OpenLeecher
commited on
End of training
Browse files- README.md +3 -2
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +1270 -0
README.md
CHANGED
@@ -4,6 +4,7 @@ license: llama3.1
|
|
4 |
base_model: meta-llama/Llama-3.1-8B-Instruct
|
5 |
tags:
|
6 |
- llama-factory
|
|
|
7 |
- generated_from_trainer
|
8 |
model-index:
|
9 |
- name: llama_8b_lima_44
|
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# llama_8b_lima_44
|
17 |
|
18 |
-
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
4 |
base_model: meta-llama/Llama-3.1-8B-Instruct
|
5 |
tags:
|
6 |
- llama-factory
|
7 |
+
- full
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
- name: llama_8b_lima_44
|
|
|
16 |
|
17 |
# llama_8b_lima_44
|
18 |
|
19 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the open_webui_dataset dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.9029
|
22 |
|
23 |
## Model description
|
24 |
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9997970367363507,
|
3 |
+
"eval_loss": 0.9028599262237549,
|
4 |
+
"eval_runtime": 10.0893,
|
5 |
+
"eval_samples_per_second": 19.823,
|
6 |
+
"eval_steps_per_second": 4.956,
|
7 |
+
"total_flos": 1.4841304991137792e+17,
|
8 |
+
"train_loss": 1.0157385155576737,
|
9 |
+
"train_runtime": 6062.254,
|
10 |
+
"train_samples_per_second": 4.876,
|
11 |
+
"train_steps_per_second": 0.135
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9997970367363507,
|
3 |
+
"eval_loss": 0.9028599262237549,
|
4 |
+
"eval_runtime": 10.0893,
|
5 |
+
"eval_samples_per_second": 19.823,
|
6 |
+
"eval_steps_per_second": 4.956
|
7 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9997970367363507,
|
3 |
+
"total_flos": 1.4841304991137792e+17,
|
4 |
+
"train_loss": 1.0157385155576737,
|
5 |
+
"train_runtime": 6062.254,
|
6 |
+
"train_samples_per_second": 4.876,
|
7 |
+
"train_steps_per_second": 0.135
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1270 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9997970367363507,
|
5 |
+
"eval_steps": 80,
|
6 |
+
"global_step": 821,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.006088897909478384,
|
13 |
+
"grad_norm": 3.566783556339775,
|
14 |
+
"learning_rate": 5.5e-07,
|
15 |
+
"loss": 1.1009,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.012177795818956769,
|
20 |
+
"grad_norm": 3.472124035548172,
|
21 |
+
"learning_rate": 1.1e-06,
|
22 |
+
"loss": 1.0381,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.018266693728435153,
|
27 |
+
"grad_norm": 2.9811017753128577,
|
28 |
+
"learning_rate": 1.6499999999999999e-06,
|
29 |
+
"loss": 0.9465,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.024355591637913537,
|
34 |
+
"grad_norm": 2.922160623410553,
|
35 |
+
"learning_rate": 2.2e-06,
|
36 |
+
"loss": 1.2107,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.03044448954739192,
|
41 |
+
"grad_norm": 2.4899147411553546,
|
42 |
+
"learning_rate": 2.75e-06,
|
43 |
+
"loss": 1.1834,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.036533387456870306,
|
48 |
+
"grad_norm": 2.4171440435334826,
|
49 |
+
"learning_rate": 3.2999999999999997e-06,
|
50 |
+
"loss": 1.0345,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.04262228536634869,
|
55 |
+
"grad_norm": 2.3631050864525105,
|
56 |
+
"learning_rate": 3.8499999999999996e-06,
|
57 |
+
"loss": 0.8937,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.048711183275827075,
|
62 |
+
"grad_norm": 2.367215460791824,
|
63 |
+
"learning_rate": 4.4e-06,
|
64 |
+
"loss": 1.0384,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.05480008118530546,
|
69 |
+
"grad_norm": 2.3735664390744695,
|
70 |
+
"learning_rate": 4.95e-06,
|
71 |
+
"loss": 0.8559,
|
72 |
+
"step": 45
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.06088897909478384,
|
76 |
+
"grad_norm": 2.1106128418644574,
|
77 |
+
"learning_rate": 5.5e-06,
|
78 |
+
"loss": 1.0974,
|
79 |
+
"step": 50
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.06697787700426223,
|
83 |
+
"grad_norm": 2.4447079098341042,
|
84 |
+
"learning_rate": 5.416103509565232e-06,
|
85 |
+
"loss": 1.0212,
|
86 |
+
"step": 55
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.07306677491374061,
|
90 |
+
"grad_norm": 2.4511103681763307,
|
91 |
+
"learning_rate": 5.333024453086441e-06,
|
92 |
+
"loss": 0.9416,
|
93 |
+
"step": 60
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.079155672823219,
|
97 |
+
"grad_norm": 2.2384105642036918,
|
98 |
+
"learning_rate": 5.250760158320862e-06,
|
99 |
+
"loss": 1.2031,
|
100 |
+
"step": 65
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.08524457073269738,
|
104 |
+
"grad_norm": 3.119602266469178,
|
105 |
+
"learning_rate": 5.16930794423241e-06,
|
106 |
+
"loss": 0.8486,
|
107 |
+
"step": 70
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.09133346864217577,
|
111 |
+
"grad_norm": 2.5881641097806862,
|
112 |
+
"learning_rate": 5.088665120904279e-06,
|
113 |
+
"loss": 1.1537,
|
114 |
+
"step": 75
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.09742236655165415,
|
118 |
+
"grad_norm": 2.2055002770457657,
|
119 |
+
