Model save
Browse files- README.md +69 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +1011 -0
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-Instruct
|
9 |
+
model-index:
|
10 |
+
- name: Meta-Llama-3-8B-Instruct-nomiracl-sft
|
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 |
+
# Meta-Llama-3-8B-Instruct-nomiracl-sft
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.6358
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 1e-05
|
41 |
+
- train_batch_size: 4
|
42 |
+
- eval_batch_size: 4
|
43 |
+
- seed: 42
|
44 |
+
- distributed_type: multi-GPU
|
45 |
+
- num_devices: 4
|
46 |
+
- gradient_accumulation_steps: 2
|
47 |
+
- total_train_batch_size: 32
|
48 |
+
- total_eval_batch_size: 16
|
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
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
+
|:-------------:|:------:|:----:|:---------------:|
|
58 |
+
| 1.6576 | 0.2981 | 200 | 1.6656 |
|
59 |
+
| 1.6447 | 0.5961 | 400 | 1.6409 |
|
60 |
+
| 1.6245 | 0.8942 | 600 | 1.6358 |
|
61 |
+
|
62 |
+
|
63 |
+
### Framework versions
|
64 |
+
|
65 |
+
- PEFT 0.7.1
|
66 |
+
- Transformers 4.41.2
|
67 |
+
- Pytorch 2.3.0+cu121
|
68 |
+
- Datasets 2.20.0
|
69 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 919616052789248.0,
|
4 |
+
"train_loss": 1.6831368206154926,
|
5 |
+
"train_runtime": 18035.2779,
|
6 |
+
"train_samples": 21471,
|
7 |
+
"train_samples_per_second": 1.191,
|
8 |
+
"train_steps_per_second": 0.037
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 919616052789248.0,
|
4 |
+
"train_loss": 1.6831368206154926,
|
5 |
+
"train_runtime": 18035.2779,
|
6 |
+
"train_samples": 21471,
|
7 |
+
"train_samples_per_second": 1.191,
|
8 |
+
"train_steps_per_second": 0.037
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1011 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.6357628107070923,
|
3 |
+
"best_model_checkpoint": "/mnt/users/n3thakur/research_new/miracl-unanswerable/models/Meta-Llama-3-8B-Instruct-nomiracl-sft/checkpoint-600",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 200,
|
6 |
+
"global_step": 671,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0014903129657228018,
|
13 |
+
"grad_norm": 1.2864242608707517,
|
14 |
+
"learning_rate": 1.4705882352941178e-07,
|
15 |
+
"loss": 1.9819,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.007451564828614009,
|
20 |
+
"grad_norm": 1.3601881935430797,
|
21 |
+
"learning_rate": 7.352941176470589e-07,
|
22 |
+
"loss": 2.0209,
|
23 |
+
"step": 5
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.014903129657228018,
|
27 |
+
"grad_norm": 1.308324783880395,
|
28 |
+
"learning_rate": 1.4705882352941177e-06,
|
29 |
+
"loss": 2.0789,
|
30 |
+
"step": 10
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.022354694485842028,
|
34 |
+
"grad_norm": 1.3402040033505984,
|
35 |
+
"learning_rate": 2.2058823529411767e-06,
|
36 |
+
"loss": 2.1346,
|
37 |
+
"step": 15
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.029806259314456036,
|
41 |
+
"grad_norm": 1.252511058906224,
|
42 |
+
"learning_rate": 2.9411764705882355e-06,
|
43 |
+
"loss": 1.9887,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.037257824143070044,
|
48 |
+
"grad_norm": 1.1571538128626155,
|
49 |
+
"learning_rate": 3.6764705882352946e-06,
|
50 |
+
"loss": 1.9678,
|
51 |
+
"step": 25
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.044709388971684055,
|
55 |
+
"grad_norm": 0.9688203213594095,
|
56 |
+
"learning_rate": 4.411764705882353e-06,
|
57 |
+
"loss": 1.9569,
|
58 |
+
"step": 30
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.05216095380029806,
|
62 |
+
"grad_norm": 0.9113616550249095,
|
63 |
+
"learning_rate": 5.147058823529411e-06,
|
64 |
+
"loss": 1.9236,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.05961251862891207,
|
69 |
+
"grad_norm": 0.8080169675485035,
|
70 |
+
"learning_rate": 5.882352941176471e-06,
|
71 |
+
"loss": 1.9358,
|
72 |
+
"step": 40
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.06706408345752608,
|
76 |
+
"grad_norm": 0.6008229695631025,
|
77 |
+
"learning_rate": 6.61764705882353e-06,
