sedrickkeh
commited on
Commit
•
11f8c1d
1
Parent(s):
a4a2985
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 +983 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
4 |
base_model: Qwen/Qwen2.5-7B
|
5 |
tags:
|
6 |
- llama-factory
|
|
|
7 |
- generated_from_trainer
|
8 |
model-index:
|
9 |
- name: hp_ablations_qwen_scheduler_cosine_warmup0.10
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# hp_ablations_qwen_scheduler_cosine_warmup0.10
|
17 |
|
18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.6208
|
21 |
|
|
|
4 |
base_model: Qwen/Qwen2.5-7B
|
5 |
tags:
|
6 |
- llama-factory
|
7 |
+
- full
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
- name: hp_ablations_qwen_scheduler_cosine_warmup0.10
|
|
|
16 |
|
17 |
# hp_ablations_qwen_scheduler_cosine_warmup0.10
|
18 |
|
19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 0.6208
|
22 |
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.996011396011396,
|
3 |
+
"eval_loss": 0.6208292245864868,
|
4 |
+
"eval_runtime": 447.515,
|
5 |
+
"eval_samples_per_second": 26.419,
|
6 |
+
"eval_steps_per_second": 0.413,
|
7 |
+
"total_flos": 2755219238682624.0,
|
8 |
+
"train_loss": 0.6149487337565314,
|
9 |
+
"train_runtime": 70718.2917,
|
10 |
+
"train_samples_per_second": 9.529,
|
11 |
+
"train_steps_per_second": 0.019
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.996011396011396,
|
3 |
+
"eval_loss": 0.6208292245864868,
|
4 |
+
"eval_runtime": 447.515,
|
5 |
+
"eval_samples_per_second": 26.419,
|
6 |
+
"eval_steps_per_second": 0.413
|
7 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.996011396011396,
|
3 |
+
"total_flos": 2755219238682624.0,
|
4 |
+
"train_loss": 0.6149487337565314,
|
5 |
+
"train_runtime": 70718.2917,
|
6 |
+
"train_samples_per_second": 9.529,
|
7 |
+
"train_steps_per_second": 0.019
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,983 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.996011396011396,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1314,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.022792022792022793,
|
13 |
+
"grad_norm": 14.146444752534505,
|
14 |
+
"learning_rate": 3.787878787878788e-07,
|
15 |
+
"loss": 0.8308,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.045584045584045586,
|
20 |
+
"grad_norm": 5.153758366693143,
|
21 |
+
"learning_rate": 7.575757575757576e-07,
|
22 |
+
"loss": 0.8105,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.06837606837606838,
|
27 |
+
"grad_norm": 1.5542878010616328,
|
28 |
+
"learning_rate": 1.1363636363636364e-06,
|
29 |
+
"loss": 0.7548,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.09116809116809117,
|
34 |
+
"grad_norm": 1.013899964163002,
|
35 |
+
"learning_rate": 1.5151515151515152e-06,
|
36 |
+
"loss": 0.7306,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.11396011396011396,
|
41 |
+
"grad_norm": 0.9161511187960373,
|
42 |
+
"learning_rate": 1.8939393939393941e-06,
|
43 |
+
"loss": 0.7157,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.13675213675213677,
|
48 |
+
"grad_norm": 0.8586592268438875,
|
49 |
+
"learning_rate": 2.2727272727272728e-06,
|
50 |
+
"loss": 0.6902,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.15954415954415954,
|
55 |
+
"grad_norm": 0.7309111880606206,
|
56 |
+
"learning_rate": 2.6515151515151514e-06,
|
57 |
+
"loss": 0.6845,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.18233618233618235,
|
62 |
+
"grad_norm": 0.8696315292996867,
|
63 |
+
"learning_rate": 3.0303030303030305e-06,
|
64 |
+
"loss": 0.6844,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.20512820512820512,
|
69 |
+
"grad_norm": 0.7998963491106827,
|
70 |
+
"learning_rate": 3.409090909090909e-06,
|
71 |
+
"loss": 0.6652,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.22792022792022792,
|
76 |
+
"grad_norm": 0.8523349303133146,
|
77 |
+
"learning_rate": 3.7878787878787882e-06,
|
78 |
+