"learning_rate": 5.008828989450109e-06,
|
120 |
+
"loss": 1.0313,
|
121 |
+
"step": 80
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.09742236655165415,
|
125 |
+
"eval_loss": 0.9289844036102295,
|
126 |
+
"eval_runtime": 10.8703,
|
127 |
+
"eval_samples_per_second": 18.399,
|
128 |
+
"eval_steps_per_second": 4.6,
|
129 |
+
"step": 80
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.10351126446113254,
|
133 |
+
"grad_norm": 2.415544688492964,
|
134 |
+
"learning_rate": 4.92979684192366e-06,
|
135 |
+
"loss": 0.9282,
|
136 |
+
"step": 85
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.10960016237061092,
|
140 |
+
"grad_norm": 1.7793675433556284,
|
141 |
+
"learning_rate": 4.851565961226947e-06,
|
142 |
+
"loss": 0.8977,
|
143 |
+
"step": 90
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.11568906028008931,
|
147 |
+
"grad_norm": 2.8859944584710293,
|
148 |
+
"learning_rate": 4.774133621016826e-06,
|
149 |
+
"loss": 0.9419,
|
150 |
+
"step": 95
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.12177795818956769,
|
154 |
+
"grad_norm": 2.469055183117004,
|
155 |
+
"learning_rate": 4.69749708560997e-06,
|
156 |
+
"loss": 0.9848,
|
157 |
+
"step": 100
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.12786685609904608,
|
161 |
+
"grad_norm": 2.2447776512327544,
|
162 |
+
"learning_rate": 4.621653609886213e-06,
|
163 |
+
"loss": 1.215,
|
164 |
+
"step": 105
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.13395575400852447,
|
168 |
+
"grad_norm": 2.531579161423441,
|
169 |
+
"learning_rate": 4.5466004391902066e-06,
|
170 |
+
"loss": 1.1061,
|
171 |
+
"step": 110
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.14004465191800283,
|
175 |
+
"grad_norm": 1.9522000168289182,
|
176 |
+
"learning_rate": 4.472334809231365e-06,
|
177 |
+
"loss": 0.9953,
|
178 |
+
"step": 115
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.14613354982748122,
|
182 |
+
"grad_norm": 2.5590272228727136,
|
183 |
+
"learning_rate": 4.398853945982053e-06,
|
184 |
+
"loss": 0.6939,
|
185 |
+
"step": 120
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.15222244773695962,
|
189 |
+
"grad_norm": 2.801526994914379,
|
190 |
+
"learning_rate": 4.326155065573944e-06,
|
191 |
+
"loss": 0.9363,
|
192 |
+
"step": 125
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.158311345646438,
|
196 |
+
"grad_norm": 1.8373874255277394,
|
197 |
+
"learning_rate": 4.254235374192553e-06,
|
198 |
+
"loss": 1.195,
|
199 |
+
"step": 130
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.16440024355591637,
|
203 |
+
"grad_norm": 2.236882560839364,
|
204 |
+
"learning_rate": 4.183092067969859e-06,
|
205 |
+
"loss": 0.9793,
|
206 |
+
"step": 135
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.17048914146539476,
|
210 |
+
"grad_norm": 3.3065776583087643,
|
211 |
+
"learning_rate": 4.112722332874986e-06,
|
212 |
+
"loss": 0.9404,
|
213 |
+
"step": 140
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.17657803937487315,
|
217 |
+
"grad_norm": 2.5409656409615695,
|
218 |
+
"learning_rate": 4.043123344602879e-06,
|
219 |
+
"loss": 0.7751,
|
220 |
+
"step": 145
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.18266693728435154,
|
224 |
+
"grad_norm": 2.6275401841731814,
|
225 |
+
"learning_rate": 3.974292268460949e-06,
|
226 |
+
"loss": 0.874,
|
227 |
+
"step": 150
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.1887558351938299,
|
231 |
+
"grad_norm": 2.8046791101602007,
|
232 |
+
"learning_rate": 3.906226259253599e-06,
|
233 |
+
"loss": 0.9028,
|
234 |
+
"step": 155
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.1948447331033083,
|
238 |
+
"grad_norm": 2.1392572989093006,
|
239 |
+
"learning_rate": 3.838922461164612e-06,
|
240 |
+
"loss": 0.985,
|
241 |
+
"step": 160
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.1948447331033083,
|
245 |
+
"eval_loss": 0.9194434881210327,
|
246 |
+
"eval_runtime": 10.0404,
|
247 |
+
"eval_samples_per_second": 19.919,
|
248 |
+
"eval_steps_per_second": 4.98,
|
249 |
+
"step": 160
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.2009336310127867,
|
253 |
+
"grad_norm": 1.937352853882511,
|
254 |
+
"learning_rate": 3.772378007637317e-06,
|
255 |
+
"loss": 1.2669,
|
256 |
+
"step": 165
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.20702252892226508,
|
260 |
+
"grad_norm": 2.31447918391138,
|
261 |
+
"learning_rate": 3.7065900212524865e-06,
|
262 |
+
"loss": 0.8301,
|
263 |
+
"step": 170
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.21311142683174344,
|
267 |
+
"grad_norm": 1.9170456106220028,
|
268 |
+
"learning_rate": 3.6415556136039017e-06,
|
269 |
+
"loss": 0.9021,
|
270 |
+
"step": 175
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.21920032474122184,
|
274 |
+
"grad_norm": 2.2610666535764716,
|
275 |
+
"learning_rate": 3.57727188517153e-06,
|
276 |
+
"loss": 0.925,
|
277 |
+
"step": 180
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 0.22528922265070023,
|
281 |
+
"grad_norm": 2.4930543513110566,
|
282 |
+
"learning_rate": 3.513735925192236e-06,
|
283 |
