Model save
Browse files- README.md +67 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- all_results.json +9 -0
- runs/Jun11_05-08-08_COE-CS-sv003/events.out.tfevents.1718082506.COE-CS-sv003.1087619.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +813 -0
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: mistralai/Mistral-7B-v0.1
|
9 |
+
model-index:
|
10 |
+
- name: mistral20pGrad_1
|
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 |
+
# mistral20pGrad_1
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.9495
|
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: 0.0002
|
41 |
+
- train_batch_size: 24
|
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: 192
|
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 |
+
| 0.702 | 0.9991 | 541 | 0.9495 |
|
59 |
+
|
60 |
+
|
61 |
+
### Framework versions
|
62 |
+
|
63 |
+
- PEFT 0.11.1
|
64 |
+
- Transformers 4.41.1
|
65 |
+
- Pytorch 2.3.0+cu121
|
66 |
+
- Datasets 2.19.1
|
67 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 8,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 6,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"o_proj",
|
24 |
+
"up_proj",
|
25 |
+
"down_proj",
|
26 |
+
"k_proj",
|
27 |
+
"q_proj",
|
28 |
+
"v_proj",
|
29 |
+
"gate_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5acc66e57ec28a385afcb6f28ad62de9c4b9c84cd96e8c5f60082a09601d6f8
|
3 |
+
size 62973728
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9990766389658357,
|
3 |
+
"total_flos": 2.2228397020277637e+18,
|
4 |
+
"train_loss": 0.7336494325489742,
|
5 |
+
"train_runtime": 26329.8311,
|
6 |
+
"train_samples": 103932,
|
7 |
+
"train_samples_per_second": 3.947,
|
8 |
+
"train_steps_per_second": 0.021
|
9 |
+
}
|
runs/Jun11_05-08-08_COE-CS-sv003/events.out.tfevents.1718082506.COE-CS-sv003.1087619.0
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:c56bc1b2b086d627d6204d2f6175579d7e20fcbe5318c042b44f553fcca87534
|
3 |
+
size 28528
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9990766389658357,
|
3 |
+
"total_flos": 2.2228397020277637e+18,
|
4 |
+
"train_loss": 0.7336494325489742,
|
5 |
+
"train_runtime": 26329.8311,
|
6 |
+
"train_samples": 103932,
|
7 |
+
"train_samples_per_second": 3.947,
|
8 |
+
"train_steps_per_second": 0.021
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,813 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9990766389658357,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 541,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0018467220683287165,
|
13 |
+
"grad_norm": 0.18254348635673523,
|
14 |
+
"learning_rate": 3.636363636363636e-06,
|
15 |
+
"loss": 0.8244,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.009233610341643583,
|
20 |
+
"grad_norm": 0.1816311925649643,
|
21 |
+
"learning_rate": 1.8181818181818182e-05,
|
22 |
+
"loss": 0.7911,
|
23 |
+
"step": 5
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.018467220683287166,
|
27 |
+
"grad_norm": 0.16621439158916473,
|
28 |
+
"learning_rate": 3.6363636363636364e-05,
|
29 |
+
"loss": 0.7968,
|
30 |
+
"step": 10
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.027700831024930747,
|
34 |
+
"grad_norm": 0.1893552839756012,
|
35 |
+
"learning_rate": 5.4545454545454546e-05,
|
36 |
+
"loss": 0.7942,
|
37 |
+
"step": 15
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.03693444136657433,
|
41 |
+
"grad_norm": 0.12671160697937012,
|
42 |
+
"learning_rate": 7.272727272727273e-05,
|
43 |
+
"loss": 0.7531,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.046168051708217916,
|
48 |
+
"grad_norm": 0.12510479986667633,
|
49 |
+
"learning_rate": 9.090909090909092e-05,
|
50 |
+
"loss": 0.7688,
|
51 |
+
"step": 25
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.055401662049861494,
|
55 |
+
"grad_norm": 0.1175699383020401,
|
56 |
+
"learning_rate": 0.00010909090909090909,
|
57 |
+
