sedrickkeh
commited on
Commit
•
7ffcbd2
1
Parent(s):
ddb520e
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_inverse_sqrt
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# hp_ablations_qwen_scheduler_inverse_sqrt
|
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: 0.6186
|
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_inverse_sqrt
|
|
|
16 |
|
17 |
# hp_ablations_qwen_scheduler_inverse_sqrt
|
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: 0.6186
|
22 |
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.996011396011396,
|
3 |
+
"eval_loss": 0.6186444163322449,
|
4 |
+
"eval_runtime": 442.2425,
|
5 |
+
"eval_samples_per_second": 26.734,
|
6 |
+
"eval_steps_per_second": 0.418,
|
7 |
+
"total_flos": 2755219238682624.0,
|
8 |
+
"train_loss": 0.604149692316215,
|
9 |
+
"train_runtime": 70723.2043,
|
10 |
+
"train_samples_per_second": 9.528,
|
11 |
+
"train_steps_per_second": 0.019
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.996011396011396,
|
3 |
+
"eval_loss": 0.6186444163322449,
|
4 |
+
"eval_runtime": 442.2425,
|
5 |
+
"eval_samples_per_second": 26.734,
|
6 |
+
"eval_steps_per_second": 0.418
|
7 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.996011396011396,
|
3 |
+
"total_flos": 2755219238682624.0,
|
4 |
+
"train_loss": 0.604149692316215,
|
5 |
+
"train_runtime": 70723.2043,
|
6 |
+
"train_samples_per_second": 9.528,
|
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": 1.525165904903376,
|
14 |
+
"learning_rate": 4.997501873438867e-06,
|
15 |
+
"loss": 0.7554,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.045584045584045586,
|
20 |
+
"grad_norm": 0.8053498795260766,
|
21 |
+
"learning_rate": 4.995007487521836e-06,
|
22 |
+
"loss": 0.7012,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.06837606837606838,
|
27 |
+
"grad_norm": 0.9238843089964248,
|
28 |
+
"learning_rate": 4.992516832922945e-06,
|
29 |
+
"loss": 0.6799,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.09116809116809117,
|
34 |
+
"grad_norm": 0.8666218585982866,
|
35 |
+
"learning_rate": 4.990029900348746e-06,
|
36 |
+
"loss": 0.6795,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.11396011396011396,
|
41 |
+
"grad_norm": 0.8088508819396967,
|
42 |
+
"learning_rate": 4.987546680538165e-06,
|
43 |
+
"loss": 0.6755,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.13675213675213677,
|
48 |
+
"grad_norm": 0.6691655296371665,
|
49 |
+
"learning_rate": 4.985067164262359e-06,
|
50 |
+
"loss": 0.655,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.15954415954415954,
|
55 |
+
"grad_norm": 0.43456809500231514,
|
56 |
+
"learning_rate": 4.98259134232457e-06,
|
57 |
+
"loss": 0.6519,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.18233618233618235,
|
62 |
+
"grad_norm": 0.3714072334118622,
|
63 |
+
"learning_rate": 4.980119205559974e-06,
|
64 |
+
"loss": 0.6549,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.20512820512820512,
|
69 |
+
"grad_norm": 0.32002706744599263,
|
70 |
+
"learning_rate": 4.977650744835555e-06,
|
71 |
+
"loss": 0.6397,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.22792022792022792,
|
76 |
+
"grad_norm": 0.30081132793404947,
|
77 |
+
"learning_rate": 4.975185951049947e-06,
|
78 |
+
"loss": 0.641,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.25071225071225073,
|
83 |
+
"grad_norm": 0.33713425539947894,
|
84 |
+
"learning_rate": 4.972724815133302e-06,
|
85 |
+
"loss": 0.6323,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.27350427350427353,
|
90 |
+
"grad_norm": 0.3102451954821332,
|
91 |
+
"learning_rate": 4.970267328047151e-06,
|
92 |
+
"loss": 0.6406,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.2962962962962963,
|
97 |
+