|
78 |
+
"loss": 1.8434,
|
79 |
+
"step": 45
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.07451564828614009,
|
83 |
+
"grad_norm": 0.5413811186895102,
|
84 |
+
"learning_rate": 7.352941176470589e-06,
|
85 |
+
"loss": 1.8786,
|
86 |
+
"step": 50
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.08196721311475409,
|
90 |
+
"grad_norm": 0.4866905959375867,
|
91 |
+
"learning_rate": 8.088235294117648e-06,
|
92 |
+
"loss": 1.7887,
|
93 |
+
"step": 55
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.08941877794336811,
|
97 |
+
"grad_norm": 0.3991956099552151,
|
98 |
+
"learning_rate": 8.823529411764707e-06,
|
99 |
+
"loss": 1.8388,
|
100 |
+
"step": 60
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.09687034277198212,
|
104 |
+
"grad_norm": 0.4089753043909763,
|
105 |
+
"learning_rate": 9.558823529411766e-06,
|
106 |
+
"loss": 1.7719,
|
107 |
+
"step": 65
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.10432190760059612,
|
111 |
+
"grad_norm": 0.3567858319466126,
|
112 |
+
"learning_rate": 9.999728567909404e-06,
|
113 |
+
"loss": 1.7757,
|
114 |
+
"step": 70
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.11177347242921014,
|
118 |
+
"grad_norm": 0.3733731735267369,
|
119 |
+
"learning_rate": 9.996675295326345e-06,
|
120 |
+
"loss": 1.7357,
|
121 |
+
"step": 75
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.11922503725782414,
|
125 |
+
"grad_norm": 0.4120045550242149,
|
126 |
+
"learning_rate": 9.99023153874608e-06,
|
127 |
+
"loss": 1.76,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.12667660208643816,
|
132 |
+
"grad_norm": 0.47838141094777215,
|
133 |
+
"learning_rate": 9.980401670566705e-06,
|
134 |
+
"loss": 1.8124,
|
135 |
+
"step": 85
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.13412816691505217,
|
139 |
+
"grad_norm": 0.34098601847525956,
|
140 |
+
"learning_rate": 9.967192360825558e-06,
|
141 |
+
"loss": 1.7454,
|
142 |
+
"step": 90
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.14157973174366617,
|
146 |
+
"grad_norm": 0.3091360382279767,
|
147 |
+
"learning_rate": 9.950612572673255e-06,
|
148 |
+
"loss": 1.7528,
|
149 |
+
"step": 95
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.14903129657228018,
|
153 |
+
"grad_norm": 0.2937982462814676,
|
154 |
+
"learning_rate": 9.930673556291789e-06,
|
155 |
+
"loss": 1.6999,
|
156 |
+
"step": 100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.15648286140089418,
|
160 |
+
"grad_norm": 0.3033053874366656,
|
161 |
+
"learning_rate": 9.907388841260723e-06,
|
162 |
+
"loss": 1.6328,
|
163 |
+
"step": 105
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.16393442622950818,
|
167 |
+
"grad_norm": 0.3147533435412934,
|
168 |
+
"learning_rate": 9.880774227376727e-06,
|
169 |
+
"loss": 1.7202,
|
170 |
+
"step": 110
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.17138599105812222,
|
174 |
+
"grad_norm": 0.30138135147702194,
|
175 |
+
"learning_rate": 9.850847773932656e-06,
|
176 |
+
"loss": 1.7147,
|
177 |
+
"step": 115
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.17883755588673622,
|
181 |
+
"grad_norm": 0.2821814099944737,
|
182 |
+
"learning_rate": 9.817629787463456e-06,
|
183 |
+
"loss": 1.7141,
|
184 |
+
"step": 120
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.18628912071535023,
|
188 |
+
"grad_norm": 0.278421347158755,
|
189 |
+
"learning_rate": 9.781142807967205e-06,
|
190 |
+
"loss": 1.7812,
|
191 |
+
"step": 125
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.19374068554396423,
|
195 |
+
"grad_norm": 0.2745120712204819,
|
196 |
+
"learning_rate": 9.741411593610635e-06,
|
197 |
+
"loss": 1.6429,
|
198 |
+
"step": 130
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.20119225037257824,
|
202 |
+
"grad_norm": 0.2915048113702178,
|
203 |
+
"learning_rate": 9.698463103929542e-06,
|
204 |
+
"loss": 1.6622,
|
205 |
+
"step": 135
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.20864381520119224,
|
209 |
+
"grad_norm": 0.29052352322277714,
|
210 |
+
"learning_rate": 9.652326481535434e-06,
|
211 |
+
"loss": 1.7323,
|