+
"loss": 0.861,
|
284 |
+
"step": 185
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.23137812056017862,
|
288 |
+
"grad_norm": 2.1552816913331334,
|
289 |
+
"learning_rate": 3.4509448115279674e-06,
|
290 |
+
"loss": 1.1969,
|
291 |
+
"step": 190
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.23746701846965698,
|
295 |
+
"grad_norm": 1.8621642100291538,
|
296 |
+
"learning_rate": 3.388895610531349e-06,
|
297 |
+
"loss": 0.8704,
|
298 |
+
"step": 195
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.24355591637913537,
|
302 |
+
"grad_norm": 2.1209832615085285,
|
303 |
+
"learning_rate": 3.3275853769086063e-06,
|
304 |
+
"loss": 0.9503,
|
305 |
+
"step": 200
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.24964481428861376,
|
309 |
+
"grad_norm": 2.237393861143882,
|
310 |
+
"learning_rate": 3.267011153579745e-06,
|
311 |
+
"loss": 0.9347,
|
312 |
+
"step": 205
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.25573371219809216,
|
316 |
+
"grad_norm": 2.2028682955334964,
|
317 |
+
"learning_rate": 3.2071699715359122e-06,
|
318 |
+
"loss": 0.8733,
|
319 |
+
"step": 210
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.2618226101075705,
|
323 |
+
"grad_norm": 2.1266652440547475,
|
324 |
+
"learning_rate": 3.148058849693859e-06,
|
325 |
+
"loss": 1.065,
|
326 |
+
"step": 215
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.26791150801704894,
|
330 |
+
"grad_norm": 2.285707011170251,
|
331 |
+
"learning_rate": 3.0896747947474105e-06,
|
332 |
+
"loss": 0.9307,
|
333 |
+
"step": 220
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.2740004059265273,
|
337 |
+
"grad_norm": 2.5710181491838737,
|
338 |
+
"learning_rate": 3.0320148010158774e-06,
|
339 |
+
"loss": 1.0314,
|
340 |
+
"step": 225
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.28008930383600567,
|
344 |
+
"grad_norm": 2.292322109336443,
|
345 |
+
"learning_rate": 2.975075850289298e-06,
|
346 |
+
"loss": 0.9115,
|
347 |
+
"step": 230
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.2861782017454841,
|
351 |
+
"grad_norm": 2.1450080532027025,
|
352 |
+
"learning_rate": 2.9188549116704386e-06,
|
353 |
+
"loss": 1.0111,
|
354 |
+
"step": 235
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.29226709965496245,
|
358 |
+
"grad_norm": 2.1135370162342717,
|
359 |
+
"learning_rate": 2.8633489414134293e-06,
|
360 |
+
"loss": 1.091,
|
361 |
+
"step": 240
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.29226709965496245,
|
365 |
+
"eval_loss": 0.9108514189720154,
|
366 |
+
"eval_runtime": 10.044,
|
367 |
+
"eval_samples_per_second": 19.912,
|
368 |
+
"eval_steps_per_second": 4.978,
|
369 |
+
"step": 240
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.2983559975644408,
|
373 |
+
"grad_norm": 1.8496992962121142,
|
374 |
+
"learning_rate": 2.8085548827589632e-06,
|
375 |
+
"loss": 0.9449,
|
376 |
+
"step": 245
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 0.30444489547391923,
|
380 |
+
"grad_norm": 2.2350891035464615,
|
381 |
+
"learning_rate": 2.7544696657659385e-06,
|
382 |
+
"loss": 1.0587,
|
383 |
+
"step": 250
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.3105337933833976,
|
387 |
+
"grad_norm": 2.6722037220078767,
|
388 |
+
"learning_rate": 2.7010902071394348e-06,
|
389 |
+
"loss": 0.7525,
|
390 |
+
"step": 255
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.316622691292876,
|
394 |
+
"grad_norm": 2.277080303923668,
|
395 |
+
"learning_rate": 2.6484134100549204e-06,
|
396 |
+
"loss": 0.8815,
|
397 |
+
"step": 260
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 0.3227115892023544,
|
401 |
+
"grad_norm": 2.0493281130802616,
|
402 |
+
"learning_rate": 2.5964361639785647e-06,
|
403 |
+
"loss": 1.1089,
|
404 |
+
"step": 265
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.32880048711183274,
|
408 |
+
"grad_norm": 2.042407938817224,
|
409 |
+
"learning_rate": 2.5451553444835415e-06,
|
410 |
+
"loss": 1.0962,
|
411 |
+
"step": 270
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.33488938502131116,
|
415 |
+
"grad_norm": 2.4634190870687287,
|
416 |
+
"learning_rate": 2.4945678130621847e-06,
|
417 |
+
"loss": 0.981,
|
418 |
+
"step": 275
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 0.3409782829307895,
|
422 |
+
"grad_norm": 2.260346564740007,
|
423 |
+
"learning_rate": 2.4446704169338846e-06,
|
424 |
+
"loss": 0.8348,
|
425 |
+
"step": 280
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.3470671808402679,
|
429 |
+
"grad_norm": 2.1046411435401806,
|
430 |
+
"learning_rate": 2.3954599888485643e-06,
|
431 |
+
"loss": 0.7611,
|
432 |
+
"step": 285
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 0.3531560787497463,
|
436 |
+
"grad_norm": 2.192608175141679,
|
437 |
+
"learning_rate": 2.3469333468856106e-06,
|
438 |
+
"loss": 1.1149,
|
439 |
+
"step": 290
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 0.35924497665922467,
|
443 |
+
"grad_norm": 1.9896811996512633,
|
444 |
+
"learning_rate": 2.299087294248103e-06,
|
445 |
+
"loss": 0.8705,
|
446 |
+
"step": 295