"grad_norm": 0.29069740779199893,
|
98 |
+
"learning_rate": 4.9678134807842575e-06,
|
99 |
+
"loss": 0.6416,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.3190883190883191,
|
104 |
+
"grad_norm": 0.31110922605055114,
|
105 |
+
"learning_rate": 4.965363264368484e-06,
|
106 |
+
"loss": 0.6437,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.3418803418803419,
|
111 |
+
"grad_norm": 0.30841690869415606,
|
112 |
+
"learning_rate": 4.962916669854652e-06,
|
113 |
+
"loss": 0.6362,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.3646723646723647,
|
118 |
+
"grad_norm": 0.3100448846559202,
|
119 |
+
"learning_rate": 4.960473688328407e-06,
|
120 |
+
"loss": 0.6414,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.38746438746438744,
|
125 |
+
"grad_norm": 0.3488301271178644,
|
126 |
+
"learning_rate": 4.95803431090608e-06,
|
127 |
+
"loss": 0.6332,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.41025641025641024,
|
132 |
+
"grad_norm": 0.29863658820743894,
|
133 |
+
"learning_rate": 4.955598528734554e-06,
|
134 |
+
"loss": 0.6387,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.43304843304843305,
|
139 |
+
"grad_norm": 0.3039290966360699,
|
140 |
+
"learning_rate": 4.953166332991125e-06,
|
141 |
+
"loss": 0.6313,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.45584045584045585,
|
146 |
+
"grad_norm": 0.30706559541216405,
|
147 |
+
"learning_rate": 4.950737714883372e-06,
|
148 |
+
"loss": 0.6394,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.47863247863247865,
|
153 |
+
"grad_norm": 0.3082675137287457,
|
154 |
+
"learning_rate": 4.948312665649022e-06,
|
155 |
+
"loss": 0.6357,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.5014245014245015,
|
160 |
+
"grad_norm": 0.30127921218162695,
|
161 |
+
"learning_rate": 4.945891176555817e-06,
|
162 |
+
"loss": 0.6394,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.5242165242165242,
|
167 |
+
"grad_norm": 0.3196585894616986,
|
168 |
+
"learning_rate": 4.943473238901383e-06,
|
169 |
+
"loss": 0.635,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.5470085470085471,
|
174 |
+
"grad_norm": 0.30078793486520006,
|
175 |
+
"learning_rate": 4.941058844013094e-06,
|
176 |
+
"loss": 0.6309,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.5698005698005698,
|
181 |
+
"grad_norm": 0.33427271614606124,
|
182 |
+
"learning_rate": 4.938647983247949e-06,
|
183 |
+
"loss": 0.6358,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.5925925925925926,
|
188 |
+
"grad_norm": 0.3016972471723858,
|
189 |
+
"learning_rate": 4.936240647992436e-06,
|
190 |
+
"loss": 0.634,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.6153846153846154,
|
195 |
+
"grad_norm": 0.3115162799082423,
|
196 |
+
"learning_rate": 4.933836829662409e-06,
|
197 |
+
"loss": 0.6312,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.6381766381766382,
|
202 |
+
"grad_norm": 0.3256775803287148,
|
203 |
+
"learning_rate": 4.9314365197029475e-06,
|
204 |
+
"loss": 0.642,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.6609686609686609,
|
209 |
+
"grad_norm": 0.3189814595928396,
|
210 |
+
"learning_rate": 4.9290397095882446e-06,
|
211 |
+
"loss": 0.6306,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.6837606837606838,
|
216 |
+
"grad_norm": 0.29642424266007356,
|
217 |
+
"learning_rate": 4.9266463908214664e-06,
|
218 |
+
"loss": 0.6287,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.7065527065527065,
|
223 |
+
"grad_norm": 0.29650226463241985,
|
224 |
+
"learning_rate": 4.924256554934632e-06,
|
225 |
+
"loss": 0.6285,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.7293447293447294,
|
230 |
+
"grad_norm": 0.3429160287206981,
|
231 |
+
"learning_rate": 4.9218701934884865e-06,