"loss": 0.6617,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.25071225071225073,
|
83 |
+
"grad_norm": 0.6685447974331892,
|
84 |
+
"learning_rate": 4.166666666666667e-06,
|
85 |
+
"loss": 0.6479,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.27350427350427353,
|
90 |
+
"grad_norm": 0.5230920487997709,
|
91 |
+
"learning_rate": 4.5454545454545455e-06,
|
92 |
+
"loss": 0.6519,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.2962962962962963,
|
97 |
+
"grad_norm": 0.37258325894749,
|
98 |
+
"learning_rate": 4.924242424242425e-06,
|
99 |
+
"loss": 0.6501,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.3190883190883191,
|
104 |
+
"grad_norm": 0.3421753272014553,
|
105 |
+
"learning_rate": 4.999434882941783e-06,
|
106 |
+
"loss": 0.6507,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.3418803418803419,
|
111 |
+
"grad_norm": 0.32126906628196517,
|
112 |
+
"learning_rate": 4.997139532754547e-06,
|
113 |
+
"loss": 0.6424,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.3646723646723647,
|
118 |
+
"grad_norm": 0.3197148648781906,
|
119 |
+
"learning_rate": 4.993080249767159e-06,
|
120 |
+
"loss": 0.6469,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.38746438746438744,
|
125 |
+
"grad_norm": 0.36121332119458893,
|
126 |
+
"learning_rate": 4.987259901381426e-06,
|
127 |
+
"loss": 0.6383,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.41025641025641024,
|
132 |
+
"grad_norm": 0.314124834735473,
|
133 |
+
"learning_rate": 4.979682598982912e-06,
|
134 |
+
"loss": 0.6435,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.43304843304843305,
|
139 |
+
"grad_norm": 0.3036806041853383,
|
140 |
+
"learning_rate": 4.970353695036733e-06,
|
141 |
+
"loss": 0.6357,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.45584045584045585,
|
146 |
+
"grad_norm": 0.3559103875504945,
|
147 |
+
"learning_rate": 4.959279779306672e-06,
|
148 |
+
"loss": 0.6437,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.47863247863247865,
|
153 |
+
"grad_norm": 0.31838294132396994,
|
154 |
+
"learning_rate": 4.9464686742003e-06,
|
155 |
+
"loss": 0.6397,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.5014245014245015,
|
160 |
+
"grad_norm": 0.31931288370247984,
|
161 |
+
"learning_rate": 4.931929429243368e-06,
|
162 |
+
"loss": 0.6433,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.5242165242165242,
|
167 |
+
"grad_norm": 0.3387661303053822,
|
168 |
+
"learning_rate": 4.915672314687389e-06,
|
169 |
+
"loss": 0.6386,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.5470085470085471,
|
174 |
+
"grad_norm": 0.307483802697865,
|
175 |
+
"learning_rate": 4.897708814254929e-06,
|
176 |
+
"loss": 0.6344,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.5698005698005698,
|
181 |
+
"grad_norm": 0.32874061771123697,
|
182 |
+
"learning_rate": 4.878051617027716e-06,
|
183 |
+
"loss": 0.6392,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.5925925925925926,
|
188 |
+
"grad_norm": 0.30196467550126727,
|
189 |
+
"learning_rate": 4.856714608483312e-06,
|
190 |
+
"loss": 0.6372,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.6153846153846154,
|
195 |
+
"grad_norm": 0.31343992161469575,
|
196 |
+
"learning_rate": 4.833712860686666e-06,
|
197 |
+
"loss": 0.6342,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.6381766381766382,
|
202 |
+
"grad_norm": 0.31574574613486234,
|
203 |
+
"learning_rate": 4.809062621643494e-06,
|
204 |
+
"loss": 0.6449,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.6609686609686609,
|
209 |
+
"grad_norm": 0.32324064230462446,
|
210 |
+
"learning_rate": 4.782781303822987e-06,
|
211 |
+
"loss": 0.6335,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.6837606837606838,
|
216 |
+
"grad_norm": 0.287913175925187,
|
217 |
+
"learning_rate": 4.75488747185797e-06,
|
218 |
+
"loss": 0.6314,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.7065527065527065,
|
223 |
+