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.3653338745687031,
|
450 |
+
"grad_norm": 2.342371852699277,
|
451 |
+
"learning_rate": 2.25191861905219e-06,
|
452 |
+
"loss": 0.7842,
|
453 |
+
"step": 300
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.37142277247818145,
|
457 |
+
"grad_norm": 2.7056358054268945,
|
458 |
+
"learning_rate": 2.205424094111439e-06,
|
459 |
+
"loss": 0.9357,
|
460 |
+
"step": 305
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 0.3775116703876598,
|
464 |
+
"grad_norm": 1.827000174010884,
|
465 |
+
"learning_rate": 2.1596004767160085e-06,
|
466 |
+
"loss": 1.088,
|
467 |
+
"step": 310
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.38360056829713823,
|
471 |
+
"grad_norm": 2.11667666402572,
|
472 |
+
"learning_rate": 2.1144445084064565e-06,
|
473 |
+
"loss": 1.0323,
|
474 |
+
"step": 315
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.3896894662066166,
|
478 |
+
"grad_norm": 1.9194964413075437,
|
479 |
+
"learning_rate": 2.069952914741992e-06,
|
480 |
+
"loss": 0.9087,
|
481 |
+
"step": 320
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.3896894662066166,
|
485 |
+
"eval_loss": 0.9030415415763855,
|
486 |
+
"eval_runtime": 10.0588,
|
487 |
+
"eval_samples_per_second": 19.883,
|
488 |
+
"eval_steps_per_second": 4.971,
|
489 |
+
"step": 320
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.39577836411609496,
|
493 |
+
"grad_norm": 2.379416328048356,
|
494 |
+
"learning_rate": 2.026122405062999e-06,
|
495 |
+
"loss": 0.9356,
|
496 |
+
"step": 325
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 0.4018672620255734,
|
500 |
+
"grad_norm": 2.3051629049862967,
|
501 |
+
"learning_rate": 1.982949672247615e-06,
|
502 |
+
"loss": 0.9179,
|
503 |
+
"step": 330
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 0.40795615993505174,
|
507 |
+
"grad_norm": 2.2745740533676724,
|
508 |
+
"learning_rate": 1.940431392462155e-06,
|
509 |
+
"loss": 0.9632,
|
510 |
+
"step": 335
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 0.41404505784453016,
|
514 |
+
"grad_norm": 2.2794095449818252,
|
515 |
+
"learning_rate": 1.8985642249051713e-06,
|
516 |
+
"loss": 0.8374,
|
517 |
+
"step": 340
|
518 |
+
},
|
519 |
+
{
|
520 |
+
"epoch": 0.4201339557540085,
|
521 |
+
"grad_norm": 1.9892966603109936,
|
522 |
+
"learning_rate": 1.8573448115449084e-06,
|
523 |
+
"loss": 0.8853,
|
524 |
+
"step": 345
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.4262228536634869,
|
528 |
+
"grad_norm": 1.9076114123449572,
|
529 |
+
"learning_rate": 1.8167697768499194e-06,
|
530 |
+
"loss": 1.006,
|
531 |
+
"step": 350
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.4323117515729653,
|
535 |
+
"grad_norm": 2.4400224099994183,
|
536 |
+
"learning_rate": 1.7768357275125856e-06,
|
537 |
+
"loss": 0.7937,
|
538 |
+
"step": 355
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 0.43840064948244367,
|
542 |
+
"grad_norm": 1.9229232682741382,
|
543 |
+
"learning_rate": 1.737539252165281e-06,
|
544 |
+
"loss": 0.937,
|
545 |
+
"step": 360
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 0.44448954739192204,
|
549 |
+
"grad_norm": 2.482169188918342,
|
550 |
+
"learning_rate": 1.6988769210889033e-06,
|
551 |
+
"loss": 0.8412,
|
552 |
+
"step": 365
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 0.45057844530140045,
|
556 |
+
"grad_norm": 2.0823727911627117,
|
557 |
+
"learning_rate": 1.6608452859134694e-06,
|
558 |
+
"loss": 1.0682,
|
559 |
+
"step": 370
|
560 |
+
},
|
561 |
+
{
|
562 |
+
"epoch": 0.4566673432108788,
|
563 |
+
"grad_norm": 2.1349739191332624,
|
564 |
+
"learning_rate": 1.6234408793104964e-06,
|
565 |
+
"loss": 0.9272,
|
566 |
+
"step": 375
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.46275624112035724,
|
570 |
+
"grad_norm": 2.30837580526881,
|
571 |
+
"learning_rate": 1.5866602146768156e-06,
|
572 |
+
"loss": 0.8386,
|
573 |
+
"step": 380
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.4688451390298356,
|
577 |
+
"grad_norm": 1.998746509174225,
|
578 |
+
"learning_rate": 1.55049978580951e-06,
|
579 |
+
"loss": 1.0616,
|
580 |
+
"step": 385
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 0.47493403693931396,
|
584 |
+
"grad_norm": 1.7126649948610602,
|
585 |
+
"learning_rate": 1.5149560665716053e-06,
|
586 |
+
"loss": 0.9667,
|
587 |
+
"step": 390
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.4810229348487924,
|
591 |
+
"grad_norm": 5.6311081714105935,
|
592 |
+
"learning_rate": 1.4800255105481483e-06,
|
593 |
+
"loss": 0.876,
|
594 |
+
"step": 395
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.48711183275827075,
|
598 |
+
"grad_norm": 2.3657992350084545,
|
599 |
+
"learning_rate": 1.445704550692281e-06,
|
600 |
+
"loss": 1.0107,
|
601 |
+
"step": 400
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 0.48711183275827075,
|
605 |
+
"eval_loss": 0.8974834680557251,
|
606 |
+
"eval_runtime": 10.0412,
|
607 |
+
"eval_samples_per_second": 19.918,
|
608 |
+
"eval_steps_per_second": 4.979,
|
609 |
+
"step": 400
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.4932007306677491,