|
232 |
+
"loss": 0.6291,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.7521367521367521,
|
237 |
+
"grad_norm": 0.30230466534717343,
|
238 |
+
"learning_rate": 4.919487298072377e-06,
|
239 |
+
"loss": 0.6258,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.7749287749287749,
|
244 |
+
"grad_norm": 0.34202573052544266,
|
245 |
+
"learning_rate": 4.917107860304125e-06,
|
246 |
+
"loss": 0.6316,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.7977207977207977,
|
251 |
+
"grad_norm": 0.33516486005488866,
|
252 |
+
"learning_rate": 4.914731871829905e-06,
|
253 |
+
"loss": 0.6387,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.8205128205128205,
|
258 |
+
"grad_norm": 0.3211212871249072,
|
259 |
+
"learning_rate": 4.912359324324121e-06,
|
260 |
+
"loss": 0.6304,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.8433048433048433,
|
265 |
+
"grad_norm": 0.322137683454166,
|
266 |
+
"learning_rate": 4.909990209489284e-06,
|
267 |
+
"loss": 0.6242,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.8660968660968661,
|
272 |
+
"grad_norm": 0.31550278369753354,
|
273 |
+
"learning_rate": 4.907624519055888e-06,
|
274 |
+
"loss": 0.6365,
|
275 |
+
"step": 380
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.8888888888888888,
|
279 |
+
"grad_norm": 0.3260141043187448,
|
280 |
+
"learning_rate": 4.905262244782294e-06,
|
281 |
+
"loss": 0.6351,
|
282 |
+
"step": 390
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.9116809116809117,
|
286 |
+
"grad_norm": 0.3040813959954933,
|
287 |
+
"learning_rate": 4.902903378454601e-06,
|
288 |
+
"loss": 0.6383,
|
289 |
+
"step": 400
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.9344729344729344,
|
293 |
+
"grad_norm": 0.2849114973684705,
|
294 |
+
"learning_rate": 4.900547911886537e-06,
|
295 |
+
"loss": 0.6345,
|
296 |
+
"step": 410
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.9572649572649573,
|
300 |
+
"grad_norm": 0.2972340394377098,
|
301 |
+
"learning_rate": 4.898195836919327e-06,
|
302 |
+
"loss": 0.6214,
|
303 |
+
"step": 420
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.98005698005698,
|
307 |
+
"grad_norm": 0.34508028269623636,
|
308 |
+
"learning_rate": 4.895847145421587e-06,
|
309 |
+
"loss": 0.6344,
|
310 |
+
"step": 430
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.9982905982905983,
|
314 |
+
"eval_loss": 0.6250626444816589,
|
315 |
+
"eval_runtime": 441.6427,
|
316 |
+
"eval_samples_per_second": 26.771,
|
317 |
+
"eval_steps_per_second": 0.419,
|
318 |
+
"step": 438
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 1.0034188034188034,
|
322 |
+
"grad_norm": 0.3476146349698735,
|
323 |
+
"learning_rate": 4.893501829289195e-06,
|
324 |
+
"loss": 0.6472,
|
325 |
+
"step": 440
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 1.0262108262108263,
|
329 |
+
"grad_norm": 0.3276756414551046,
|
330 |
+
"learning_rate": 4.891159880445185e-06,
|
331 |
+
"loss": 0.6016,
|
332 |
+
"step": 450
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.049002849002849,
|
336 |
+
"grad_norm": 0.3019871041088552,
|
337 |
+
"learning_rate": 4.888821290839617e-06,
|
338 |
+
"loss": 0.5954,
|
339 |
+
"step": 460
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 1.0717948717948718,
|
343 |
+
"grad_norm": 0.29126627395932514,
|
344 |
+
"learning_rate": 4.886486052449469e-06,
|
345 |
+
"loss": 0.5963,
|
346 |
+
"step": 470
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 1.0945868945868946,
|
350 |
+
"grad_norm": 0.30453199438005507,
|
351 |
+
"learning_rate": 4.8841541572785224e-06,
|
352 |
+
"loss": 0.6038,
|
353 |
+
"step": 480
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 1.1173789173789175,
|
357 |
+