"loss": 0.7694,
|
58 |
+
"step": 30
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.06463527239150507,
|
62 |
+
"grad_norm": 0.11805781722068787,
|
63 |
+
"learning_rate": 0.00012727272727272728,
|
64 |
+
"loss": 0.7348,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.07386888273314866,
|
69 |
+
"grad_norm": 0.11772854626178741,
|
70 |
+
"learning_rate": 0.00014545454545454546,
|
71 |
+
"loss": 0.7407,
|
72 |
+
"step": 40
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.08310249307479224,
|
76 |
+
"grad_norm": 0.2634792625904083,
|
77 |
+
"learning_rate": 0.00016363636363636366,
|
78 |
+
"loss": 0.7324,
|
79 |
+
"step": 45
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.09233610341643583,
|
83 |
+
"grad_norm": 0.1200411394238472,
|
84 |
+
"learning_rate": 0.00018181818181818183,
|
85 |
+
"loss": 0.7535,
|
86 |
+
"step": 50
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.10156971375807941,
|
90 |
+
"grad_norm": 0.12060506641864777,
|
91 |
+
"learning_rate": 0.0002,
|
92 |
+
"loss": 0.7487,
|
93 |
+
"step": 55
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.11080332409972299,
|
97 |
+
"grad_norm": 0.12120962888002396,
|
98 |
+
"learning_rate": 0.00019994777247895855,
|
99 |
+
"loss": 0.745,
|
100 |
+
"step": 60
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.12003693444136658,
|
104 |
+
"grad_norm": 0.14212490618228912,
|
105 |
+
"learning_rate": 0.00019979114447011323,
|
106 |
+
"loss": 0.7294,
|
107 |
+
"step": 65
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.12927054478301014,
|
111 |
+
"grad_norm": 0.1235802099108696,
|
112 |
+
"learning_rate": 0.00019953027957931658,
|
113 |
+
"loss": 0.7391,
|
114 |
+
"step": 70
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.13850415512465375,
|
118 |
+
"grad_norm": 0.11884737759828568,
|
119 |
+
"learning_rate": 0.00019916545029310012,
|
120 |
+
"loss": 0.7324,
|
121 |
+
"step": 75
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.14773776546629733,
|
125 |
+
"grad_norm": 0.1151009351015091,
|
126 |
+
"learning_rate": 0.00019869703769404828,
|
127 |
+
"loss": 0.7266,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.1569713758079409,
|
132 |
+
"grad_norm": 0.11894387751817703,
|
133 |
+
"learning_rate": 0.00019812553106273847,
|
134 |
+
"loss": 0.7467,
|
135 |
+
"step": 85
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.16620498614958448,
|
139 |
+
"grad_norm": 0.1144394502043724,
|
140 |
+
"learning_rate": 0.00019745152736666302,
|
141 |
+
"loss": 0.7376,
|
142 |
+
"step": 90
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.17543859649122806,
|
146 |
+
"grad_norm": 0.11750061810016632,
|
147 |
+
"learning_rate": 0.0001966757306366662,
|
148 |
+
"loss": 0.7383,
|
149 |
+
"step": 95
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.18467220683287167,
|
153 |
+
"grad_norm": 0.13155049085617065,
|
154 |
+
"learning_rate": 0.0001957989512315489,
|
155 |
+
"loss": 0.7451,
|
156 |
+
"step": 100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.19390581717451524,
|
160 |
+
"grad_norm": 0.11150489002466202,
|
161 |
+
"learning_rate": 0.00019482210499160765,
|
162 |
+
"loss": 0.7412,
|
163 |
+
"step": 105
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.20313942751615882,
|
167 |
+
"grad_norm": 0.10819390416145325,
|
168 |
+
"learning_rate": 0.0001937462122819935,
|
169 |
+
"loss": 0.7422,
|
170 |
+
"step": 110
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.2123730378578024,
|
174 |
+
"grad_norm": 0.11923832446336746,
|
175 |
+
"learning_rate": 0.00019257239692688907,
|
176 |
+
"loss": 0.7377,
|
177 |
+
"step": 115
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.22160664819944598,
|
181 |
+
"grad_norm": 0.11017678678035736,
|
182 |
+
"learning_rate": 0.00019130188503561741,
|
183 |
+
"loss": 0.7351,
|
184 |
+
"step": 120