212 |
+
"step": 140
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.21609538002980627,
|
216 |
+
"grad_norm": 0.30795018674862495,
|
217 |
+
"learning_rate": 9.603033032340875e-06,
|
218 |
+
"loss": 1.7064,
|
219 |
+
"step": 145
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.22354694485842028,
|
223 |
+
"grad_norm": 0.27173782182479533,
|
224 |
+
"learning_rate": 9.550616204316922e-06,
|
225 |
+
"loss": 1.7384,
|
226 |
+
"step": 150
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.23099850968703428,
|
230 |
+
"grad_norm": 0.3106086974094058,
|
231 |
+
"learning_rate": 9.495111564797073e-06,
|
232 |
+
"loss": 1.7267,
|
233 |
+
"step": 155
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.23845007451564829,
|
237 |
+
"grad_norm": 0.3021509489363488,
|
238 |
+
"learning_rate": 9.43655677634312e-06,
|
239 |
+
"loss": 1.6479,
|
240 |
+
"step": 160
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.2459016393442623,
|
244 |
+
"grad_norm": 0.29504453527495433,
|
245 |
+
"learning_rate": 9.374991571189292e-06,
|
246 |
+
"loss": 1.6919,
|
247 |
+
"step": 165
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.2533532041728763,
|
251 |
+
"grad_norm": 0.3337725680370752,
|
252 |
+
"learning_rate": 9.310457724282034e-06,
|
253 |
+
"loss": 1.7475,
|
254 |
+
"step": 170
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.2608047690014903,
|
258 |
+
"grad_norm": 0.271616871396071,
|
259 |
+
"learning_rate": 9.242999024933694e-06,
|
260 |
+
"loss": 1.6249,
|
261 |
+
"step": 175
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.26825633383010433,
|
265 |
+
"grad_norm": 0.27469314451092647,
|
266 |
+
"learning_rate": 9.172661247109382e-06,
|
267 |
+
"loss": 1.6289,
|
268 |
+
"step": 180
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.2757078986587183,
|
272 |
+
"grad_norm": 0.32247904554795664,
|
273 |
+
"learning_rate": 9.099492118367123e-06,
|
274 |
+
"loss": 1.6759,
|
275 |
+
"step": 185
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.28315946348733234,
|
279 |
+
"grad_norm": 0.32346400909431516,
|
280 |
+
"learning_rate": 9.023541287472435e-06,
|
281 |
+
"loss": 1.7517,
|
282 |
+
"step": 190
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.2906110283159464,
|
286 |
+
"grad_norm": 0.28010968189921137,
|
287 |
+
"learning_rate": 8.944860290709245e-06,
|
288 |
+
"loss": 1.6495,
|
289 |
+
"step": 195
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.29806259314456035,
|
293 |
+
"grad_norm": 0.3073056244750479,
|
294 |
+
"learning_rate": 8.863502516910058e-06,
|
295 |
+
"loss": 1.6576,
|
296 |
+
"step": 200
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.29806259314456035,
|
300 |
+
"eval_loss": 1.6655718088150024,
|
301 |
+
"eval_runtime": 581.6685,
|
302 |
+
"eval_samples_per_second": 4.102,
|
303 |
+
"eval_steps_per_second": 0.258,
|
304 |
+
"step": 200
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.3055141579731744,
|
308 |
+
"grad_norm": 0.2982943497092564,
|
309 |
+
"learning_rate": 8.779523171229061e-06,
|
310 |
+
"loss": 1.6927,
|
311 |
+
"step": 205
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.31296572280178836,
|
315 |
+
"grad_norm": 0.3097195272484475,
|
316 |
+
"learning_rate": 8.692979237682785e-06,
|
317 |
+
"loss": 1.6619,
|
318 |
+
"step": 210
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.3204172876304024,
|
322 |
+
"grad_norm": 0.34367552210427565,
|
323 |
+
"learning_rate": 8.603929440483714e-06,
|
324 |
+
"loss": 1.684,
|
325 |
+
"step": 215
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.32786885245901637,
|
329 |
+
"grad_norm": 0.3023959348087803,
|
330 |
+
"learning_rate": 8.51243420419308e-06,
|
331 |
+
"loss": 1.5742,
|
332 |
+
"step": 220
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.3353204172876304,
|
336 |
+
"grad_norm": 0.2908694884413669,
|
337 |
+
"learning_rate": 8.418555612719912e-06,
|
338 |
+
"loss": 1.6211,
|
339 |
+
"step": 225
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.34277198211624443,
|
343 |
+
"grad_norm": 0.3265065297068578,
|
344 |
+
"learning_rate": 8.32235736719411e-06,