|
613 |
+
"grad_norm": 1.7698636674115102,
|
614 |
+
"learning_rate": 1.4119895989608974e-06,
|
615 |
+
"loss": 0.9153,
|
616 |
+
"step": 405
|
617 |
+
},
|
618 |
+
{
|
619 |
+
"epoch": 0.49928962857722753,
|
620 |
+
"grad_norm": 2.054779528570307,
|
621 |
+
"learning_rate": 1.3788770459394496e-06,
|
622 |
+
"loss": 0.8891,
|
623 |
+
"step": 410
|
624 |
+
},
|
625 |
+
{
|
626 |
+
"epoch": 0.5053785264867059,
|
627 |
+
"grad_norm": 1.9369644275849407,
|
628 |
+
"learning_rate": 1.3463632604554425e-06,
|
629 |
+
"loss": 0.9571,
|
630 |
+
"step": 415
|
631 |
+
},
|
632 |
+
{
|
633 |
+
"epoch": 0.5114674243961843,
|
634 |
+
"grad_norm": 1.8987765645217645,
|
635 |
+
"learning_rate": 1.3144445891801363e-06,
|
636 |
+
"loss": 0.963,
|
637 |
+
"step": 420
|
638 |
+
},
|
639 |
+
{
|
640 |
+
"epoch": 0.5175563223056627,
|
641 |
+
"grad_norm": 2.403051805328199,
|
642 |
+
"learning_rate": 1.28311735621795e-06,
|
643 |
+
"loss": 1.1635,
|
644 |
+
"step": 425
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 0.523645220215141,
|
648 |
+
"grad_norm": 2.109077522246386,
|
649 |
+
"learning_rate": 1.252377862683016e-06,
|
650 |
+
"loss": 1.0585,
|
651 |
+
"step": 430
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 0.5297341181246195,
|
655 |
+
"grad_norm": 1.874133422791628,
|
656 |
+
"learning_rate": 1.222222386262332e-06,
|
657 |
+
"loss": 0.9143,
|
658 |
+
"step": 435
|
659 |
+
},
|
660 |
+
{
|
661 |
+
"epoch": 0.5358230160340979,
|
662 |
+
"grad_norm": 2.1929101428736177,
|
663 |
+
"learning_rate": 1.1926471807648967e-06,
|
664 |
+
"loss": 0.9188,
|
665 |
+
"step": 440
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 0.5419119139435762,
|
669 |
+
"grad_norm": 1.6260373540934423,
|
670 |
+
"learning_rate": 1.1636484756561917e-06,
|
671 |
+
"loss": 0.8914,
|
672 |
+
"step": 445
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 0.5480008118530546,
|
676 |
+
"grad_norm": 1.9739709292895855,
|
677 |
+
"learning_rate": 1.1352224755773445e-06,
|
678 |
+
"loss": 1.0831,
|
679 |
+
"step": 450
|
680 |
+
},
|
681 |
+
{
|
682 |
+
"epoch": 0.554089709762533,
|
683 |
+
"grad_norm": 2.023310630964453,
|
684 |
+
"learning_rate": 1.107365359848245e-06,
|
685 |
+
"loss": 1.0402,
|
686 |
+
"step": 455
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 0.5601786076720113,
|
690 |
+
"grad_norm": 2.466428732846668,
|
691 |
+
"learning_rate": 1.0800732819538616e-06,
|
692 |
+
"loss": 0.9395,
|
693 |
+
"step": 460
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.5662675055814897,
|
697 |
+
"grad_norm": 1.9030259115900607,
|
698 |
+
"learning_rate": 1.0533423690129516e-06,
|
699 |
+
"loss": 0.8586,
|
700 |
+
"step": 465
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"epoch": 0.5723564034909682,
|
704 |
+
"grad_norm": 2.1592861330197946,
|
705 |
+
"learning_rate": 1.0271687212283061e-06,
|
706 |
+
"loss": 0.9337,
|
707 |
+
"step": 470
|
708 |
+
},
|
709 |
+
{
|
710 |
+
"epoch": 0.5784453014004465,
|
711 |
+
"grad_norm": 2.356602817957484,
|
712 |
+
"learning_rate": 1.0015484113176207e-06,
|
713 |
+
"loss": 0.8562,
|
714 |
+
"step": 475
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.5845341993099249,
|
718 |
+
"grad_norm": 1.9750104030522446,
|
719 |
+
"learning_rate": 9.764774839240228e-07,
|
720 |
+
"loss": 0.9108,
|
721 |
+
"step": 480
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 0.5845341993099249,
|
725 |
+
"eval_loss": 0.8940006494522095,
|
726 |
+
"eval_runtime": 10.0627,
|
727 |
+
"eval_samples_per_second": 19.875,
|
728 |
+
"eval_steps_per_second": 4.969,
|
729 |
+
"step": 480
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.5906230972194033,
|
733 |
+
"grad_norm": 2.294181751504768,
|
734 |
+
"learning_rate": 9.519519550052165e-07,
|
735 |
+
"loss": 0.9483,
|
736 |
+
"step": 485
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"epoch": 0.5967119951288816,
|
740 |
+
"grad_norm": 2.390172284421488,
|
741 |
+
"learning_rate": 9.27967811200154e-07,
|
742 |
+
"loss": 0.9252,
|
743 |
+
"step": 490
|
744 |
+
},
|
745 |
+
{
|
746 |
+
"epoch": 0.60280089303836,
|
747 |
+
"grad_norm": 1.9195131453200192,
|
748 |
+
"learning_rate": 9.045210091720488e-07,
|
749 |
+
"loss": 1.045,
|
750 |
+
"step": 495
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 0.6088897909478385,
|
754 |
+
"grad_norm": 2.3087652972941957,
|
755 |
+
"learning_rate": 8.816074749264782e-07,
|
756 |
+
"loss": 0.8324,
|
757 |
+
"step": 500
|
758 |
+
},
|
759 |
+
{
|
760 |
+
"epoch": 0.6149786888573169,
|
761 |
+
"grad_norm": 1.887331233479458,
|
762 |
+
"learning_rate": 8.592231031032369e-07,
|
763 |
+
"loss": 0.9797,
|
764 |
+
"step": 505
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 0.6210675867667952,
|
768 |
+
"grad_norm": 2.546311216104545,
|
769 |
+
"learning_rate": 8.37363756240493e-07,
|
770 |
+
"loss": 0.9758,
|
771 |
+
"step": 510
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.6271564846762736,
|
775 |
+
"grad_norm": 2.052324183223674,
|
776 |
+
"learning_rate": 8.160252640097203e-07,
|
777 |
+
"loss": 0.9379,
|