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.23084025854108955,
|
188 |
+
"grad_norm": 0.11701685935258865,
|
189 |
+
"learning_rate": 0.00018993600372190932,
|
190 |
+
"loss": 0.7282,
|
191 |
+
"step": 125
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.24007386888273316,
|
195 |
+
"grad_norm": 0.11328760534524918,
|
196 |
+
"learning_rate": 0.00018847617971766577,
|
197 |
+
"loss": 0.7269,
|
198 |
+
"step": 130
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.24930747922437674,
|
202 |
+
"grad_norm": 0.11526869982481003,
|
203 |
+
"learning_rate": 0.00018692393788266479,
|
204 |
+
"loss": 0.7083,
|
205 |
+
"step": 135
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.2585410895660203,
|
209 |
+
"grad_norm": 0.1022554561495781,
|
210 |
+
"learning_rate": 0.0001852808996117683,
|
211 |
+
"loss": 0.7118,
|
212 |
+
"step": 140
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.2677746999076639,
|
216 |
+
"grad_norm": 0.12440157681703568,
|
217 |
+
"learning_rate": 0.00018354878114129367,
|
218 |
+
"loss": 0.7294,
|
219 |
+
"step": 145
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.2770083102493075,
|
223 |
+
"grad_norm": 0.11588307470083237,
|
224 |
+
"learning_rate": 0.00018172939175631808,
|
225 |
+
"loss": 0.743,
|
226 |
+
"step": 150
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.28624192059095105,
|
230 |
+
"grad_norm": 0.12347640097141266,
|
231 |
+
"learning_rate": 0.0001798246319007893,
|
232 |
+
"loss": 0.7449,
|
233 |
+
"step": 155
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.29547553093259465,
|
237 |
+
"grad_norm": 0.12588274478912354,
|
238 |
+
"learning_rate": 0.00017783649119241602,
|
239 |
+
"loss": 0.761,
|
240 |
+
"step": 160
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.3047091412742382,
|
244 |
+
"grad_norm": 0.11528731882572174,
|
245 |
+
"learning_rate": 0.0001757670463444118,
|
246 |
+
"loss": 0.7353,
|
247 |
+
"step": 165
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.3139427516158818,
|
251 |
+
"grad_norm": 0.11055415123701096,
|
252 |
+
"learning_rate": 0.00017361845899626355,
|
253 |
+
"loss": 0.7331,
|
254 |
+
"step": 170
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.3231763619575254,
|
258 |
+
"grad_norm": 0.10451104491949081,
|
259 |
+
"learning_rate": 0.00017139297345578994,
|
260 |
+
"loss": 0.7594,
|
261 |
+
"step": 175
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.33240997229916897,
|
265 |
+
"grad_norm": 0.11109859496355057,
|
266 |
+
"learning_rate": 0.0001690929143548488,
|
267 |
+
"loss": 0.7291,
|
268 |
+
"step": 180
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.34164358264081257,
|
272 |
+
"grad_norm": 0.11210189759731293,
|
273 |
+
"learning_rate": 0.00016672068422114196,
|
274 |
+
"loss": 0.7372,
|
275 |
+
"step": 185
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.3508771929824561,
|
279 |
+
"grad_norm": 0.11521945893764496,
|
280 |
+
"learning_rate": 0.00016427876096865394,
|
281 |
+
"loss": 0.7404,
|
282 |
+
"step": 190
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.3601108033240997,
|
286 |
+
"grad_norm": 0.11584653705358505,
|
287 |
+
"learning_rate": 0.00016176969530934572,
|
288 |
+
"loss": 0.7465,
|
289 |
+
"step": 195
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.36934441366574333,
|
293 |
+
"grad_norm": 0.11106808483600616,
|
294 |
+
"learning_rate": 0.0001591961080888076,
|
295 |
+
"loss": 0.7235,
|
296 |
+
"step": 200
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.3785780240073869,
|
300 |
+
"grad_norm": 0.09438136965036392,
|
301 |
+
"learning_rate": 0.00015656068754865387,
|
302 |
+
"loss": 0.7104,
|
303 |
+
"step": 205
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.3878116343490305,
|
307 |
+
"grad_norm": 0.10474290698766708,
|
308 |
+
"learning_rate": 0.0001538661865185188,
|
309 |
+
"loss": 0.7567,
|
310 |
+