|
345 |
+
"loss": 1.6614,
|
346 |
+
"step": 230
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.3502235469448584,
|
350 |
+
"grad_norm": 0.29528676002450155,
|
351 |
+
"learning_rate": 8.223904742742182e-06,
|
352 |
+
"loss": 1.6757,
|
353 |
+
"step": 235
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.35767511177347244,
|
357 |
+
"grad_norm": 0.30070470151226314,
|
358 |
+
"learning_rate": 8.123264544194934e-06,
|
359 |
+
"loss": 1.6443,
|
360 |
+
"step": 240
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.3651266766020864,
|
364 |
+
"grad_norm": 0.3090720148911324,
|
365 |
+
"learning_rate": 8.02050506075718e-06,
|
366 |
+
"loss": 1.6689,
|
367 |
+
"step": 245
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.37257824143070045,
|
371 |
+
"grad_norm": 0.29743017001679256,
|
372 |
+
"learning_rate": 7.91569601967025e-06,
|
373 |
+
"loss": 1.6278,
|
374 |
+
"step": 250
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.38002980625931443,
|
378 |
+
"grad_norm": 0.297851200782397,
|
379 |
+
"learning_rate": 7.808908538898703e-06,
|
380 |
+
"loss": 1.6155,
|
381 |
+
"step": 255
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.38748137108792846,
|
385 |
+
"grad_norm": 0.3435439482120138,
|
386 |
+
"learning_rate": 7.70021507887338e-06,
|
387 |
+
"loss": 1.5611,
|
388 |
+
"step": 260
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.3949329359165425,
|
392 |
+
"grad_norm": 0.32733272749783104,
|
393 |
+
"learning_rate": 7.5896893933235135e-06,
|
394 |
+
"loss": 1.6055,
|
395 |
+
"step": 265
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.40238450074515647,
|
399 |
+
"grad_norm": 0.3056544624446995,
|
400 |
+
"learning_rate": 7.477406479231299e-06,
|
401 |
+
"loss": 1.678,
|
402 |
+
"step": 270
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.4098360655737705,
|
406 |
+
"grad_norm": 0.31368790810083264,
|
407 |
+
"learning_rate": 7.363442525942827e-06,
|
408 |
+
"loss": 1.5912,
|
409 |
+
"step": 275
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.4172876304023845,
|
413 |
+
"grad_norm": 0.2993808857251287,
|
414 |
+
"learning_rate": 7.247874863469964e-06,
|
415 |
+
"loss": 1.6412,
|
416 |
+
"step": 280
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.4247391952309985,
|
420 |
+
"grad_norm": 0.32056752037833786,
|
421 |
+
"learning_rate": 7.1307819100182275e-06,
|
422 |
+
"loss": 1.6949,
|
423 |
+
"step": 285
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.43219076005961254,
|
427 |
+
"grad_norm": 0.3361900057942298,
|
428 |
+
"learning_rate": 7.01224311877627e-06,
|
429 |
+
"loss": 1.6513,
|
430 |
+
"step": 290
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.4396423248882265,
|
434 |
+
"grad_norm": 0.3373143541448011,
|
435 |
+
"learning_rate": 6.892338924003068e-06,
|
436 |
+
"loss": 1.6699,
|
437 |
+
"step": 295
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.44709388971684055,
|
441 |
+
"grad_norm": 0.30913581638324406,
|
442 |
+
"learning_rate": 6.771150686449436e-06,
|
443 |
+
"loss": 1.5889,
|
444 |
+
"step": 300
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.45454545454545453,
|
448 |
+
"grad_norm": 0.3324140439223907,
|
449 |
+
"learning_rate": 6.648760638150833e-06,
|
450 |
+
"loss": 1.6559,
|
451 |
+
"step": 305
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.46199701937406856,
|
455 |
+
"grad_norm": 0.3143801425022107,
|
456 |
+
"learning_rate": 6.525251826628991e-06,
|
457 |
+
"loss": 1.6297,
|
458 |
+
"step": 310
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.46944858420268254,
|
462 |
+
"grad_norm": 0.32690734523122295,
|
463 |
+
"learning_rate": 6.400708058540182e-06,
|
464 |
+
"loss": 1.6407,
|
465 |
+
"step": 315
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.47690014903129657,
|
469 |
+
"grad_norm": 0.31268911619063705,
|
470 |
+
"learning_rate": 6.275213842808383e-06,
|
471 |
+
"loss": 1.6245,
|
472 |
+
"step": 320
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 0.4843517138599106,
|
476 |
+
"grad_norm": 0.36149919350714527,
|
477 |
+
"learning_rate": 6.148854333281905e-06,