"grad_norm": 0.29874584820110867,
|
224 |
+
"learning_rate": 4.7254008294311856e-06,
|
225 |
+
"loss": 0.6312,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.7293447293447294,
|
230 |
+
"grad_norm": 0.3296980657627112,
|
231 |
+
"learning_rate": 4.694342205356989e-06,
|
232 |
+
"loss": 0.6317,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.7521367521367521,
|
237 |
+
"grad_norm": 0.29794479816918795,
|
238 |
+
"learning_rate": 4.661733538868256e-06,
|
239 |
+
"loss": 0.6283,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.7749287749287749,
|
244 |
+
"grad_norm": 0.3170073715761538,
|
245 |
+
"learning_rate": 4.627597864118919e-06,
|
246 |
+
"loss": 0.634,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.7977207977207977,
|
251 |
+
"grad_norm": 0.32128376305549455,
|
252 |
+
"learning_rate": 4.591959293913071e-06,
|
253 |
+
"loss": 0.6411,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.8205128205128205,
|
258 |
+
"grad_norm": 0.3204925483417397,
|
259 |
+
"learning_rate": 4.554843002672129e-06,
|
260 |
+
"loss": 0.6328,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.8433048433048433,
|
265 |
+
"grad_norm": 0.3329534096064245,
|
266 |
+
"learning_rate": 4.516275208652094e-06,
|
267 |
+
"loss": 0.6265,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.8660968660968661,
|
272 |
+
"grad_norm": 0.32160572276482535,
|
273 |
+
"learning_rate": 4.4762831554234655e-06,
|
274 |
+
"loss": 0.6387,
|
275 |
+
"step": 380
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.8888888888888888,
|
279 |
+
"grad_norm": 0.30402339621917396,
|
280 |
+
"learning_rate": 4.434895092626883e-06,
|
281 |
+
"loss": 0.6372,
|
282 |
+
"step": 390
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.9116809116809117,
|
286 |
+
"grad_norm": 0.30894589289734836,
|
287 |
+
"learning_rate": 4.392140256018117e-06,
|
288 |
+
"loss": 0.6404,
|
289 |
+
"step": 400
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.9344729344729344,
|
293 |
+
"grad_norm": 0.2721461491779075,
|
294 |
+
"learning_rate": 4.348048846816472e-06,
|
295 |
+
"loss": 0.6366,
|
296 |
+
"step": 410
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.9572649572649573,
|
300 |
+
"grad_norm": 0.2931868634895431,
|
301 |
+
"learning_rate": 4.302652010371205e-06,
|
302 |
+
"loss": 0.6234,
|
303 |
+
"step": 420
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.98005698005698,
|
307 |
+
"grad_norm": 0.33224372295864196,
|
308 |
+
"learning_rate": 4.255981814161038e-06,
|
309 |
+
"loss": 0.6365,
|
310 |
+
"step": 430
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.9982905982905983,
|
314 |
+
"eval_loss": 0.6270219683647156,
|
315 |
+
"eval_runtime": 441.4607,
|
316 |
+
"eval_samples_per_second": 26.782,
|
317 |
+
"eval_steps_per_second": 0.419,
|
318 |
+
"step": 438
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 1.0034188034188034,
|
322 |
+
"grad_norm": 0.30982191873103315,
|
323 |
+
"learning_rate": 4.208071225142283e-06,
|
324 |
+
"loss": 0.6498,
|
325 |
+
"step": 440
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 1.0262108262108263,
|
329 |
+
"grad_norm": 0.3223209055964483,
|
330 |
+
"learning_rate": 4.158954086461603e-06,
|
331 |
+
"loss": 0.6077,
|
332 |
+
"step": 450
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.049002849002849,
|
336 |
+
"grad_norm": 0.3279808548257942,
|
337 |
+
"learning_rate": 4.108665093549844e-06,
|
338 |
+
"loss": 0.6014,
|
339 |
+
"step": 460
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 1.0717948717948718,
|
343 |
+
"grad_norm": 0.2800454775432525,
|
344 |
+
"learning_rate": 4.057239769613827e-06,
|
345 |
+
"loss": 0.6023,
|
346 |
+
"step": 470
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 1.0945868945868946,
|
350 |
+
"grad_norm": 0.29883377707281294,
|
351 |
+
"learning_rate": 4.004714440543418e-06,
|
352 |
+
"loss": 0.6098,
|
353 |
+
"step": 480