"grad_norm": 0.3278803012067222,
|
358 |
+
"learning_rate": 4.881825597357242e-06,
|
359 |
+
"loss": 0.6089,
|
360 |
+
"step": 490
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 1.1401709401709401,
|
364 |
+
"grad_norm": 0.2965789673527869,
|
365 |
+
"learning_rate": 4.8795003647426654e-06,
|
366 |
+
"loss": 0.5987,
|
367 |
+
"step": 500
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 1.162962962962963,
|
371 |
+
"grad_norm": 0.31265022709916646,
|
372 |
+
"learning_rate": 4.877178451518289e-06,
|
373 |
+
"loss": 0.5966,
|
374 |
+
"step": 510
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.1857549857549858,
|
378 |
+
"grad_norm": 0.3006543348402962,
|
379 |
+
"learning_rate": 4.8748598497939494e-06,
|
380 |
+
"loss": 0.6023,
|
381 |
+
"step": 520
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 1.2085470085470085,
|
385 |
+
"grad_norm": 0.32429016802211824,
|
386 |
+
"learning_rate": 4.872544551705718e-06,
|
387 |
+
"loss": 0.5953,
|
388 |
+
"step": 530
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 1.2313390313390313,
|
392 |
+
"grad_norm": 0.29037801778251926,
|
393 |
+
"learning_rate": 4.870232549415787e-06,
|
394 |
+
"loss": 0.6056,
|
395 |
+
"step": 540
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 1.2541310541310542,
|
399 |
+
"grad_norm": 0.3348609323819345,
|
400 |
+
"learning_rate": 4.867923835112355e-06,
|
401 |
+
"loss": 0.6021,
|
402 |
+
"step": 550
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 1.2769230769230768,
|
406 |
+
"grad_norm": 0.2831871289987126,
|
407 |
+
"learning_rate": 4.865618401009519e-06,
|
408 |
+
"loss": 0.6037,
|
409 |
+
"step": 560
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 1.2997150997150997,
|
413 |
+
"grad_norm": 0.3006000412993847,
|
414 |
+
"learning_rate": 4.863316239347163e-06,
|
415 |
+
"loss": 0.5977,
|
416 |
+
"step": 570
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.3225071225071225,
|
420 |
+
"grad_norm": 0.27196198233146873,
|
421 |
+
"learning_rate": 4.861017342390847e-06,
|
422 |
+
"loss": 0.5962,
|
423 |
+
"step": 580
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 1.3452991452991454,
|
427 |
+
"grad_norm": 0.2967670383985263,
|
428 |
+
"learning_rate": 4.858721702431704e-06,
|
429 |
+
"loss": 0.5959,
|
430 |
+
"step": 590
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 1.368091168091168,
|
434 |
+
"grad_norm": 0.342796374484054,
|
435 |
+
"learning_rate": 4.856429311786322e-06,
|
436 |
+
"loss": 0.6014,
|
437 |
+
"step": 600
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 1.390883190883191,
|
441 |
+
"grad_norm": 0.3292423768345227,
|
442 |
+
"learning_rate": 4.8541401627966426e-06,
|
443 |
+
"loss": 0.6016,
|
444 |
+
"step": 610
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 1.4136752136752135,
|
448 |
+
"grad_norm": 0.299728514910799,
|
449 |
+
"learning_rate": 4.85185424782985e-06,
|
450 |
+
"loss": 0.6041,
|
451 |
+
"step": 620
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 1.4364672364672364,
|
455 |
+
"grad_norm": 0.30887594524743867,
|
456 |
+
"learning_rate": 4.8495715592782715e-06,
|
457 |
+
"loss": 0.6021,
|
458 |
+
"step": 630
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.4592592592592593,
|
462 |
+
"grad_norm": 0.305132962765952,
|
463 |
+
"learning_rate": 4.847292089559258e-06,
|
464 |
+
"loss": 0.597,
|
465 |
+
"step": 640
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.4820512820512821,
|
469 |
+
"grad_norm": 0.2969561784557187,
|
470 |
+
"learning_rate": 4.845015831115093e-06,
|
471 |
+
"loss": 0.5949,
|
472 |
+
"step": 650
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 1.504843304843305,
|
476 |
+
"grad_norm": 0.2870255011777952,
|
477 |
+