778 |
+
"step": 515
|
779 |
+
},
|
780 |
+
{
|
781 |
+
"epoch": 0.633245382585752,
|
782 |
+
"grad_norm": 1.8162505508545923,
|
783 |
+
"learning_rate": 7.952034224197429e-07,
|
784 |
+
"loss": 1.0445,
|
785 |
+
"step": 520
|
786 |
+
},
|
787 |
+
{
|
788 |
+
"epoch": 0.6393342804952303,
|
789 |
+
"grad_norm": 1.9039113307487847,
|
790 |
+
"learning_rate": 7.748939929881281e-07,
|
791 |
+
"loss": 0.9693,
|
792 |
+
"step": 525
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 0.6454231784047088,
|
796 |
+
"grad_norm": 1.7791797404105452,
|
797 |
+
"learning_rate": 7.5509270187801e-07,
|
798 |
+
"loss": 1.1654,
|
799 |
+
"step": 530
|
800 |
+
},
|
801 |
+
{
|
802 |
+
"epoch": 0.6515120763141872,
|
803 |
+
"grad_norm": 2.2713665666241023,
|
804 |
+
"learning_rate": 7.357952389983003e-07,
|
805 |
+
"loss": 1.0812,
|
806 |
+
"step": 535
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 0.6576009742236655,
|
810 |
+
"grad_norm": 2.7771426272207926,
|
811 |
+
"learning_rate": 7.169972570650695e-07,
|
812 |
+
"loss": 1.0663,
|
813 |
+
"step": 540
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.6636898721331439,
|
817 |
+
"grad_norm": 2.1095605296190794,
|
818 |
+
"learning_rate": 6.986943706217093e-07,
|
819 |
+
"loss": 1.2464,
|
820 |
+
"step": 545
|
821 |
+
},
|
822 |
+
{
|
823 |
+
"epoch": 0.6697787700426223,
|
824 |
+
"grad_norm": 2.165590845905102,
|
825 |
+
"learning_rate": 6.808821550153036e-07,
|
826 |
+
"loss": 1.1615,
|
827 |
+
"step": 550
|
828 |
+
},
|
829 |
+
{
|
830 |
+
"epoch": 0.6758676679521006,
|
831 |
+
"grad_norm": 2.098201375795868,
|
832 |
+
"learning_rate": 6.635561453264081e-07,
|
833 |
+
"loss": 1.2256,
|
834 |
+
"step": 555
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.681956565861579,
|
838 |
+
"grad_norm": 1.597477657082927,
|
839 |
+
"learning_rate": 6.467118352492235e-07,
|
840 |
+
"loss": 1.1531,
|
841 |
+
"step": 560
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 0.681956565861579,
|
845 |
+
"eval_loss": 0.9038890600204468,
|
846 |
+
"eval_runtime": 10.0714,
|
847 |
+
"eval_samples_per_second": 19.858,
|
848 |
+
"eval_steps_per_second": 4.965,
|
849 |
+
"step": 560
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.6880454637710575,
|
853 |
+
"grad_norm": 1.9610561566970353,
|
854 |
+
"learning_rate": 6.303446759188759e-07,
|
855 |
+
"loss": 1.1032,
|
856 |
+
"step": 565
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.6941343616805358,
|
860 |
+
"grad_norm": 1.8771579285205593,
|
861 |
+
"learning_rate": 6.14450074682243e-07,
|
862 |
+
"loss": 1.0247,
|
863 |
+
"step": 570
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.7002232595900142,
|
867 |
+
"grad_norm": 1.9428546209099045,
|
868 |
+
"learning_rate": 5.990233938084431e-07,
|
869 |
+
"loss": 0.9957,
|
870 |
+
"step": 575
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.7063121574994926,
|
874 |
+
"grad_norm": 2.0685369493893453,
|
875 |
+
"learning_rate": 5.840599491347582e-07,
|
876 |
+
"loss": 1.073,
|
877 |
+
"step": 580
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.712401055408971,
|
881 |
+
"grad_norm": 1.4232455246953637,
|
882 |
+
"learning_rate": 5.695550086433726e-07,
|
883 |
+
"loss": 1.17,
|
884 |
+
"step": 585
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.7184899533184493,
|
888 |
+
"grad_norm": 1.9953305653364002,
|
889 |
+
"learning_rate": 5.555037909638744e-07,
|
890 |
+
"loss": 1.0394,
|
891 |
+
"step": 590
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.7245788512279278,
|
895 |
+
"grad_norm": 2.234757544147466,
|
896 |
+
"learning_rate": 5.419014637959808e-07,
|
897 |
+
"loss": 1.1472,
|
898 |
+
"step": 595
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.7306677491374062,
|
902 |
+
"grad_norm": 2.2367049852297876,
|
903 |
+
"learning_rate": 5.287431422464098e-07,
|
904 |
+
"loss": 1.0496,
|
905 |
+
"step": 600
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.7367566470468845,
|
909 |
+
"grad_norm": 2.2212989204910367,
|
910 |
+
"learning_rate": 5.160238870732056e-07,
|
911 |
+
"loss": 0.9907,
|
912 |
+
"step": 605
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.7428455449563629,
|
916 |
+
"grad_norm": 1.8355911585139566,
|
917 |
+
"learning_rate": 5.037387028301462e-07,
|
918 |
+
"loss": 1.3347,
|
919 |
+
"step": 610
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.7489344428658413,
|
923 |
+
"grad_norm": 2.172477947251129,
|
924 |
+
"learning_rate": 4.918825359030837e-07,
|
925 |
+
"loss": 1.1386,
|
926 |
+
"step": 615
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.7550233407753196,
|
930 |
+
"grad_norm": 1.8047316252716201,
|
931 |
+
"learning_rate": 4.804502724291952e-07,
|
932 |
+
"loss": 1.1201,
|
933 |
+
"step": 620
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.761112238684798,
|
937 |
+
"grad_norm": 1.8666031715794023,
|
938 |
+
"learning_rate": 4.6943673608912795e-07,
|
939 |
+
"loss": 1.0354,
|
940 |
+
"step": 625
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.7672011365942765,
|
944 |
+
"grad_norm": 1.948049167249183,
|
945 |