"step": 210
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.39704524469067404,
|
314 |
+
"grad_norm": 0.11921609193086624,
|
315 |
+
"learning_rate": 0.00015111541954058734,
|
316 |
+
"loss": 0.739,
|
317 |
+
"step": 215
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.40627885503231764,
|
321 |
+
"grad_norm": 0.11335526406764984,
|
322 |
+
"learning_rate": 0.00014831125992966385,
|
323 |
+
"loss": 0.734,
|
324 |
+
"step": 220
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.4155124653739612,
|
328 |
+
"grad_norm": 0.11289556324481964,
|
329 |
+
"learning_rate": 0.00014545663677185006,
|
330 |
+
"loss": 0.7448,
|
331 |
+
"step": 225
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.4247460757156048,
|
335 |
+
"grad_norm": 0.10999900847673416,
|
336 |
+
"learning_rate": 0.00014255453186496673,
|
337 |
+
"loss": 0.7316,
|
338 |
+
"step": 230
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.4339796860572484,
|
342 |
+
"grad_norm": 0.1110299751162529,
|
343 |
+
"learning_rate": 0.0001396079766039157,
|
344 |
+
"loss": 0.7247,
|
345 |
+
"step": 235
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.44321329639889195,
|
349 |
+
"grad_norm": 0.11613520234823227,
|
350 |
+
"learning_rate": 0.0001366200488142348,
|
351 |
+
"loss": 0.7364,
|
352 |
+
"step": 240
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.45244690674053556,
|
356 |
+
"grad_norm": 0.11091934144496918,
|
357 |
+
"learning_rate": 0.00013359386953715421,
|
358 |
+
"loss": 0.7497,
|
359 |
+
"step": 245
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.4616805170821791,
|
363 |
+
"grad_norm": 0.1117897480726242,
|
364 |
+
"learning_rate": 0.00013053259976951133,
|
365 |
+
"loss": 0.7318,
|
366 |
+
"step": 250
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.4709141274238227,
|
370 |
+
"grad_norm": 0.10972230136394501,
|
371 |
+
"learning_rate": 0.00012743943716193016,
|
372 |
+
"loss": 0.7362,
|
373 |
+
"step": 255
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.4801477377654663,
|
377 |
+
"grad_norm": 0.1100962832570076,
|
378 |
+
"learning_rate": 0.00012431761267871417,
|
379 |
+
"loss": 0.7246,
|
380 |
+
"step": 260
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.48938134810710987,
|
384 |
+
"grad_norm": 0.11420110613107681,
|
385 |
+
"learning_rate": 0.0001211703872229411,
|
386 |
+
"loss": 0.6997,
|
387 |
+
"step": 265
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.4986149584487535,
|
391 |
+
"grad_norm": 0.11659246683120728,
|
392 |
+
"learning_rate": 0.00011800104823028515,
|
393 |
+
"loss": 0.7216,
|
394 |
+
"step": 270
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.5078485687903971,
|
398 |
+
"grad_norm": 0.10777433216571808,
|
399 |
+
"learning_rate": 0.0001148129062351249,
|
400 |
+
"loss": 0.7386,
|
401 |
+
"step": 275
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.5170821791320406,
|
405 |
+
"grad_norm": 0.1175241768360138,
|
406 |
+
"learning_rate": 0.00011160929141252303,
|
407 |
+
"loss": 0.7354,
|
408 |
+
"step": 280
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.5263157894736842,
|
412 |
+
"grad_norm": 0.11116177588701248,
|
413 |
+
"learning_rate": 0.00010839355009969068,
|
414 |
+
"loss": 0.74,
|
415 |
+
"step": 285
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.5355493998153278,
|
419 |
+
"grad_norm": 0.11569847166538239,
|
420 |
+
"learning_rate": 0.00010516904130056946,
|
421 |
+
"loss": 0.7488,
|
422 |
+
"step": 290
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.5447830101569714,
|
426 |
+
"grad_norm": 0.12016792595386505,
|
427 |
+
"learning_rate": 0.00010193913317718244,
|
428 |
+
"loss": 0.7238,
|
429 |
+
"step": 295
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.554016620498615,
|
433 |
+
"grad_norm": 0.11518382281064987,
|
434 |
+
"learning_rate": 9.870719953141917e-05,
|
435 |
+
"loss": 0.7223,