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 1.1173789173789175,
|
357 |
+
"grad_norm": 0.3092428877092738,
|
358 |
+
"learning_rate": 3.951126209251599e-06,
|
359 |
+
"loss": 0.6148,
|
360 |
+
"step": 490
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 1.1401709401709401,
|
364 |
+
"grad_norm": 0.27196645349799226,
|
365 |
+
"learning_rate": 3.8965129294656586e-06,
|
366 |
+
"loss": 0.6046,
|
367 |
+
"step": 500
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 1.162962962962963,
|
371 |
+
"grad_norm": 0.31199904774590587,
|
372 |
+
"learning_rate": 3.84091317898803e-06,
|
373 |
+
"loss": 0.6023,
|
374 |
+
"step": 510
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.1857549857549858,
|
378 |
+
"grad_norm": 0.3074229624216695,
|
379 |
+
"learning_rate": 3.7843662324456465e-06,
|
380 |
+
"loss": 0.6079,
|
381 |
+
"step": 520
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 1.2085470085470085,
|
385 |
+
"grad_norm": 0.28879942705874306,
|
386 |
+
"learning_rate": 3.726912033547076e-06,
|
387 |
+
"loss": 0.6009,
|
388 |
+
"step": 530
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 1.2313390313390313,
|
392 |
+
"grad_norm": 0.29573529015381267,
|
393 |
+
"learning_rate": 3.668591166867035e-06,
|
394 |
+
"loss": 0.6111,
|
395 |
+
"step": 540
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 1.2541310541310542,
|
399 |
+
"grad_norm": 0.2943249221910953,
|
400 |
+
"learning_rate": 3.6094448291781992e-06,
|
401 |
+
"loss": 0.6075,
|
402 |
+
"step": 550
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 1.2769230769230768,
|
406 |
+
"grad_norm": 0.2913348604970632,
|
407 |
+
"learning_rate": 3.549514800350572e-06,
|
408 |
+
"loss": 0.6091,
|
409 |
+
"step": 560
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 1.2997150997150997,
|
413 |
+
"grad_norm": 0.30264400504017175,
|
414 |
+
"learning_rate": 3.488843413838963e-06,
|
415 |
+
"loss": 0.6029,
|
416 |
+
"step": 570
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.3225071225071225,
|
420 |
+
"grad_norm": 0.2662727717857523,
|
421 |
+
"learning_rate": 3.4274735267794246e-06,
|
422 |
+
"loss": 0.6013,
|
423 |
+
"step": 580
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 1.3452991452991454,
|
427 |
+
"grad_norm": 0.2681498436832575,
|
428 |
+
"learning_rate": 3.3654484897157717e-06,
|
429 |
+
"loss": 0.6011,
|
430 |
+
"step": 590
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 1.368091168091168,
|
434 |
+
"grad_norm": 0.2984325688299942,
|
435 |
+
"learning_rate": 3.3028121159775658e-06,
|
436 |
+
"loss": 0.6066,
|
437 |
+
"step": 600
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 1.390883190883191,
|
441 |
+
"grad_norm": 0.2976332928085903,
|
442 |
+
"learning_rate": 3.239608650731193e-06,
|
443 |
+
"loss": 0.6066,
|
444 |
+
"step": 610
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 1.4136752136752135,
|
448 |
+
"grad_norm": 0.2944058336808568,
|
449 |
+
"learning_rate": 3.1758827397259078e-06,
|
450 |
+
"loss": 0.6093,
|
451 |
+
"step": 620
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 1.4364672364672364,
|
455 |
+
"grad_norm": 0.28155079188959703,
|
456 |
+
"learning_rate": 3.111679397756906e-06,
|
457 |
+
"loss": 0.607,
|
458 |
+
"step": 630
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.4592592592592593,
|
462 |
+
"grad_norm": 0.29389202117647023,
|
463 |
+
"learning_rate": 3.0470439768677116e-06,
|
464 |
+
"loss": 0.6018,
|
465 |
+
"step": 640
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.4820512820512821,
|
469 |
+
"grad_norm": 0.29252690351217875,
|
470 |
+
"learning_rate": 2.982022134314344e-06,
|
471 |
+
"loss": 0.5996,
|
472 |
+
"step": 650
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 1.504843304843305,
|
476 |
+
"grad_norm": 0.2750049021563567,
|
477 |
+
"learning_rate": 2.9166598003138768e-06,
|
478 |
+
"loss": 0.5995,
|
479 |
+
"step": 660