"learning_rate": 4.842742776412874e-06,
|
478 |
+
"loss": 0.5946,
|
479 |
+
"step": 660
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 1.5276353276353276,
|
483 |
+
"grad_norm": 0.3136573065822191,
|
484 |
+
"learning_rate": 4.840472917944417e-06,
|
485 |
+
"loss": 0.6022,
|
486 |
+
"step": 670
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 1.5504273504273505,
|
490 |
+
"grad_norm": 0.2775783004125175,
|
491 |
+
"learning_rate": 4.838206248226147e-06,
|
492 |
+
"loss": 0.5908,
|
493 |
+
"step": 680
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 1.573219373219373,
|
497 |
+
"grad_norm": 0.32400364521332364,
|
498 |
+
"learning_rate": 4.835942759799002e-06,
|
499 |
+
"loss": 0.5947,
|
500 |
+
"step": 690
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 1.596011396011396,
|
504 |
+
"grad_norm": 0.287719331253849,
|
505 |
+
"learning_rate": 4.833682445228318e-06,
|
506 |
+
"loss": 0.6102,
|
507 |
+
"step": 700
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 1.6188034188034188,
|
511 |
+
"grad_norm": 0.3061981877613935,
|
512 |
+
"learning_rate": 4.831425297103738e-06,
|
513 |
+
"loss": 0.5973,
|
514 |
+
"step": 710
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 1.6415954415954417,
|
518 |
+
"grad_norm": 0.2935986527130749,
|
519 |
+
"learning_rate": 4.829171308039099e-06,
|
520 |
+
"loss": 0.6019,
|
521 |
+
"step": 720
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 1.6643874643874645,
|
525 |
+
"grad_norm": 0.3278074868861201,
|
526 |
+
"learning_rate": 4.826920470672344e-06,
|
527 |
+
"loss": 0.595,
|
528 |
+
"step": 730
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 1.6871794871794872,
|
532 |
+
"grad_norm": 0.31438196017683884,
|
533 |
+
"learning_rate": 4.824672777665406e-06,
|
534 |
+
"loss": 0.5961,
|
535 |
+
"step": 740
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 1.7099715099715098,
|
539 |
+
"grad_norm": 0.29590816240567525,
|
540 |
+
"learning_rate": 4.822428221704122e-06,
|
541 |
+
"loss": 0.5935,
|
542 |
+
"step": 750
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 1.7327635327635327,
|
546 |
+
"grad_norm": 0.30748668539068935,
|
547 |
+
"learning_rate": 4.820186795498119e-06,
|
548 |
+
"loss": 0.5974,
|
549 |
+
"step": 760
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 1.7555555555555555,
|
553 |
+
"grad_norm": 0.29187796953262835,
|
554 |
+
"learning_rate": 4.817948491780728e-06,
|
555 |
+
"loss": 0.5938,
|
556 |
+
"step": 770
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 1.7783475783475784,
|
560 |
+
"grad_norm": 0.29933508547691845,
|
561 |
+
"learning_rate": 4.815713303308872e-06,
|
562 |
+
"loss": 0.6009,
|
563 |
+
"step": 780
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 1.8011396011396013,
|
567 |
+
"grad_norm": 0.2964931056797495,
|
568 |
+
"learning_rate": 4.813481222862981e-06,
|
569 |
+
"loss": 0.5985,
|
570 |
+
"step": 790
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 1.823931623931624,
|
574 |
+
"grad_norm": 0.3119877619286405,
|
575 |
+
"learning_rate": 4.811252243246881e-06,
|
576 |
+
"loss": 0.5853,
|
577 |
+
"step": 800
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 1.8467236467236468,
|
581 |
+
"grad_norm": 0.30077090862615286,
|
582 |
+
"learning_rate": 4.809026357287709e-06,
|
583 |
+
"loss": 0.5932,
|
584 |
+
"step": 810
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 1.8695156695156694,
|
588 |
+
"grad_norm": 0.30995473438720483,
|
589 |
+
"learning_rate": 4.806803557835802e-06,
|
590 |
+
"loss": 0.5909,
|
591 |
+
"step": 820
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 1.8923076923076922,
|
595 |
+
"grad_norm": 0.3313446191052585,
|
596 |
+
"learning_rate": 4.804583837764616e-06,