|
436 |
+
"step": 300
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.5632502308402585,
|
440 |
+
"grad_norm": 0.1142842248082161,
|
441 |
+
"learning_rate": 9.547661628092937e-05,
|
442 |
+
"loss": 0.7409,
|
443 |
+
"step": 305
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.5724838411819021,
|
447 |
+
"grad_norm": 0.10657477378845215,
|
448 |
+
"learning_rate": 9.225075793280692e-05,
|
449 |
+
"loss": 0.7228,
|
450 |
+
"step": 310
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.5817174515235457,
|
454 |
+
"grad_norm": 0.10703656822443008,
|
455 |
+
"learning_rate": 8.903299405874684e-05,
|
456 |
+
"loss": 0.7367,
|
457 |
+
"step": 315
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.5909510618651893,
|
461 |
+
"grad_norm": 0.10378415137529373,
|
462 |
+
"learning_rate": 8.582668577535797e-05,
|
463 |
+
"loss": 0.7368,
|
464 |
+
"step": 320
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.6001846722068329,
|
468 |
+
"grad_norm": 0.1063636764883995,
|
469 |
+
"learning_rate": 8.263518223330697e-05,
|
470 |
+
"loss": 0.7504,
|
471 |
+
"step": 325
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.6094182825484764,
|
475 |
+
"grad_norm": 0.1067524254322052,
|
476 |
+
"learning_rate": 7.94618171189618e-05,
|
477 |
+
"loss": 0.7114,
|
478 |
+
"step": 330
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.61865189289012,
|
482 |
+
"grad_norm": 0.11942796409130096,
|
483 |
+
"learning_rate": 7.630990517218808e-05,
|
484 |
+
"loss": 0.7372,
|
485 |
+
"step": 335
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.6278855032317636,
|
489 |
+
"grad_norm": 0.11493529379367828,
|
490 |
+
"learning_rate": 7.318273872393625e-05,
|
491 |
+
"loss": 0.7194,
|
492 |
+
"step": 340
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.6371191135734072,
|
496 |
+
"grad_norm": 0.10850054770708084,
|
497 |
+
"learning_rate": 7.008358425723585e-05,
|
498 |
+
"loss": 0.7423,
|
499 |
+
"step": 345
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.6463527239150508,
|
503 |
+
"grad_norm": 0.11228082329034805,
|
504 |
+
"learning_rate": 6.701567899518924e-05,
|
505 |
+
"loss": 0.7064,
|
506 |
+
"step": 350
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.6555863342566943,
|
510 |
+
"grad_norm": 0.10916541516780853,
|
511 |
+
"learning_rate": 6.398222751952899e-05,
|
512 |
+
"loss": 0.7026,
|
513 |
+
"step": 355
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.6648199445983379,
|
517 |
+
"grad_norm": 0.11889058351516724,
|
518 |
+
"learning_rate": 6.098639842327052e-05,
|
519 |
+
"loss": 0.7273,
|
520 |
+
"step": 360
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.6740535549399815,
|
524 |
+
"grad_norm": 0.11622773110866547,
|
525 |
+
"learning_rate": 5.80313210009571e-05,
|
526 |
+
"loss": 0.7251,
|
527 |
+
"step": 365
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.6832871652816251,
|
531 |
+
"grad_norm": 0.11390994489192963,
|
532 |
+
"learning_rate": 5.5120081979953785e-05,
|
533 |
+
"loss": 0.7425,
|
534 |
+
"step": 370
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.6925207756232687,
|
538 |
+
"grad_norm": 0.10942788422107697,
|
539 |
+
"learning_rate": 5.22557222962051e-05,
|
540 |
+
"loss": 0.7278,
|
541 |
+
"step": 375
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.7017543859649122,
|
545 |
+
"grad_norm": 0.11150877922773361,
|
546 |
+
"learning_rate": 4.9441233917824106e-05,
|
547 |
+
"loss": 0.7199,
|
548 |
+
"step": 380
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.7109879963065558,
|
552 |
+
"grad_norm": 0.11406592279672623,
|
553 |
+
"learning_rate": 4.66795567198309e-05,
|
554 |
+
"loss": 0.7635,
|
555 |
+
"step": 385
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.7202216066481995,
|
559 |
+
"grad_norm": 0.10552997142076492,
|
560 |
+
"learning_rate": 4.397357541330476e-05,
|
561 |
+