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 1.5276353276353276,
|
483 |
+
"grad_norm": 0.294567165891501,
|
484 |
+
"learning_rate": 2.8510031456001946e-06,
|
485 |
+
"loss": 0.607,
|
486 |
+
"step": 670
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 1.5504273504273505,
|
490 |
+
"grad_norm": 0.2653990825203286,
|
491 |
+
"learning_rate": 2.785098548809844e-06,
|
492 |
+
"loss": 0.5956,
|
493 |
+
"step": 680
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 1.573219373219373,
|
497 |
+
"grad_norm": 0.32424963851879257,
|
498 |
+
"learning_rate": 2.7189925637210325e-06,
|
499 |
+
"loss": 0.5994,
|
500 |
+
"step": 690
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 1.596011396011396,
|
504 |
+
"grad_norm": 0.28116188877931586,
|
505 |
+
"learning_rate": 2.652731886368906e-06,
|
506 |
+
"loss": 0.6152,
|
507 |
+
"step": 700
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 1.6188034188034188,
|
511 |
+
"grad_norm": 0.289124746715315,
|
512 |
+
"learning_rate": 2.586363322060339e-06,
|
513 |
+
"loss": 0.6022,
|
514 |
+
"step": 710
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 1.6415954415954417,
|
518 |
+
"grad_norm": 0.2896827266034778,
|
519 |
+
"learning_rate": 2.519933752311542e-06,
|
520 |
+
"loss": 0.6066,
|
521 |
+
"step": 720
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 1.6643874643874645,
|
525 |
+
"grad_norm": 0.292122351078682,
|
526 |
+
"learning_rate": 2.4534901017318296e-06,
|
527 |
+
"loss": 0.5995,
|
528 |
+
"step": 730
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 1.6871794871794872,
|
532 |
+
"grad_norm": 0.28733382706761834,
|
533 |
+
"learning_rate": 2.387079304876954e-06,
|
534 |
+
"loss": 0.6006,
|
535 |
+
"step": 740
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 1.7099715099715098,
|
539 |
+
"grad_norm": 0.28600009597025633,
|
540 |
+
"learning_rate": 2.3207482730954066e-06,
|
541 |
+
"loss": 0.5978,
|
542 |
+
"step": 750
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 1.7327635327635327,
|
546 |
+
"grad_norm": 0.28872990570576484,
|
547 |
+
"learning_rate": 2.2545438613911212e-06,
|
548 |
+
"loss": 0.602,
|
549 |
+
"step": 760
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 1.7555555555555555,
|
553 |
+
"grad_norm": 0.2898958466462769,
|
554 |
+
"learning_rate": 2.1885128353259687e-06,
|
555 |
+
"loss": 0.5985,
|
556 |
+
"step": 770
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 1.7783475783475784,
|
560 |
+
"grad_norm": 0.28131336352135394,
|
561 |
+
"learning_rate": 2.1227018379854384e-06,
|
562 |
+
"loss": 0.6056,
|
563 |
+
"step": 780
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 1.8011396011396013,
|
567 |
+
"grad_norm": 0.2712379996070474,
|
568 |
+
"learning_rate": 2.0571573570308296e-06,
|
569 |
+
"loss": 0.603,
|
570 |
+
"step": 790
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 1.823931623931624,
|
574 |
+
"grad_norm": 0.2790752087160646,
|
575 |
+
"learning_rate": 1.9919256918612407e-06,
|
576 |
+
"loss": 0.5898,
|
577 |
+
"step": 800
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 1.8467236467236468,
|
581 |
+
"grad_norm": 0.29154871136330335,
|
582 |
+
"learning_rate": 1.927052920908528e-06,
|
583 |
+
"loss": 0.5977,
|
584 |
+
"step": 810
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 1.8695156695156694,
|
588 |
+
"grad_norm": 0.277334855491975,
|
589 |
+
"learning_rate": 1.8625848690883686e-06,
|
590 |
+
"loss": 0.5954,
|
591 |
+
"step": 820
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 1.8923076923076922,
|
595 |
+
"grad_norm": 0.27268605650616284,
|
596 |
+
"learning_rate": 1.7985670754303907e-06,
|
597 |
+
"loss": 0.5992,
|
598 |
+
"step": 830
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 1.915099715099715,
|
602 |
+
"grad_norm": 0.2844929476101612,
|
603 |
+
"learning_rate": 1.7350447609102513e-06,
|
604 |
+
"loss": 0.6038,
|
605 |
+
"step": 840