+
"learning_rate": 4.588366857608947e-07,
|
946 |
+
"loss": 0.9314,
|
947 |
+
"step": 630
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.7732900345037548,
|
951 |
+
"grad_norm": 1.9360471601880767,
|
952 |
+
"learning_rate": 4.4864481302308764e-07,
|
953 |
+
"loss": 1.3016,
|
954 |
+
"step": 635
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.7793789324132332,
|
958 |
+
"grad_norm": 1.7603394486420607,
|
959 |
+
"learning_rate": 4.388557394934996e-07,
|
960 |
+
"loss": 1.2698,
|
961 |
+
"step": 640
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.7793789324132332,
|
965 |
+
"eval_loss": 0.9068670868873596,
|
966 |
+
"eval_runtime": 10.0454,
|
967 |
+
"eval_samples_per_second": 19.91,
|
968 |
+
"eval_steps_per_second": 4.977,
|
969 |
+
"step": 640
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.7854678303227116,
|
973 |
+
"grad_norm": 1.8121869716312213,
|
974 |
+
"learning_rate": 4.2946401398754887e-07,
|
975 |
+
"loss": 1.0936,
|
976 |
+
"step": 645
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 0.7915567282321899,
|
980 |
+
"grad_norm": 2.2784724809217116,
|
981 |
+
"learning_rate": 4.20464109478947e-07,
|
982 |
+
"loss": 1.0688,
|
983 |
+
"step": 650
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 0.7976456261416683,
|
987 |
+
"grad_norm": 1.9511498628400707,
|
988 |
+
"learning_rate": 4.118504198427839e-07,
|
989 |
+
"loss": 1.2066,
|
990 |
+
"step": 655
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 0.8037345240511468,
|
994 |
+
"grad_norm": 1.6886651269860387,
|
995 |
+
"learning_rate": 4.036172563585779e-07,
|
996 |
+
"loss": 1.0209,
|
997 |
+
"step": 660
|
998 |
+
},
|
999 |
+
{
|
1000 |
+
"epoch": 0.8098234219606252,
|
1001 |
+
"grad_norm": 1.770877392703053,
|
1002 |
+
"learning_rate": 3.957588439477604e-07,
|
1003 |
+
"loss": 1.1583,
|
1004 |
+
"step": 665
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 0.8159123198701035,
|
1008 |
+
"grad_norm": 2.1758718521360385,
|
1009 |
+
"learning_rate": 3.8826931711647146e-07,
|
1010 |
+
"loss": 1.0352,
|
1011 |
+
"step": 670
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.8220012177795819,
|
1015 |
+
"grad_norm": 2.003054070991938,
|
1016 |
+
"learning_rate": 3.8114271557029493e-07,
|
1017 |
+
"loss": 1.1568,
|
1018 |
+
"step": 675
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 0.8280901156890603,
|
1022 |
+
"grad_norm": 2.167247263874176,
|
1023 |
+
"learning_rate": 3.74372979462545e-07,
|
1024 |
+
"loss": 1.0868,
|
1025 |
+
"step": 680
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 0.8341790135985386,
|
1029 |
+
"grad_norm": 1.8384381989648775,
|
1030 |
+
"learning_rate": 3.679539442317327e-07,
|
1031 |
+
"loss": 1.1053,
|
1032 |
+
"step": 685
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 0.840267911508017,
|
1036 |
+
"grad_norm": 2.1673707360409877,
|
1037 |
+
"learning_rate": 3.6187933497668937e-07,
|
1038 |
+
"loss": 1.1503,
|
1039 |
+
"step": 690
|
1040 |
+
},
|
1041 |
+
{
|
1042 |
+
"epoch": 0.8463568094174955,
|
1043 |
+
"grad_norm": 1.9246135785489056,
|
1044 |
+
"learning_rate": 3.5614276030919706e-07,
|
1045 |
+
"loss": 1.0148,
|
1046 |
+
"step": 695
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.8524457073269738,
|
1050 |
+
"grad_norm": 1.675592035681543,
|
1051 |
+
"learning_rate": 3.507377056135281e-07,
|
1052 |
+
"loss": 1.0533,
|
1053 |
+
"step": 700
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.8585346052364522,
|
1057 |
+
"grad_norm": 1.58433949898804,
|
1058 |
+
"learning_rate": 3.456575256295274e-07,
|
1059 |
+
"loss": 0.9223,
|
1060 |
+
"step": 705
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 0.8646235031459306,
|
1064 |
+
"grad_norm": 1.5089882230199272,
|
1065 |
+
"learning_rate": 3.408954362601715e-07,
|
1066 |
+
"loss": 1.1612,
|
1067 |
+
"step": 710
|
1068 |
+
},
|
1069 |
+
{
|
1070 |
+
"epoch": 0.8707124010554089,
|
1071 |
+
"grad_norm": 1.8812149702939354,
|
1072 |
+
"learning_rate": 3.364445054850564e-07,
|
1073 |
+
"loss": 1.1011,
|
1074 |
+
"step": 715
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.8768012989648873,
|
1078 |
+
"grad_norm": 1.8009898237225854,
|
1079 |
+
"learning_rate": 3.322976432368887e-07,
|
1080 |
+
"loss": 1.1988,
|
1081 |
+
"step": 720
|
1082 |
+
},
|
1083 |
+
{
|
1084 |
+
"epoch": 0.8768012989648873,
|
1085 |
+
"eval_loss": 0.9062988758087158,
|
1086 |
+
"eval_runtime": 10.0522,
|
1087 |
+
"eval_samples_per_second": 19.896,
|
1088 |
+
"eval_steps_per_second": 4.974,
|
1089 |
+
"step": 720
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.8828901968743658,
|
1093 |
+
"grad_norm": 2.0516728550272494,
|
1094 |
+
"learning_rate": 3.284475900672534e-07,
|
1095 |
+
"loss": 1.217,
|
1096 |
+
"step": 725
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 0.8889790947838441,
|
1100 |
+
"grad_norm": 1.8636754853646536,
|
1101 |
+
"learning_rate": 3.2488690438860155e-07,
|
1102 |
+
"loss": 1.05,
|
1103 |
+
"step": 730
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 0.8950679926933225,
|
1107 |
+
"grad_norm": 2.0197164306265973,