"loss": 0.74,
|
562 |
+
"step": 390
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.7294552169898431,
|
566 |
+
"grad_norm": 0.11307038366794586,
|
567 |
+
"learning_rate": 4.132611653215822e-05,
|
568 |
+
"loss": 0.7155,
|
569 |
+
"step": 395
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.7386888273314867,
|
573 |
+
"grad_norm": 0.11548582464456558,
|
574 |
+
"learning_rate": 3.873994548067972e-05,
|
575 |
+
"loss": 0.735,
|
576 |
+
"step": 400
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.7479224376731302,
|
580 |
+
"grad_norm": 0.11258837580680847,
|
581 |
+
"learning_rate": 3.621776364492939e-05,
|
582 |
+
"loss": 0.7438,
|
583 |
+
"step": 405
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.7571560480147738,
|
587 |
+
"grad_norm": 0.11234745383262634,
|
588 |
+
"learning_rate": 3.376220557100523e-05,
|
589 |
+
"loss": 0.7289,
|
590 |
+
"step": 410
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.7663896583564174,
|
594 |
+
"grad_norm": 0.11089134961366653,
|
595 |
+
"learning_rate": 3.137583621312665e-05,
|
596 |
+
"loss": 0.7185,
|
597 |
+
"step": 415
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.775623268698061,
|
601 |
+
"grad_norm": 0.1163964495062828,
|
602 |
+
"learning_rate": 2.906114825441072e-05,
|
603 |
+
"loss": 0.7194,
|
604 |
+
"step": 420
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.7848568790397045,
|
608 |
+
"grad_norm": 0.12141181528568268,
|
609 |
+
"learning_rate": 2.6820559503138797e-05,
|
610 |
+
"loss": 0.7271,
|
611 |
+
"step": 425
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.7940904893813481,
|
615 |
+
"grad_norm": 0.11405418813228607,
|
616 |
+
"learning_rate": 2.465641036723393e-05,
|
617 |
+
"loss": 0.7176,
|
618 |
+
"step": 430
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.8033240997229917,
|
622 |
+
"grad_norm": 0.1123843789100647,
|
623 |
+
"learning_rate": 2.2570961409586754e-05,
|
624 |
+
"loss": 0.7218,
|
625 |
+
"step": 435
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.8125577100646353,
|
629 |
+
"grad_norm": 0.1090715080499649,
|
630 |
+
"learning_rate": 2.0566390986783646e-05,
|
631 |
+
"loss": 0.7348,
|
632 |
+
"step": 440
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.8217913204062789,
|
636 |
+
"grad_norm": 0.1076655238866806,
|
637 |
+
"learning_rate": 1.864479297370325e-05,
|
638 |
+
"loss": 0.7508,
|
639 |
+
"step": 445
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.8310249307479224,
|
643 |
+
"grad_norm": 0.1181124672293663,
|
644 |
+
"learning_rate": 1.6808174576358848e-05,
|
645 |
+
"loss": 0.7248,
|
646 |
+
"step": 450
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.840258541089566,
|
650 |
+
"grad_norm": 0.11672370880842209,
|
651 |
+
"learning_rate": 1.505845423527027e-05,
|
652 |
+
"loss": 0.7357,
|
653 |
+
"step": 455
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.8494921514312096,
|
657 |
+
"grad_norm": 0.10791666060686111,
|
658 |
+
"learning_rate": 1.339745962155613e-05,
|
659 |
+
"loss": 0.7117,
|
660 |
+
"step": 460
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.8587257617728532,
|
664 |
+
"grad_norm": 0.10970946401357651,
|
665 |
+
"learning_rate": 1.18269257278392e-05,
|
666 |
+
"loss": 0.724,
|
667 |
+
"step": 465
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.8679593721144968,
|
671 |
+
"grad_norm": 0.10867480933666229,
|
672 |
+
"learning_rate": 1.0348493055959062e-05,
|
673 |
+
"loss": 0.7184,
|
674 |
+
"step": 470
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.8771929824561403,
|
678 |
+
"grad_norm": 0.10204034298658371,
|
679 |
+
"learning_rate": 8.963705903385345e-06,
|
680 |
+
"loss": 0.7395,
|
681 |
+
"step": 475
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.8864265927977839,
|
685 |
+
"grad_norm": 0.10882284492254257,
|
686 |
+
"learning_rate": 7.674010750120964e-06,
|
687 |
+