|
478 |
+
"loss": 1.6476,
|
479 |
+
"step": 325
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.4918032786885246,
|
483 |
+
"grad_norm": 0.3590585354206088,
|
484 |
+
"learning_rate": 6.021715270952435e-06,
|
485 |
+
"loss": 1.6452,
|
486 |
+
"step": 330
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 0.4992548435171386,
|
490 |
+
"grad_norm": 0.3039096750446457,
|
491 |
+
"learning_rate": 5.893882925775648e-06,
|
492 |
+
"loss": 1.6415,
|
493 |
+
"step": 335
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.5067064083457526,
|
497 |
+
"grad_norm": 0.31141048527235143,
|
498 |
+
"learning_rate": 5.765444038132901e-06,
|
499 |
+
"loss": 1.6571,
|
500 |
+
"step": 340
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.5141579731743666,
|
504 |
+
"grad_norm": 0.3173169163707792,
|
505 |
+
"learning_rate": 5.636485759973729e-06,
|
506 |
+
"loss": 1.5806,
|
507 |
+
"step": 345
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.5216095380029806,
|
511 |
+
"grad_norm": 0.3363924031410881,
|
512 |
+
"learning_rate": 5.507095595679059e-06,
|
513 |
+
"loss": 1.6871,
|
514 |
+
"step": 350
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.5290611028315947,
|
518 |
+
"grad_norm": 0.3307680686760043,
|
519 |
+
"learning_rate": 5.377361342685287e-06,
|
520 |
+
"loss": 1.6933,
|
521 |
+
"step": 355
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.5365126676602087,
|
525 |
+
"grad_norm": 0.32876995727805525,
|
526 |
+
"learning_rate": 5.2473710319095054e-06,
|
527 |
+
"loss": 1.6201,
|
528 |
+
"step": 360
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 0.5439642324888226,
|
532 |
+
"grad_norm": 0.3452442083785589,
|
533 |
+
"learning_rate": 5.117212868016303e-06,
|
534 |
+
"loss": 1.7146,
|
535 |
+
"step": 365
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 0.5514157973174366,
|
539 |
+
"grad_norm": 0.3659924599969553,
|
540 |
+
"learning_rate": 4.9869751695666615e-06,
|
541 |
+
"loss": 1.6215,
|
542 |
+
"step": 370
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.5588673621460507,
|
546 |
+
"grad_norm": 0.3233317882165812,
|
547 |
+
"learning_rate": 4.856746309089582e-06,
|
548 |
+
"loss": 1.6315,
|
549 |
+
"step": 375
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.5663189269746647,
|
553 |
+
"grad_norm": 0.30217314493419994,
|
554 |
+
"learning_rate": 4.726614653117071e-06,
|
555 |
+
"loss": 1.6945,
|
556 |
+
"step": 380
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.5737704918032787,
|
560 |
+
"grad_norm": 0.35844882665530153,
|
561 |
+
"learning_rate": 4.596668502223214e-06,
|
562 |
+
"loss": 1.6924,
|
563 |
+
"step": 385
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.5812220566318927,
|
567 |
+
"grad_norm": 0.34041157047813575,
|
568 |
+
"learning_rate": 4.466996031108004e-06,
|
569 |
+
"loss": 1.629,
|
570 |
+
"step": 390
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.5886736214605067,
|
574 |
+
"grad_norm": 0.314658238073181,
|
575 |
+
"learning_rate": 4.337685228766561e-06,
|
576 |
+
"loss": 1.6797,
|
577 |
+
"step": 395
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 0.5961251862891207,
|
581 |
+
"grad_norm": 0.32647573861445145,
|
582 |
+
"learning_rate": 4.208823838784387e-06,
|
583 |
+
"loss": 1.6447,
|
584 |
+
"step": 400
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.5961251862891207,
|
588 |
+
"eval_loss": 1.6408501863479614,
|
589 |
+
"eval_runtime": 580.0543,
|
590 |
+
"eval_samples_per_second": 4.113,
|
591 |
+
"eval_steps_per_second": 0.259,
|
592 |
+
"step": 400
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.6035767511177347,
|
596 |
+
"grad_norm": 0.37909958848060366,
|
597 |
+
"learning_rate": 4.0804992997991335e-06,
|
598 |
+
"loss": 1.6574,
|
599 |
+
"step": 405
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.6110283159463488,
|
603 |
+
"grad_norm": 0.3790204664396362,
|
604 |
+
"learning_rate": 3.952798686169279e-06,
|
605 |
+
"loss": 1.7235,
|
606 |
+
"step": 410
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.6184798807749627,
|
610 |
+
"grad_norm": 0.3703026855695823,