|
597 |
+
"loss": 0.5947,
|
598 |
+
"step": 830
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 1.915099715099715,
|
602 |
+
"grad_norm": 0.30558861743932775,
|
603 |
+
"learning_rate": 4.802367189970616e-06,
|
604 |
+
"loss": 0.5992,
|
605 |
+
"step": 840
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 1.937891737891738,
|
609 |
+
"grad_norm": 0.30382616090223413,
|
610 |
+
"learning_rate": 4.8001536073731936e-06,
|
611 |
+
"loss": 0.5973,
|
612 |
+
"step": 850
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 1.9606837606837608,
|
616 |
+
"grad_norm": 0.311102028704937,
|
617 |
+
"learning_rate": 4.797943082914558e-06,
|
618 |
+
"loss": 0.5986,
|
619 |
+
"step": 860
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 1.9834757834757835,
|
623 |
+
"grad_norm": 0.3331012493756619,
|
624 |
+
"learning_rate": 4.795735609559657e-06,
|
625 |
+
"loss": 0.5961,
|
626 |
+
"step": 870
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 1.9994301994301993,
|
630 |
+
"eval_loss": 0.618708610534668,
|
631 |
+
"eval_runtime": 442.8586,
|
632 |
+
"eval_samples_per_second": 26.697,
|
633 |
+
"eval_steps_per_second": 0.418,
|
634 |
+
"step": 877
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 2.006837606837607,
|
638 |
+
"grad_norm": 0.3512930734127694,
|
639 |
+
"learning_rate": 4.793531180296065e-06,
|
640 |
+
"loss": 0.6157,
|
641 |
+
"step": 880
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 2.0296296296296297,
|
645 |
+
"grad_norm": 0.3599795362623166,
|
646 |
+
"learning_rate": 4.7913297881339085e-06,
|
647 |
+
"loss": 0.5553,
|
648 |
+
"step": 890
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 2.0524216524216525,
|
652 |
+
"grad_norm": 0.3164425885661232,
|
653 |
+
"learning_rate": 4.789131426105757e-06,
|
654 |
+
"loss": 0.5704,
|
655 |
+
"step": 900
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 2.0752136752136754,
|
659 |
+
"grad_norm": 0.36033177622984786,
|
660 |
+
"learning_rate": 4.786936087266542e-06,
|
661 |
+
"loss": 0.5686,
|
662 |
+
"step": 910
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 2.098005698005698,
|
666 |
+
"grad_norm": 0.33104525900123416,
|
667 |
+
"learning_rate": 4.784743764693455e-06,
|
668 |
+
"loss": 0.5717,
|
669 |
+
"step": 920
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 2.1207977207977207,
|
673 |
+
"grad_norm": 0.29338052297451017,
|
674 |
+
"learning_rate": 4.7825544514858655e-06,
|
675 |
+
"loss": 0.5697,
|
676 |
+
"step": 930
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 2.1435897435897435,
|
680 |
+
"grad_norm": 0.30967219938255186,
|
681 |
+
"learning_rate": 4.780368140765222e-06,
|
682 |
+
"loss": 0.5644,
|
683 |
+
"step": 940
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 2.1663817663817664,
|
687 |
+
"grad_norm": 0.3116949593974322,
|
688 |
+
"learning_rate": 4.778184825674966e-06,
|
689 |
+
"loss": 0.5653,
|
690 |
+
"step": 950
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 2.1891737891737892,
|
694 |
+
"grad_norm": 0.305260137885279,
|
695 |
+
"learning_rate": 4.776004499380439e-06,
|
696 |
+
"loss": 0.5703,
|
697 |
+
"step": 960
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 2.211965811965812,
|
701 |
+
"grad_norm": 0.29822541696944915,
|
702 |
+
"learning_rate": 4.773827155068793e-06,
|
703 |
+
"loss": 0.5698,
|
704 |
+
"step": 970
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 2.234757834757835,
|
708 |
+
"grad_norm": 0.2859968833970714,
|
709 |
+
"learning_rate": 4.771652785948902e-06,
|
710 |
+
"loss": 0.5594,
|
711 |
+
"step": 980
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 2.2575498575498574,
|
715 |
+
"grad_norm": 0.3174033757002569,
|
716 |
+
"learning_rate": 4.769481385251275e-06,