"loss": 0.727,
|
688 |
+
"step": 480
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.8956602031394275,
|
692 |
+
"grad_norm": 0.11304344236850739,
|
693 |
+
"learning_rate": 6.480754747781037e-06,
|
694 |
+
"loss": 0.7039,
|
695 |
+
"step": 485
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.9048938134810711,
|
699 |
+
"grad_norm": 0.11570131033658981,
|
700 |
+
"learning_rate": 5.385184312424974e-06,
|
701 |
+
"loss": 0.7444,
|
702 |
+
"step": 490
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.9141274238227147,
|
706 |
+
"grad_norm": 0.10709495097398758,
|
707 |
+
"learning_rate": 4.3884438226120424e-06,
|
708 |
+
"loss": 0.7134,
|
709 |
+
"step": 495
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.9233610341643582,
|
713 |
+
"grad_norm": 0.11614098399877548,
|
714 |
+
"learning_rate": 3.4915744240403558e-06,
|
715 |
+
"loss": 0.707,
|
716 |
+
"step": 500
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.9325946445060018,
|
720 |
+
"grad_norm": 0.11611202359199524,
|
721 |
+
"learning_rate": 2.6955129420176196e-06,
|
722 |
+
"loss": 0.737,
|
723 |
+
"step": 505
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.9418282548476454,
|
727 |
+
"grad_norm": 0.11080285161733627,
|
728 |
+
"learning_rate": 2.0010909028998827e-06,
|
729 |
+
"loss": 0.7359,
|
730 |
+
"step": 510
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.951061865189289,
|
734 |
+
"grad_norm": 0.1167815551161766,
|
735 |
+
"learning_rate": 1.409033665520354e-06,
|
736 |
+
"loss": 0.7131,
|
737 |
+
"step": 515
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.9602954755309326,
|
741 |
+
"grad_norm": 0.11581467092037201,
|
742 |
+
"learning_rate": 9.199596635154683e-07,
|
743 |
+
"loss": 0.7062,
|
744 |
+
"step": 520
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.9695290858725761,
|
748 |
+
"grad_norm": 0.1139911562204361,
|
749 |
+
"learning_rate": 5.343797593398536e-07,
|
750 |
+
"loss": 0.7382,
|
751 |
+
"step": 525
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.9787626962142197,
|
755 |
+
"grad_norm": 0.10670532286167145,
|
756 |
+
"learning_rate": 2.5269671064467313e-07,
|
757 |
+
"loss": 0.6965,
|
758 |
+
"step": 530
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.9879963065558633,
|
762 |
+
"grad_norm": 0.10769211500883102,
|
763 |
+
"learning_rate": 7.520474957699586e-08,
|
764 |
+
"loss": 0.7086,
|
765 |
+
"step": 535
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.997229916897507,
|
769 |
+
"grad_norm": 0.10409457236528397,
|
770 |
+
"learning_rate": 2.0892754394208346e-09,
|
771 |
+
"loss": 0.702,
|
772 |
+
"step": 540
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.9990766389658357,
|
776 |
+
"eval_loss": 0.9494999051094055,
|
777 |
+
"eval_runtime": 131.5083,
|
778 |
+
"eval_samples_per_second": 8.783,
|
779 |
+
"eval_steps_per_second": 0.555,
|
780 |
+
"step": 541
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.9990766389658357,
|
784 |
+
"step": 541,
|
785 |
+
"total_flos": 2.2228397020277637e+18,
|
786 |
+
"train_loss": 0.7336494325489742,
|
787 |
+
"train_runtime": 26329.8311,
|
788 |
+
"train_samples_per_second": 3.947,
|
789 |
+
"train_steps_per_second": 0.021
|
790 |
+
}
|
791 |
+
],
|
792 |
+
"logging_steps": 5,
|
793 |
+
"max_steps": 541,
|
794 |
+
"num_input_tokens_seen": 0,
|
795 |
+
"num_train_epochs": 1,
|
796 |
+
"save_steps": 25,
|
797 |
+
"stateful_callbacks": {
|
798 |
+
"TrainerControl": {
|
799 |
+
"args": {
|
800 |
+
"should_epoch_stop": false,
|
801 |
+
"should_evaluate": false,
|
802 |
+
"should_log": false,
|
803 |
+
"should_save": true,
|
804 |
+
"should_training_stop": false
|
805 |
+
},
|
806 |
+
"attributes": {}
|
807 |
+
}
|
808 |
+
},
|
809 |
+
"total_flos": 2.2228397020277637e+18,
|
810 |
+
"train_batch_size": 24,
|
811 |
+
"trial_name": null,
|
812 |
+
"trial_params": null
|
813 |
+
}
|