|
611 |
+
"learning_rate": 3.825808648890005e-06,
|
612 |
+
"loss": 1.675,
|
613 |
+
"step": 415
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.6259314456035767,
|
617 |
+
"grad_norm": 0.3426042362005175,
|
618 |
+
"learning_rate": 3.699615356796342e-06,
|
619 |
+
"loss": 1.5951,
|
620 |
+
"step": 420
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.6333830104321908,
|
624 |
+
"grad_norm": 0.3472991803298781,
|
625 |
+
"learning_rate": 3.5743044380934655e-06,
|
626 |
+
"loss": 1.7072,
|
627 |
+
"step": 425
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.6408345752608048,
|
631 |
+
"grad_norm": 0.3645949602782747,
|
632 |
+
"learning_rate": 3.449960922253858e-06,
|
633 |
+
"loss": 1.6207,
|
634 |
+
"step": 430
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.6482861400894188,
|
638 |
+
"grad_norm": 0.3314569171608062,
|
639 |
+
"learning_rate": 3.326669182320736e-06,
|
640 |
+
"loss": 1.6281,
|
641 |
+
"step": 435
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.6557377049180327,
|
645 |
+
"grad_norm": 0.31811370472714595,
|
646 |
+
"learning_rate": 3.2045128776568783e-06,
|
647 |
+
"loss": 1.6572,
|
648 |
+
"step": 440
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.6631892697466468,
|
652 |
+
"grad_norm": 0.3377222335896338,
|
653 |
+
"learning_rate": 3.0835748971777413e-06,
|
654 |
+
"loss": 1.6651,
|
655 |
+
"step": 445
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.6706408345752608,
|
659 |
+
"grad_norm": 0.331361220355902,
|
660 |
+
"learning_rate": 2.9639373031073525e-06,
|
661 |
+
"loss": 1.6878,
|
662 |
+
"step": 450
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.6780923994038748,
|
666 |
+
"grad_norm": 0.30006578695394276,
|
667 |
+
"learning_rate": 2.8456812752951483e-06,
|
668 |
+
"loss": 1.6887,
|
669 |
+
"step": 455
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.6855439642324889,
|
673 |
+
"grad_norm": 0.34387137915082105,
|
674 |
+
"learning_rate": 2.728887056131553e-06,
|
675 |
+
"loss": 1.6273,
|
676 |
+
"step": 460
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.6929955290611028,
|
680 |
+
"grad_norm": 0.3426777102093575,
|
681 |
+
"learning_rate": 2.6136338960996665e-06,
|
682 |
+
"loss": 1.6867,
|
683 |
+
"step": 465
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.7004470938897168,
|
687 |
+
"grad_norm": 0.3047030104059201,
|
688 |
+
"learning_rate": 2.5000000000000015e-06,
|
689 |
+
"loss": 1.6514,
|
690 |
+
"step": 470
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.7078986587183308,
|
694 |
+
"grad_norm": 0.3194123549278598,
|
695 |
+
"learning_rate": 2.3880624738847837e-06,
|
696 |
+
"loss": 1.6494,
|
697 |
+
"step": 475
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.7153502235469449,
|
701 |
+
"grad_norm": 0.28354706856772705,
|
702 |
+
"learning_rate": 2.277897272737787e-06,
|
703 |
+
"loss": 1.5821,
|
704 |
+
"step": 480
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.7228017883755589,
|
708 |
+
"grad_norm": 0.36693040405683097,
|
709 |
+
"learning_rate": 2.1695791489352346e-06,
|
710 |
+
"loss": 1.6627,
|
711 |
+
"step": 485
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.7302533532041728,
|
715 |
+
"grad_norm": 0.3268289701429299,
|
716 |
+
"learning_rate": 2.063181601522722e-06,
|
717 |
+
"loss": 1.543,
|
718 |
+
"step": 490
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.7377049180327869,
|
722 |
+
"grad_norm": 0.337638547503993,
|
723 |
+
"learning_rate": 1.9587768263425886e-06,
|
724 |
+
"loss": 1.6527,
|
725 |
+
"step": 495
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.7451564828614009,
|
729 |
+
"grad_norm": 0.2879745114712397,
|
730 |
+
"learning_rate": 1.856435667045577e-06,
|
731 |
+
"loss": 1.5879,
|
732 |
+
"step": 500
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.7526080476900149,
|
736 |
+
"grad_norm": 0.3081841268702886,
|
737 |
+
"learning_rate": 1.7562275670200041e-06,
|
738 |
+
"loss": 1.5423,
|
739 |
+
"step": 505
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.7600596125186289,
|
743 |
+
"grad_norm": 0.3237369195299089,
