sedrickkeh
commited on
End of training
Browse files- README.md +2 -1
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +136 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
@@ -4,6 +4,7 @@ license: llama3.1
|
|
4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
5 |
tags:
|
6 |
- llama-factory
|
|
|
7 |
- generated_from_trainer
|
8 |
model-index:
|
9 |
- name: stackoverflow_25000tasks_.5p
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# stackoverflow_25000tasks_.5p
|
17 |
|
18 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.6484
|
21 |
|
|
|
4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
5 |
tags:
|
6 |
- llama-factory
|
7 |
+
- full
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
- name: stackoverflow_25000tasks_.5p
|
|
|
16 |
|
17 |
# stackoverflow_25000tasks_.5p
|
18 |
|
19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/stackoverflow_25000tasks_.5p dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 0.6484
|
22 |
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.989010989010989,
|
3 |
+
"eval_loss": 0.6484237909317017,
|
4 |
+
"eval_runtime": 24.326,
|
5 |
+
"eval_samples_per_second": 37.737,
|
6 |
+
"eval_steps_per_second": 0.617,
|
7 |
+
"total_flos": 170644419379200.0,
|
8 |
+
"train_loss": 0.6762744293493383,
|
9 |
+
"train_runtime": 3624.8354,
|
10 |
+
"train_samples_per_second": 14.425,
|
11 |
+
"train_steps_per_second": 0.028
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.989010989010989,
|
3 |
+
"eval_loss": 0.6484237909317017,
|
4 |
+
"eval_runtime": 24.326,
|
5 |
+
"eval_samples_per_second": 37.737,
|
6 |
+
"eval_steps_per_second": 0.617
|
7 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.989010989010989,
|
3 |
+
"total_flos": 170644419379200.0,
|
4 |
+
"train_loss": 0.6762744293493383,
|
5 |
+
"train_runtime": 3624.8354,
|
6 |
+
"train_samples_per_second": 14.425,
|
7 |
+
"train_steps_per_second": 0.028
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.989010989010989,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 102,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.29304029304029305,
|
13 |
+
"grad_norm": 6.00564017416128,
|
14 |
+
"learning_rate": 5e-06,
|
15 |
+
"loss": 0.8612,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.5860805860805861,
|
20 |
+
"grad_norm": 3.810412857546984,
|
21 |
+
"learning_rate": 5e-06,
|
22 |
+
"loss": 0.7583,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.8791208791208791,
|
27 |
+
"grad_norm": 2.835346031353567,
|
28 |
+
"learning_rate": 5e-06,
|
29 |
+
"loss": 0.7171,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.9963369963369964,
|
34 |
+
"eval_loss": 0.6949356198310852,
|
35 |
+
"eval_runtime": 23.9449,
|
36 |
+
"eval_samples_per_second": 38.338,
|
37 |
+
"eval_steps_per_second": 0.626,
|
38 |
+
"step": 34
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.1721611721611722,
|
42 |
+
"grad_norm": 3.6787612930551394,
|
43 |
+
"learning_rate": 5e-06,
|
44 |
+
"loss": 0.7449,
|
45 |
+
"step": 40
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 1.4652014652014653,
|
49 |
+
"grad_norm": 0.8606934602884543,
|
50 |
+
"learning_rate": 5e-06,
|
51 |
+
"loss": 0.6554,
|
52 |
+
"step": 50
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 1.7582417582417582,
|
56 |
+
"grad_norm": 0.9805632267452244,
|
57 |
+
"learning_rate": 5e-06,
|
58 |
+
"loss": 0.6415,
|
59 |
+
"step": 60
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 1.9926739926739927,
|
63 |
+
"eval_loss": 0.6563424468040466,
|
64 |
+
"eval_runtime": 24.5646,
|
65 |
+
"eval_samples_per_second": 37.371,
|
66 |
+
"eval_steps_per_second": 0.611,
|
67 |
+
"step": 68
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 2.051282051282051,
|
71 |
+
"grad_norm": 1.0030553009772163,
|
72 |
+
"learning_rate": 5e-06,
|
73 |
+
"loss": 0.6776,
|
74 |
+
"step": 70
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 2.3443223443223444,
|
78 |
+
"grad_norm": 1.1368386124641172,
|
79 |
+
"learning_rate": 5e-06,
|
80 |
+
"loss": 0.5809,
|
81 |
+
"step": 80
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 2.6373626373626373,
|
85 |
+
"grad_norm": 1.2620401338366838,
|
86 |
+
"learning_rate": 5e-06,
|
87 |
+
"loss": 0.5752,
|
88 |
+
"step": 90
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 2.9304029304029307,
|
92 |
+
"grad_norm": 0.8239444630205299,
|
93 |
+
"learning_rate": 5e-06,
|
94 |
+
"loss": 0.5713,
|
95 |
+
"step": 100
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 2.989010989010989,
|
99 |
+
"eval_loss": 0.6484237909317017,
|
100 |
+
"eval_runtime": 22.7074,
|
101 |
+
"eval_samples_per_second": 40.427,
|
102 |
+
"eval_steps_per_second": 0.661,
|
103 |
+
"step": 102
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 2.989010989010989,
|
107 |
+
"step": 102,
|
108 |
+
"total_flos": 170644419379200.0,
|
109 |
+
"train_loss": 0.6762744293493383,
|
110 |
+
"train_runtime": 3624.8354,
|
111 |
+
"train_samples_per_second": 14.425,
|
112 |
+
"train_steps_per_second": 0.028
|
113 |
+
}
|
114 |
+
],
|
115 |
+
"logging_steps": 10,
|
116 |
+
"max_steps": 102,
|
117 |
+
"num_input_tokens_seen": 0,
|
118 |
+
"num_train_epochs": 3,
|
119 |
+
"save_steps": 500,
|
120 |
+
"stateful_callbacks": {
|
121 |
+
"TrainerControl": {
|
122 |
+
"args": {
|
123 |
+
"should_epoch_stop": false,
|
124 |
+
"should_evaluate": false,
|
125 |
+
"should_log": false,
|
126 |
+
"should_save": true,
|
127 |
+
"should_training_stop": true
|
128 |
+
},
|
129 |
+
"attributes": {}
|
130 |
+
}
|
131 |
+
},
|
132 |
+
"total_flos": 170644419379200.0,
|
133 |
+
"train_batch_size": 8,
|
134 |
+
"trial_name": null,
|
135 |
+
"trial_params": null
|
136 |
+
}
|
training_eval_loss.png
ADDED
training_loss.png
ADDED