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 1.937891737891738,
|
609 |
+
"grad_norm": 0.28770081260298885,
|
610 |
+
"learning_rate": 1.6720627965063876e-06,
|
611 |
+
"loss": 0.6018,
|
612 |
+
"step": 850
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 1.9606837606837608,
|
616 |
+
"grad_norm": 0.27708084645145203,
|
617 |
+
"learning_rate": 1.6096656715039868e-06,
|
618 |
+
"loss": 0.603,
|
619 |
+
"step": 860
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 1.9834757834757835,
|
623 |
+
"grad_norm": 0.2975526235682639,
|
624 |
+
"learning_rate": 1.5478974620685922e-06,
|
625 |
+
"loss": 0.6006,
|
626 |
+
"step": 870
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 1.9994301994301993,
|
630 |
+
"eval_loss": 0.6204226016998291,
|
631 |
+
"eval_runtime": 442.6386,
|
632 |
+
"eval_samples_per_second": 26.71,
|
633 |
+
"eval_steps_per_second": 0.418,
|
634 |
+
"step": 877
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 2.006837606837607,
|
638 |
+
"grad_norm": 0.2660113640695103,
|
639 |
+
"learning_rate": 1.4868018001115166e-06,
|
640 |
+
"loss": 0.6233,
|
641 |
+
"step": 880
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 2.0296296296296297,
|
645 |
+
"grad_norm": 0.28026483024484405,
|
646 |
+
"learning_rate": 1.4264218424690759e-06,
|
647 |
+
"loss": 0.5696,
|
648 |
+
"step": 890
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 2.0524216524216525,
|
652 |
+
"grad_norm": 0.28181694489301495,
|
653 |
+
"learning_rate": 1.3668002404174047e-06,
|
654 |
+
"loss": 0.5855,
|
655 |
+
"step": 900
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 2.0752136752136754,
|
659 |
+
"grad_norm": 0.28298520415629186,
|
660 |
+
"learning_rate": 1.307979109544388e-06,
|
661 |
+
"loss": 0.5834,
|
662 |
+
"step": 910
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 2.098005698005698,
|
666 |
+
"grad_norm": 0.2704142615239853,
|
667 |
+
"learning_rate": 1.2500000000000007e-06,
|
668 |
+
"loss": 0.5865,
|
669 |
+
"step": 920
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 2.1207977207977207,
|
673 |
+
"grad_norm": 0.2711904141610201,
|
674 |
+
"learning_rate": 1.1929038671460486e-06,
|
675 |
+
"loss": 0.584,
|
676 |
+
"step": 930
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 2.1435897435897435,
|
680 |
+
"grad_norm": 0.28015029336959785,
|
681 |
+
"learning_rate": 1.136731042626073e-06,
|
682 |
+
"loss": 0.5787,
|
683 |
+
"step": 940
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 2.1663817663817664,
|
687 |
+
"grad_norm": 0.2705809516221485,
|
688 |
+
"learning_rate": 1.0815212058758218e-06,
|
689 |
+
"loss": 0.5796,
|
690 |
+
"step": 950
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 2.1891737891737892,
|
694 |
+
"grad_norm": 0.27273162517988947,
|
695 |
+
"learning_rate": 1.0273133560944432e-06,
|
696 |
+
"loss": 0.5845,
|
697 |
+
"step": 960
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 2.211965811965812,
|
701 |
+
"grad_norm": 0.2830067338695591,
|
702 |
+
"learning_rate": 9.741457846961721e-07,
|
703 |
+
"loss": 0.5833,
|
704 |
+
"step": 970
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 2.234757834757835,
|
708 |
+
"grad_norm": 0.28075024037195573,
|
709 |
+
"learning_rate": 9.220560482619956e-07,
|
710 |
+
"loss": 0.573,
|
711 |
+
"step": 980
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 2.2575498575498574,
|
715 |
+
"grad_norm": 0.27521631417439996,
|
716 |
+
"learning_rate": 8.710809420103788e-07,
|
717 |
+
"loss": 0.5819,
|
718 |
+
"step": 990
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 2.2803418803418802,
|
722 |
+
"grad_norm": 0.2641332093050321,
|
723 |
+
"learning_rate": 8.21256473805811e-07,
|
724 |
+
"loss": 0.5821,
|
725 |
+
"step": 1000
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 2.303133903133903,
|
729 |
+
"grad_norm": 0.28140142311128546,
|
730 |
+
"learning_rate": 7.726178387235234e-07,
|
731 |
+
"loss": 0.5796,
|
732 |
+