|
717 |
+
"loss": 0.5684,
|
718 |
+
"step": 990
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 2.2803418803418802,
|
722 |
+
"grad_norm": 0.31269556215191746,
|
723 |
+
"learning_rate": 4.767312946227961e-06,
|
724 |
+
"loss": 0.5687,
|
725 |
+
"step": 1000
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 2.303133903133903,
|
729 |
+
"grad_norm": 0.3051928602107768,
|
730 |
+
"learning_rate": 4.765147462152471e-06,
|
731 |
+
"loss": 0.5662,
|
732 |
+
"step": 1010
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 2.325925925925926,
|
736 |
+
"grad_norm": 0.31501362221921503,
|
737 |
+
"learning_rate": 4.762984926319677e-06,
|
738 |
+
"loss": 0.5693,
|
739 |
+
"step": 1020
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 2.348717948717949,
|
743 |
+
"grad_norm": 0.3448956830891534,
|
744 |
+
"learning_rate": 4.760825332045738e-06,
|
745 |
+
"loss": 0.5706,
|
746 |
+
"step": 1030
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 2.3715099715099717,
|
750 |
+
"grad_norm": 0.3026934523794964,
|
751 |
+
"learning_rate": 4.758668672668006e-06,
|
752 |
+
"loss": 0.5685,
|
753 |
+
"step": 1040
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 2.394301994301994,
|
757 |
+
"grad_norm": 0.3099921114639337,
|
758 |
+
"learning_rate": 4.756514941544941e-06,
|
759 |
+
"loss": 0.5679,
|
760 |
+
"step": 1050
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 2.417094017094017,
|
764 |
+
"grad_norm": 0.30114216044285347,
|
765 |
+
"learning_rate": 4.754364132056025e-06,
|
766 |
+
"loss": 0.5762,
|
767 |
+
"step": 1060
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 2.43988603988604,
|
771 |
+
"grad_norm": 0.29726040323415187,
|
772 |
+
"learning_rate": 4.752216237601676e-06,
|
773 |
+
"loss": 0.579,
|
774 |
+
"step": 1070
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 2.4626780626780627,
|
778 |
+
"grad_norm": 0.29775393502122444,
|
779 |
+
"learning_rate": 4.750071251603165e-06,
|
780 |
+
"loss": 0.5743,
|
781 |
+
"step": 1080
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 2.4854700854700855,
|
785 |
+
"grad_norm": 0.2943291979563702,
|
786 |
+
"learning_rate": 4.7479291675025314e-06,
|
787 |
+
"loss": 0.5719,
|
788 |
+
"step": 1090
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 2.5082621082621084,
|
792 |
+
"grad_norm": 0.31015578394336496,
|
793 |
+
"learning_rate": 4.745789978762496e-06,
|
794 |
+
"loss": 0.5784,
|
795 |
+
"step": 1100
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 2.5310541310541312,
|
799 |
+
"grad_norm": 0.3067404718121527,
|
800 |
+
"learning_rate": 4.7436536788663765e-06,
|
801 |
+
"loss": 0.5718,
|
802 |
+
"step": 1110
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 2.5538461538461537,
|
806 |
+
"grad_norm": 0.30476772110006034,
|
807 |
+
"learning_rate": 4.74152026131801e-06,
|
808 |
+
"loss": 0.57,
|
809 |
+
"step": 1120
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 2.5766381766381765,
|
813 |
+
"grad_norm": 0.3200412884206867,
|
814 |
+
"learning_rate": 4.739389719641665e-06,
|
815 |
+
"loss": 0.5694,
|
816 |
+
"step": 1130
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 2.5994301994301994,
|
820 |
+
"grad_norm": 0.30781710889202074,
|
821 |
+
"learning_rate": 4.7372620473819615e-06,
|
822 |
+
"loss": 0.5691,
|
823 |
+
"step": 1140
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 2.6222222222222222,
|
827 |
+
"grad_norm": 0.2990058185323815,
|
828 |
+
"learning_rate": 4.735137238103785e-06,
|
829 |
+
"loss": 0.5694,
|
830 |
+
"step": 1150
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 2.645014245014245,
|
834 |
+
"grad_norm": 0.3039158464988474,
|
835 |
+
"learning_rate": 4.7330152853922064e-06,
|
836 |