|
744 |
+
"learning_rate": 1.6582205222711051e-06,
|
745 |
+
"loss": 1.6172,
|
746 |
+
"step": 510
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.767511177347243,
|
750 |
+
"grad_norm": 0.3484298930902378,
|
751 |
+
"learning_rate": 1.5624810352824709e-06,
|
752 |
+
"loss": 1.6456,
|
753 |
+
"step": 515
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.7749627421758569,
|
757 |
+
"grad_norm": 0.3160389330113336,
|
758 |
+
"learning_rate": 1.4690740698909223e-06,
|
759 |
+
"loss": 1.5929,
|
760 |
+
"step": 520
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 0.7824143070044709,
|
764 |
+
"grad_norm": 0.36108945655051267,
|
765 |
+
"learning_rate": 1.3780630072054313e-06,
|
766 |
+
"loss": 1.6718,
|
767 |
+
"step": 525
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 0.789865871833085,
|
771 |
+
"grad_norm": 0.32927194714240243,
|
772 |
+
"learning_rate": 1.289509602599996e-06,
|
773 |
+
"loss": 1.6058,
|
774 |
+
"step": 530
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.797317436661699,
|
778 |
+
"grad_norm": 0.3769043230835878,
|
779 |
+
"learning_rate": 1.203473943809651e-06,
|
780 |
+
"loss": 1.6295,
|
781 |
+
"step": 535
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.8047690014903129,
|
785 |
+
"grad_norm": 0.33941548710215963,
|
786 |
+
"learning_rate": 1.1200144101580634e-06,
|
787 |
+
"loss": 1.6792,
|
788 |
+
"step": 540
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.812220566318927,
|
792 |
+
"grad_norm": 0.3706526425603311,
|
793 |
+
"learning_rate": 1.0391876329443534e-06,
|
794 |
+
"loss": 1.6146,
|
795 |
+
"step": 545
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.819672131147541,
|
799 |
+
"grad_norm": 0.35398755740858545,
|
800 |
+
"learning_rate": 9.610484570160444e-07,
|
801 |
+
"loss": 1.7103,
|
802 |
+
"step": 550
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 0.827123695976155,
|
806 |
+
"grad_norm": 0.35561387409815454,
|
807 |
+
"learning_rate": 8.856499035541972e-07,
|
808 |
+
"loss": 1.6163,
|
809 |
+
"step": 555
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 0.834575260804769,
|
813 |
+
"grad_norm": 0.348602818005502,
|
814 |
+
"learning_rate": 8.130431340959982e-07,
|
815 |
+
"loss": 1.6807,
|
816 |
+
"step": 560
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 0.842026825633383,
|
820 |
+
"grad_norm": 0.3675149781602246,
|
821 |
+
"learning_rate": 7.432774158191946e-07,
|
822 |
+
"loss": 1.6201,
|
823 |
+
"step": 565
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.849478390461997,
|
827 |
+
"grad_norm": 0.35625514274912495,
|
828 |
+
"learning_rate": 6.764000881119631e-07,
|
829 |
+
"loss": 1.5743,
|
830 |
+
"step": 570
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.856929955290611,
|
834 |
+
"grad_norm": 0.3186585069526685,
|
835 |
+
"learning_rate": 6.12456530450844e-07,
|
836 |
+
"loss": 1.6272,
|
837 |
+
"step": 575
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.8643815201192251,
|
841 |
+
"grad_norm": 0.3347624139888847,
|
842 |
+
"learning_rate": 5.514901316086058e-07,
|
843 |
+
"loss": 1.6818,
|
844 |
+
"step": 580
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 0.8718330849478391,
|
848 |
+
"grad_norm": 0.3821665104781894,
|
849 |
+
"learning_rate": 4.935422602128698e-07,
|
850 |
+
"loss": 1.7344,
|
851 |
+
"step": 585
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 0.879284649776453,
|
855 |
+
"grad_norm": 0.31160320897543975,
|
856 |
+
"learning_rate": 4.386522366755169e-07,
|
857 |
+
"loss": 1.5668,
|
858 |
+
"step": 590
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 0.886736214605067,
|
862 |
+
"grad_norm": 0.32657433748759934,
|
863 |
+
"learning_rate": 3.868573065118936e-07,
|
864 |
+
"loss": 1.6732,
|
865 |
+
"step": 595
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 0.8941877794336811,
|
869 |
+
"grad_norm": 0.34252424286072203,
|
870 |
+
"learning_rate": 3.381926150679543e-07,
|
871 |
+
"loss": 1.6245,
|
872 |
+
"step": 600
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.8941877794336811,
|
876 |
+
"eval_loss": 1.6357628107070923,