"step": 1010
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 2.325925925925926,
|
736 |
+
"grad_norm": 0.2813678146041498,
|
737 |
+
"learning_rate": 7.251993941883428e-07,
|
738 |
+
"loss": 0.5825,
|
739 |
+
"step": 1020
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 2.348717948717949,
|
743 |
+
"grad_norm": 0.26733817473037325,
|
744 |
+
"learning_rate": 6.790346357052443e-07,
|
745 |
+
"loss": 0.584,
|
746 |
+
"step": 1030
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 2.3715099715099717,
|
750 |
+
"grad_norm": 0.2604883848198127,
|
751 |
+
"learning_rate": 6.341561731987572e-07,
|
752 |
+
"loss": 0.5816,
|
753 |
+
"step": 1040
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 2.394301994301994,
|
757 |
+
"grad_norm": 0.289012080255221,
|
758 |
+
"learning_rate": 5.905957079779187e-07,
|
759 |
+
"loss": 0.5808,
|
760 |
+
"step": 1050
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 2.417094017094017,
|
764 |
+
"grad_norm": 0.2695833722813263,
|
765 |
+
"learning_rate": 5.483840103430599e-07,
|
766 |
+
"loss": 0.589,
|
767 |
+
"step": 1060
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 2.43988603988604,
|
771 |
+
"grad_norm": 0.26691946928176913,
|
772 |
+
"learning_rate": 5.0755089785024e-07,
|
773 |
+
"loss": 0.5922,
|
774 |
+
"step": 1070
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 2.4626780626780627,
|
778 |
+
"grad_norm": 0.26813063058675607,
|
779 |
+
"learning_rate": 4.6812521424868416e-07,
|
780 |
+
"loss": 0.5874,
|
781 |
+
"step": 1080
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 2.4854700854700855,
|
785 |
+
"grad_norm": 0.2638423364986993,
|
786 |
+
"learning_rate": 4.301348091060906e-07,
|
787 |
+
"loss": 0.5847,
|
788 |
+
"step": 1090
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 2.5082621082621084,
|
792 |
+
"grad_norm": 0.28075479357187255,
|
793 |
+
"learning_rate": 3.936065181362211e-07,
|
794 |
+
"loss": 0.5914,
|
795 |
+
"step": 1100
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 2.5310541310541312,
|
799 |
+
"grad_norm": 0.26465289459340213,
|
800 |
+
"learning_rate": 3.585661442426494e-07,
|
801 |
+
"loss": 0.5844,
|
802 |
+
"step": 1110
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 2.5538461538461537,
|
806 |
+
"grad_norm": 0.260920376837073,
|
807 |
+
"learning_rate": 3.250384392920741e-07,
|
808 |
+
"loss": 0.5826,
|
809 |
+
"step": 1120
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 2.5766381766381765,
|
813 |
+
"grad_norm": 0.26750993710726595,
|
814 |
+
"learning_rate": 2.930470866300583e-07,
|
815 |
+
"loss": 0.5819,
|
816 |
+
"step": 1130
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 2.5994301994301994,
|
820 |
+
"grad_norm": 0.2622362163032793,
|
821 |
+
"learning_rate": 2.626146843515598e-07,
|
822 |
+
"loss": 0.5816,
|
823 |
+
"step": 1140
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 2.6222222222222222,
|
827 |
+
"grad_norm": 0.2707711955951654,
|
828 |
+
"learning_rate": 2.3376272933805482e-07,
|
829 |
+
"loss": 0.5817,
|
830 |
+
"step": 1150
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 2.645014245014245,
|
834 |
+
"grad_norm": 0.27125876578009134,
|
835 |
+
"learning_rate": 2.065116020725433e-07,
|
836 |
+
"loss": 0.5824,
|
837 |
+
"step": 1160
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 2.667806267806268,
|
841 |
+
"grad_norm": 0.2697526018968707,
|
842 |
+
"learning_rate": 1.80880552243157e-07,
|
843 |
+
"loss": 0.5858,
|
844 |
+
"step": 1170
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 2.690598290598291,
|
848 |
+
"grad_norm": 0.2617655076275081,
|
849 |
+
"learning_rate": 1.5688768514553587e-07,
|
850 |
+
"loss": 0.5808,
|
851 |
+
"step": 1180
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 2.7133903133903132,
|
855 |
+
"grad_norm": 0.25665192252847907,
|
856 |
+
"learning_rate": 1.345499488935875e-07,
|
857 |
+
"loss": 0.5817,
|
858 |
+
