss": 1.0848,
|
695 |
+
"step": 485
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.9167446211412535,
|
699 |
+
"grad_norm": 0.16036880753390018,
|
700 |
+
"learning_rate": 2.0590132565903475e-07,
|
701 |
+
"loss": 1.0904,
|
702 |
+
"step": 490
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.9260991580916744,
|
706 |
+
"grad_norm": 0.16046720313774515,
|
707 |
+
"learning_rate": 1.6200453819870122e-07,
|
708 |
+
"loss": 1.0839,
|
709 |
+
"step": 495
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.9354536950420954,
|
713 |
+
"grad_norm": 0.16013022562616708,
|
714 |
+
"learning_rate": 1.232883974574367e-07,
|
715 |
+
"loss": 1.0876,
|
716 |
+
"step": 500
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.9448082319925164,
|
720 |
+
"grad_norm": 0.1680369869804664,
|
721 |
+
"learning_rate": 8.979436164848088e-08,
|
722 |
+
"loss": 1.0854,
|
723 |
+
"step": 505
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.9541627689429373,
|
727 |
+
"grad_norm": 0.1538401535295636,
|
728 |
+
"learning_rate": 6.15582970243117e-08,
|
729 |
+
"loss": 1.0904,
|
730 |
+
"step": 510
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.9635173058933583,
|
734 |
+
"grad_norm": 0.1590652953665931,
|
735 |
+
"learning_rate": 3.861043947016474e-08,
|
736 |
+
"loss": 1.0783,
|
737 |
+
"step": 515
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.9728718428437793,
|
741 |
+
"grad_norm": 0.15600780093245614,
|
742 |
+
"learning_rate": 2.097536212669171e-08,
|
743 |
+
"loss": 1.0857,
|
744 |
+
"step": 520
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.9822263797942001,
|
748 |
+
"grad_norm": 0.1590897713521175,
|
749 |
+
"learning_rate": 8.671949076420883e-09,
|
750 |
+
"loss": 1.0859,
|
751 |
+
"step": 525
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.9915809167446211,
|
755 |
+
"grad_norm": 0.15861216238412335,
|
756 |
+
"learning_rate": 1.7133751222137007e-09,
|
757 |
+
"loss": 1.0845,
|
758 |
+
"step": 530
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.9990645463049579,
|
762 |
+
"eval_runtime": 3.2564,
|
763 |
+
"eval_samples_per_second": 3.071,
|
764 |
+
"eval_steps_per_second": 0.921,
|
765 |
+
"step": 534
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.9990645463049579,
|
769 |
+
"step": 534,
|
770 |
+
"total_flos": 2.2276586722453094e+17,
|
771 |
+
"train_loss": 1.1599709373734863,
|
772 |
+
"train_runtime": 17757.3527,
|
773 |
+
"train_samples_per_second": 1.925,
|
774 |
+
"train_steps_per_second": 0.03
|
775 |
+
}
|
776 |
+
],
|
777 |
+
"logging_steps": 5,
|
778 |
+
"max_steps": 534,
|
779 |
+
"num_input_tokens_seen": 0,
|
780 |
+
"num_train_epochs": 1,
|
781 |
+
"save_steps": 100,
|
782 |
+
"stateful_callbacks": {
|
783 |
+
"TrainerControl": {
|
784 |
+
"args": {
|
785 |
+
"should_epoch_stop": false,
|
786 |
+
"should_evaluate": false,
|
787 |
+
"should_log": false,
|
788 |
+
"should_save": true,
|
789 |
+
"should_training_stop": true
|
790 |
+
},
|
791 |
+
"attributes": {}
|
792 |
+
}
|
793 |
+
},
|
794 |
+
"total_flos": 2.2276586722453094e+17,
|
795 |
+
"train_batch_size": 8,
|
796 |
+
"trial_name": null,
|
797 |
+
"trial_params": null
|
798 |
+
}
|