|
1108 |
+
"learning_rate": 3.216079480286014e-07,
|
1109 |
+
"loss": 1.083,
|
1110 |
+
"step": 735
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 0.9011568906028009,
|
1114 |
+
"grad_norm": 1.7192487834075223,
|
1115 |
+
"learning_rate": 3.186028697665536e-07,
|
1116 |
+
"loss": 0.9577,
|
1117 |
+
"step": 740
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"epoch": 0.9072457885122793,
|
1121 |
+
"grad_norm": 1.9547679875155324,
|
1122 |
+
"learning_rate": 3.1586358643344154e-07,
|
1123 |
+
"loss": 1.0405,
|
1124 |
+
"step": 745
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 0.9133346864217576,
|
1128 |
+
"grad_norm": 2.0062949300387847,
|
1129 |
+
"learning_rate": 3.1338176103847303e-07,
|
1130 |
+
"loss": 1.1779,
|
1131 |
+
"step": 750
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.919423584331236,
|
1135 |
+
"grad_norm": 1.5531676528239142,
|
1136 |
+
"learning_rate": 3.111487772222592e-07,
|
1137 |
+
"loss": 1.1676,
|
1138 |
+
"step": 755
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 0.9255124822407145,
|
1142 |
+
"grad_norm": 1.5372578345670411,
|
1143 |
+
"learning_rate": 3.0915570910938297e-07,
|
1144 |
+
"loss": 1.0719,
|
1145 |
+
"step": 760
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 0.9316013801501928,
|
1149 |
+
"grad_norm": 2.1454113233082706,
|
1150 |
+
"learning_rate": 3.07393285308207e-07,
|
1151 |
+
"loss": 1.0105,
|
1152 |
+
"step": 765
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 0.9376902780596712,
|
1156 |
+
"grad_norm": 1.5547170974986044,
|
1157 |
+
"learning_rate": 3.0585184532967033e-07,
|
1158 |
+
"loss": 1.0721,
|
1159 |
+
"step": 770
|
1160 |
+
},
|
1161 |
+
{
|
1162 |
+
"epoch": 0.9437791759691496,
|
1163 |
+
"grad_norm": 1.852645012921805,
|
1164 |
+
"learning_rate": 3.045212859784411e-07,
|
1165 |
+
"loss": 1.0933,
|
1166 |
+
"step": 775
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 0.9498680738786279,
|
1170 |
+
"grad_norm": 1.8094221288522232,
|
1171 |
+
"learning_rate": 3.033909941480833e-07,
|
1172 |
+
"loss": 0.9671,
|
1173 |
+
"step": 780
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.9559569717881063,
|
1177 |
+
"grad_norm": 1.5561960733621902,
|
1178 |
+
"learning_rate": 3.024497606276943e-07,
|
1179 |
+
"loss": 1.1151,
|
1180 |
+
"step": 785
|
1181 |
+
},
|
1182 |
+
{
|
1183 |
+
"epoch": 0.9620458696975848,
|
1184 |
+
"grad_norm": 1.84094988169291,
|
1185 |
+
"learning_rate": 3.016856664111943e-07,
|
1186 |
+
"loss": 0.9727,
|
1187 |
+
"step": 790
|
1188 |
+
},
|
1189 |
+
{
|
1190 |
+
"epoch": 0.9681347676070631,
|
1191 |
+
"grad_norm": 1.8600686188407434,
|
1192 |
+
"learning_rate": 3.0108592734273526e-07,
|
1193 |
+
"loss": 1.1713,
|
1194 |
+
"step": 795
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.9742236655165415,
|
1198 |
+
"grad_norm": 1.9971464440071154,
|
1199 |
+
"learning_rate": 3.006366718310598e-07,
|
1200 |
+
"loss": 1.1649,
|
1201 |
+
"step": 800
|
1202 |
+
},
|
1203 |
+
{
|
1204 |
+
"epoch": 0.9742236655165415,
|
1205 |
+
"eval_loss": 0.9046012759208679,
|
1206 |
+
"eval_runtime": 10.0656,
|
1207 |
+
"eval_samples_per_second": 19.87,
|
1208 |
+
"eval_steps_per_second": 4.967,
|
1209 |
+
"step": 800
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.9803125634260199,
|
1213 |
+
"grad_norm": 1.801943230059916,
|
1214 |
+
"learning_rate": 3.00322602222577e-07,
|
1215 |
+
"loss": 1.0695,
|
1216 |
+
"step": 805
|
1217 |
+
},
|
1218 |
+
{
|
1219 |
+
"epoch": 0.9864014613354982,
|
1220 |
+
"grad_norm": 1.839016967735732,
|
1221 |
+
"learning_rate": 3.001264297011597e-07,
|
1222 |
+
"loss": 0.9731,
|
1223 |
+
"step": 810
|
1224 |
+
},
|
1225 |
+
{
|
1226 |
+
"epoch": 0.9924903592449766,
|
1227 |
+
"grad_norm": 1.9692055921355986,
|
1228 |
+
"learning_rate": 3.00027780849675e-07,
|
1229 |
+
"loss": 0.9058,
|
1230 |
+
"step": 815
|
1231 |
+
},
|
1232 |
+
{
|
1233 |
+
"epoch": 0.9985792571544551,
|
1234 |
+
"grad_norm": 2.8720134735995413,
|
1235 |
+
"learning_rate": 3.0000031504123295e-07,
|
1236 |
+
"loss": 1.2194,
|
1237 |
+
"step": 820
|
1238 |
+
},
|
1239 |
+
{
|
1240 |
+
"epoch": 0.9997970367363507,
|
1241 |
+
"step": 821,
|
1242 |
+
"total_flos": 1.4841304991137792e+17,
|
1243 |
+
"train_loss": 1.0157385155576737,
|
1244 |
+
"train_runtime": 6062.254,
|
1245 |
+
"train_samples_per_second": 4.876,
|
1246 |
+
"train_steps_per_second": 0.135
|
1247 |
+
}
|
1248 |
+
],
|
1249 |
+
"logging_steps": 5,
|
1250 |
+
"max_steps": 821,
|
1251 |
+
"num_input_tokens_seen": 0,
|
1252 |
+
"num_train_epochs": 1,
|
1253 |
+
"save_steps": 821,
|
1254 |
+
"stateful_callbacks": {
|
1255 |
+
"TrainerControl": {
|
1256 |
+
"args": {
|
1257 |
+
"should_epoch_stop": false,
|
1258 |
+
"should_evaluate": false,
|
1259 |
+
"should_log": false,
|
1260 |
+
"should_save": true,
|
1261 |
+
"should_training_stop": true
|
1262 |
+
},
|
1263 |
+
"attributes": {}
|
1264 |
+
}
|
1265 |
+
},
|
1266 |
+
"total_flos": 1.4841304991137792e+17,
|
1267 |
+
"train_batch_size": 3,
|
1268 |
+
"trial_name": null,
|
1269 |
+
"trial_params": null
|
1270 |
+
}
|