"step": 1190
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 2.736182336182336,
|
862 |
+
"grad_norm": 0.264271353582254,
|
863 |
+
"learning_rate": 1.1388312244765332e-07,
|
864 |
+
"loss": 0.5849,
|
865 |
+
"step": 1200
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 2.758974358974359,
|
869 |
+
"grad_norm": 0.25635457369854714,
|
870 |
+
"learning_rate": 9.490180446854791e-08,
|
871 |
+
"loss": 0.5881,
|
872 |
+
"step": 1210
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 2.781766381766382,
|
876 |
+
"grad_norm": 0.2608245013747383,
|
877 |
+
"learning_rate": 7.7619403005334e-08,
|
878 |
+
"loss": 0.5778,
|
879 |
+
"step": 1220
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 2.8045584045584047,
|
883 |
+
"grad_norm": 0.2520807093959864,
|
884 |
+
"learning_rate": 6.204812602412901e-08,
|
885 |
+
"loss": 0.5763,
|
886 |
+
"step": 1230
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 2.827350427350427,
|
890 |
+
"grad_norm": 0.2587943339148964,
|
891 |
+
"learning_rate": 4.8198972784625205e-08,
|
892 |
+
"loss": 0.5913,
|
893 |
+
"step": 1240
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 2.8501424501424504,
|
897 |
+
"grad_norm": 0.26075750237607453,
|
898 |
+
"learning_rate": 3.608172607041632e-08,
|
899 |
+
"loss": 0.5882,
|
900 |
+
"step": 1250
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 2.872934472934473,
|
904 |
+
"grad_norm": 0.26447256486892573,
|
905 |
+
"learning_rate": 2.5704945278623438e-08,
|
906 |
+
"loss": 0.5852,
|
907 |
+
"step": 1260
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 2.8957264957264957,
|
911 |
+
"grad_norm": 0.2675763366142142,
|
912 |
+
"learning_rate": 1.7075960373695022e-08,
|
913 |
+
"loss": 0.5861,
|
914 |
+
"step": 1270
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 2.9185185185185185,
|
918 |
+
"grad_norm": 0.2625544683764617,
|
919 |
+
"learning_rate": 1.0200866709657863e-08,
|
920 |
+
"loss": 0.5763,
|
921 |
+
"step": 1280
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 2.9413105413105414,
|
925 |
+
"grad_norm": 0.2636204922137769,
|
926 |
+
"learning_rate": 5.08452072447152e-09,
|
927 |
+
"loss": 0.5762,
|
928 |
+
"step": 1290
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 2.9641025641025642,
|
932 |
+
"grad_norm": 0.2680005327249821,
|
933 |
+
"learning_rate": 1.7305365095324211e-09,
|
934 |
+
"loss": 0.5775,
|
935 |
+
"step": 1300
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 2.9868945868945866,
|
939 |
+
"grad_norm": 0.269400024292336,
|
940 |
+
"learning_rate": 1.412832567460054e-10,
|
941 |
+
"loss": 0.5877,
|
942 |
+
"step": 1310
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 2.996011396011396,
|
946 |
+
"eval_loss": 0.6208292245864868,
|
947 |
+
"eval_runtime": 441.8042,
|
948 |
+
"eval_samples_per_second": 26.761,
|
949 |
+
"eval_steps_per_second": 0.419,
|
950 |
+
"step": 1314
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 2.996011396011396,
|
954 |
+
"step": 1314,
|
955 |
+
"total_flos": 2755219238682624.0,
|
956 |
+
"train_loss": 0.6149487337565314,
|
957 |
+
"train_runtime": 70718.2917,
|
958 |
+
"train_samples_per_second": 9.529,
|
959 |
+
"train_steps_per_second": 0.019
|
960 |
+
}
|
961 |
+
],
|
962 |
+
"logging_steps": 10,
|
963 |
+
"max_steps": 1314,
|
964 |
+
"num_input_tokens_seen": 0,
|
965 |
+
"num_train_epochs": 3,
|
966 |
+
"save_steps": 500,
|
967 |
+
"stateful_callbacks": {
|
968 |
+
"TrainerControl": {
|
969 |
+
"args": {
|
970 |
+
"should_epoch_stop": false,
|
971 |
+
"should_evaluate": false,
|
972 |
+
"should_log": false,
|
973 |
+
"should_save": true,
|
974 |
+
"should_training_stop": true
|
975 |
+
},
|
976 |
+
"attributes": {}
|
977 |
+
}
|
978 |
+
},
|
979 |
+
"total_flos": 2755219238682624.0,
|
980 |
+
"train_batch_size": 8,
|
981 |
+
"trial_name": null,
|
982 |
+
"trial_params": null
|
983 |
+
}
|
training_eval_loss.png
ADDED
training_loss.png
ADDED