|
877 |
+
"eval_runtime": 580.6663,
|
878 |
+
"eval_samples_per_second": 4.109,
|
879 |
+
"eval_steps_per_second": 0.258,
|
880 |
+
"step": 600
|
881 |
+
},
|
882 |
+
{
|
883 |
+
"epoch": 0.9016393442622951,
|
884 |
+
"grad_norm": 0.3432161875223241,
|
885 |
+
"learning_rate": 2.9269118367244385e-07,
|
886 |
+
"loss": 1.6999,
|
887 |
+
"step": 605
|
888 |
+
},
|
889 |
+
{
|
890 |
+
"epoch": 0.9090909090909091,
|
891 |
+
"grad_norm": 0.3458124106576635,
|
892 |
+
"learning_rate": 2.5038388723034935e-07,
|
893 |
+
"loss": 1.6037,
|
894 |
+
"step": 610
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 0.9165424739195231,
|
898 |
+
"grad_norm": 0.34778709529194757,
|
899 |
+
"learning_rate": 2.1129943327279522e-07,
|
900 |
+
"loss": 1.7079,
|
901 |
+
"step": 615
|
902 |
+
},
|
903 |
+
{
|
904 |
+
"epoch": 0.9239940387481371,
|
905 |
+
"grad_norm": 0.3605158717479098,
|
906 |
+
"learning_rate": 1.7546434247760147e-07,
|
907 |
+
"loss": 1.6404,
|
908 |
+
"step": 620
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 0.9314456035767511,
|
912 |
+
"grad_norm": 0.29865645458342877,
|
913 |
+
"learning_rate": 1.429029306737345e-07,
|
914 |
+
"loss": 1.6086,
|
915 |
+
"step": 625
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 0.9388971684053651,
|
919 |
+
"grad_norm": 0.3290659895478686,
|
920 |
+
"learning_rate": 1.1363729234184828e-07,
|
921 |
+
"loss": 1.596,
|
922 |
+
"step": 630
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 0.9463487332339792,
|
926 |
+
"grad_norm": 0.32311961294020886,
|
927 |
+
"learning_rate": 8.768728562211948e-08,
|
928 |
+
"loss": 1.5774,
|
929 |
+
"step": 635
|
930 |
+
},
|
931 |
+
{
|
932 |
+
"epoch": 0.9538002980625931,
|
933 |
+
"grad_norm": 0.3628568702485729,
|
934 |
+
"learning_rate": 6.507051883954618e-08,
|
935 |
+
"loss": 1.6421,
|
936 |
+
"step": 640
|
937 |
+
},
|
938 |
+
{
|
939 |
+
"epoch": 0.9612518628912071,
|
940 |
+
"grad_norm": 0.35678638324651946,
|
941 |
+
"learning_rate": 4.580233855585425e-08,
|
942 |
+
"loss": 1.5815,
|
943 |
+
"step": 645
|
944 |
+
},
|
945 |
+
{
|
946 |
+
"epoch": 0.9687034277198212,
|
947 |
+
"grad_norm": 0.32862520535733186,
|
948 |
+
"learning_rate": 2.989581915611994e-08,
|
949 |
+
"loss": 1.5756,
|
950 |
+
"step": 650
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 0.9761549925484352,
|
954 |
+
"grad_norm": 0.36012152823713983,
|
955 |
+
"learning_rate": 1.7361753977169214e-08,
|
956 |
+
"loss": 1.6405,
|
957 |
+
"step": 655
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.9836065573770492,
|
961 |
+
"grad_norm": 0.3640507189017552,
|
962 |
+
"learning_rate": 8.208647983782847e-09,
|
963 |
+
"loss": 1.62,
|
964 |
+
"step": 660
|
965 |
+
},
|
966 |
+
{
|
967 |
+
"epoch": 0.9910581222056631,
|
968 |
+
"grad_norm": 0.33586265256557224,
|
969 |
+
"learning_rate": 2.442711997670544e-09,
|
970 |
+
"loss": 1.6375,
|
971 |
+
"step": 665
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 0.9985096870342772,
|
975 |
+
"grad_norm": 0.3189391910196833,
|
976 |
+
"learning_rate": 6.785848312707011e-11,
|
977 |
+
"loss": 1.6954,
|
978 |
+
"step": 670
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 1.0,
|
982 |
+
"step": 671,
|
983 |
+
"total_flos": 919616052789248.0,
|
984 |
+
"train_loss": 1.6831368206154926,
|
985 |
+
"train_runtime": 18035.2779,
|
986 |
+
"train_samples_per_second": 1.191,
|
987 |
+
"train_steps_per_second": 0.037
|
988 |
+
}
|
989 |
+
],
|
990 |
+
"logging_steps": 5,
|
991 |
+
"max_steps": 671,
|
992 |
+
"num_input_tokens_seen": 0,
|
993 |
+
"num_train_epochs": 1,
|
994 |
+
"save_steps": 200,
|
995 |
+
"stateful_callbacks": {
|
996 |
+
"TrainerControl": {
|
997 |
+
"args": {
|
998 |
+
"should_epoch_stop": false,
|
999 |
+
"should_evaluate": false,
|
1000 |
+
"should_log": false,
|
1001 |
+
"should_save": true,
|
1002 |
+
"should_training_stop": false
|
1003 |
+
},
|
1004 |
+
"attributes": {}
|
1005 |
+
}
|
1006 |
+
},
|
1007 |
+
"total_flos": 919616052789248.0,
|
1008 |
+
"train_batch_size": 4,
|
1009 |
+
"trial_name": null,
|
1010 |
+
"trial_params": null
|
1011 |
+
}
|