+
"loss": 0.5705,
|
837 |
+
"step": 1160
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 2.667806267806268,
|
841 |
+
"grad_norm": 0.2968978926486904,
|
842 |
+
"learning_rate": 4.730896182852409e-06,
|
843 |
+
"loss": 0.5733,
|
844 |
+
"step": 1170
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 2.690598290598291,
|
848 |
+
"grad_norm": 0.2952864087104688,
|
849 |
+
"learning_rate": 4.72877992410959e-06,
|
850 |
+
"loss": 0.5684,
|
851 |
+
"step": 1180
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 2.7133903133903132,
|
855 |
+
"grad_norm": 0.288700561234537,
|
856 |
+
"learning_rate": 4.7266665028088985e-06,
|
857 |
+
"loss": 0.5695,
|
858 |
+
"step": 1190
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 2.736182336182336,
|
862 |
+
"grad_norm": 0.29212831117890853,
|
863 |
+
"learning_rate": 4.72455591261534e-06,
|
864 |
+
"loss": 0.5727,
|
865 |
+
"step": 1200
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 2.758974358974359,
|
869 |
+
"grad_norm": 0.28360998087695266,
|
870 |
+
"learning_rate": 4.722448147213712e-06,
|
871 |
+
"loss": 0.5761,
|
872 |
+
"step": 1210
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 2.781766381766382,
|
876 |
+
"grad_norm": 0.2843161577709465,
|
877 |
+
"learning_rate": 4.720343200308507e-06,
|
878 |
+
"loss": 0.5659,
|
879 |
+
"step": 1220
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 2.8045584045584047,
|
883 |
+
"grad_norm": 0.30629830967088484,
|
884 |
+
"learning_rate": 4.7182410656238484e-06,
|
885 |
+
"loss": 0.5644,
|
886 |
+
"step": 1230
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 2.827350427350427,
|
890 |
+
"grad_norm": 0.31248945067389905,
|
891 |
+
"learning_rate": 4.716141736903407e-06,
|
892 |
+
"loss": 0.5792,
|
893 |
+
"step": 1240
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 2.8501424501424504,
|
897 |
+
"grad_norm": 0.2962592773085804,
|
898 |
+
"learning_rate": 4.714045207910318e-06,
|
899 |
+
"loss": 0.5759,
|
900 |
+
"step": 1250
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 2.872934472934473,
|
904 |
+
"grad_norm": 0.2982145036424215,
|
905 |
+
"learning_rate": 4.71195147242711e-06,
|
906 |
+
"loss": 0.573,
|
907 |
+
"step": 1260
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 2.8957264957264957,
|
911 |
+
"grad_norm": 0.30389926739813455,
|
912 |
+
"learning_rate": 4.709860524255622e-06,
|
913 |
+
"loss": 0.574,
|
914 |
+
"step": 1270
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 2.9185185185185185,
|
918 |
+
"grad_norm": 0.28975007917463824,
|
919 |
+
"learning_rate": 4.707772357216934e-06,
|
920 |
+
"loss": 0.5642,
|
921 |
+
"step": 1280
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 2.9413105413105414,
|
925 |
+
"grad_norm": 0.2984479549098159,
|
926 |
+
"learning_rate": 4.705686965151282e-06,
|
927 |
+
"loss": 0.5644,
|
928 |
+
"step": 1290
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 2.9641025641025642,
|
932 |
+
"grad_norm": 0.3364273603754725,
|
933 |
+
"learning_rate": 4.703604341917987e-06,
|
934 |
+
"loss": 0.5655,
|
935 |
+
"step": 1300
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 2.9868945868945866,
|
939 |
+
"grad_norm": 0.30326945997963417,
|
940 |
+
"learning_rate": 4.701524481395374e-06,
|
941 |
+
"loss": 0.5753,
|
942 |
+
"step": 1310
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 2.996011396011396,
|
946 |
+
"eval_loss": 0.6186444163322449,
|
947 |
+
"eval_runtime": 441.5391,
|
948 |
+
"eval_samples_per_second": 26.777,
|
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": 0.604149692316215,
|
957 |
+
"train_runtime": 70723.2043,
|
958 |
+
"train_samples_per_second": 9.528,
|
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